diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..cefe54d867848bc36312e6aa4083712594cc7f2a 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,563 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +model/model/embed_tokens/embedding/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/embed_tokens/embedding/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/embed_tokens/embedding/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/embed_tokens/embedding/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/21/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/13/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/1/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/3/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/4/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/5/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/20/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/18/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/17/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/19/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/10/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/8/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/16/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/11/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/14/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/6/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/23/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/2/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/9/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/22/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/15/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/7/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/0/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/self_attn/v_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/self_attn/v_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/self_attn/v_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/self_attn/q_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/self_attn/q_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/self_attn/q_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/self_attn/o_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/self_attn/o_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/self_attn/o_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/self_attn/k_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/self_attn/k_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/self_attn/k_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text +model/model/layers/12/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/lm_head/kernel/0.1 filter=lfs diff=lfs merge=lfs -text +model/lm_head/kernel/0.3 filter=lfs diff=lfs merge=lfs -text +model/lm_head/kernel/0.0 filter=lfs diff=lfs merge=lfs -text +model/lm_head/kernel/0.2 filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..9e7b56b005122adab840ddf24b8d91e43ad77480 --- /dev/null +++ b/README.md @@ -0,0 +1,123 @@ +--- +tags: +- EasyDeL +- GptOssForCausalLM +- TaskType.CAUSAL_LM +- AttentionMechanisms.RAGGED_PAGE_ATTENTION_V3 +- safetensors +- TPU +- GPU +- XLA +- Flax +--- +

+ + + +

+ +

+ + + + + + +

+ +# EasyDeL/gpt-oss-20b + +A model implemented using the EasyDeL framework, designed to deliver optimal performance for large-scale natural language processing tasks. + +## Overview + +This model is built using [EasyDeL](https://github.com/erfanzar/EasyDeL), an open-source framework designed to enhance and streamline the training and serving process of machine learning models, with a primary focus on Jax/Flax on TPU/GPU at scale. + +EasyDeL provides an efficient, highly-optimized, and customizable machine learning model compatible with both GPU and TPU environments. Built with JAX, this model supports advanced features such as sharded model parallelism, making it suitable for distributed training and inference and customized kernels. + +## Features Provided by EasyDeL + +**EasyDeL Framework Features:** + +- **Efficient Implementation**: Built with JAX/Flax for high-performance computation. +- **Modern Architecture**: Built on Flax NNX for better integration, modularity, and performance. +- **Multi-Device Support**: Optimized to run on TPU, GPU, and CPU environments. +- **Sharded Model Parallelism**: Supports model parallelism across multiple devices for scalability (using `auto_shard_model=True`). +- **Customizable Precision**: Allows specification of `dtype`, `param_dtype`, and `precision`. +- **Advanced Serving**: Includes `eSurge` LLM serving engine, `vWhisper` speech endpoints, and OpenAI-compatible APIs. +- **Optimized Kernels**: Integrates multiple attention mechanisms (like `AttentionMechanisms.RAGGED_PAGE_ATTENTION_V3`) and platform-specific optimizations. + +## Installation + +To use this model via EasyDeL, first install EasyDeL: + +```bash +pip install easydel +``` + +## Usage + +### Loading the Pre-trained Model + +To load this pre-trained model with EasyDeL: + +```python +from easydel import AutoEasyDeLModelForCausalLM, EasyDeLBaseConfigDict, AttentionMechanisms +from jax import numpy as jnp, lax + +# Define max_length if needed for memory optimization +max_length = None + +# Load model and parameters +# Set auto_shard_model=True to automatically distribute across devices +model = AutoEasyDeLModelForCausalLM.from_pretrained( + "EasyDeL/gpt-oss-20b", + config_kwargs=EasyDeLBaseConfigDict( + # use_scan_mlp=False, # Set to True to potentially reduce memory usage + attn_dtype=jnp.float16, # Or jnp.bfloat16 + # freq_max_position_embeddings=max_length, # Set if using RoPE and need truncation + # mask_max_position_embeddings=max_length, # Set if max length is defined + attn_mechanism=AttentionMechanisms.PAGED # Matches the mechanism used by this model + ), + dtype=jnp.float16, # Or jnp.bfloat16 - Computation data type + param_dtype=jnp.float16, # Or jnp.bfloat16 - Parameter data type + precision=lax.Precision("fastest"), # Like "default", "fastest", "high", "highest" + auto_shard_model=True, # Auto-shard across available devices +) +``` + +## Supported Tasks + +The primary task for this model is **TaskType.CAUSAL_LM**. Further specific supported tasks are not explicitly listed. + +## Limitations + +**General Limitations:** + +- **Hardware Dependency**: Performance can vary significantly based on the hardware (TPU/GPU) used. +- **JAX/Flax Setup Required**: The environment must support JAX/Flax for optimal use. +- **Experimental Features**: Some EasyDeL features (like custom kernels) may require additional configuration. + +## License 📜 + +EasyDeL is released under the Apache v2 license. The license for this specific model might differ; please consult the original model repository or documentation. + +```code +# Apache License 2.0 (referring to EasyDeL Framework) +# ... (Full license text usually included in the main repo) ... +``` + +## Citation + +If you use EasyDeL in your research or work, please cite it: + +```bibtex +@misc{Zare Chavoshi_2023, + title={EasyDeL: An open-source library for enhancing and streamlining the training process of machine learning models}, + url={https://github.com/erfanzar/EasyDeL}, + author={Zare Chavoshi, Erfan}, + year={2023} +} +``` + +Please also consider citing the original paper or source for the **EasyDeL/gpt-oss-20b** model architecture if applicable. diff --git a/checkpoint_metadata.json b/checkpoint_metadata.json new file mode 100644 index 0000000000000000000000000000000000000000..1c2751a562dc80e929b7953ead497ad67c546c4d --- /dev/null +++ b/checkpoint_metadata.json @@ -0,0 +1,8 @@ +{ + "version": "0.0.84", + "timestamp": "2025-11-24T14:39:38.911214", + "checksum": {}, + "array_metadata": {}, + "framework_version": null, + "custom_metadata": {} +} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..60a15351df68f37f9cf61f0a7eabe1e1c0d5230c --- /dev/null +++ b/config.json @@ -0,0 +1,162 @@ +{ + "architectures": [ + "GptOssForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "attn_mechanism": "ragged_page_attention_v3", + "backend": null, + "bits": null, + "blocksize_b": 1, + "blocksize_k": 128, + "blocksize_q": 128, + "decode_attn_mechanism": null, + "dtype": "bfloat16", + "easy_method": "train", + "eos_token_id": 200002, + "experts_per_token": 4, + "fcm_max_ratio": 0.0, + "fcm_min_ratio": 0.0, + "flash_attention_backward_pass_impl": "triton", + "freq_max_position_embeddings": 4096, + "fsdp_is_ep_bound": true, + "gradient_checkpointing": "", + "gradient_checkpointing_targets": null, + "hardware_abstraction": true, + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2880, + "initial_context_length": 4096, + "initializer_range": 0.02, + "intermediate_size": 2880, + "kv_cache_quantization_blocksize": 128, + "kv_cache_quantization_method": "None", + "kv_cache_sharding_sequence_axis_name": "sp", + "layer_types": [ + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention" + ], + "mask_max_position_embeddings": 4096, + "max_position_embeddings": 131072, + "mlp_activations_limit": 7.0, + "model_type": "gpt_oss", + "moe_force_xla_gmm": false, + "moe_method": "fused_moe", + "moe_tiling_size_batch": 4, + "moe_tiling_size_dim": 128, + "moe_tiling_size_seqlen": 128, + "num_attention_heads": 64, + "num_experts_per_tok": 4, + "num_hidden_layers": 24, + "num_key_value_heads": 8, + "num_local_experts": 32, + "output_router_logits": false, + "pallas_k_block_size": 128, + "pallas_m_block_size": 128, + "pallas_n_block_size": 128, + "partition_axis": { + "attention_dim_axis": null, + "attention_kv_dim_axis": null, + "batch_axis": [ + "fsdp", + "dp" + ], + "bias_head_sequence_axis": null, + "bias_key_sequence_axis": null, + "data_parallel_axis": "dp", + "decode_attention_dim_axis": null, + "decode_attention_kv_dim_axis": null, + "decode_batch_axis": [ + "fsdp", + "dp" + ], + "decode_head_axis": "tp", + "decode_key_sequence_axis": "sp", + "decode_kv_head_axis": "tp", + "decode_query_sequence_axis": null, + "expert_axis": "ep", + "expert_gate_axis": null, + "expert_parallel_axis": "ep", + "fully_sharded_data_parallel_axis": "fsdp", + "head_axis": "tp", + "hidden_state_axis": "tp", + "key_sequence_axis": "sp", + "kv_head_axis": "tp", + "mlp_intermediate_axis": "tp", + "query_sequence_axis": "sp", + "sequence_axis": "sp", + "sequence_parallel_axis": "sp", + "tensor_parallel_axis": "tp", + "vocab_axis": "tp" + }, + "platform": null, + "precompute_masks": true, + "pretraining_tp": 1, + "quantization_blocksize": 64, + "quantization_method": "None", + "quantization_pattern": ".*", + "rms_norm_eps": 1e-05, + "rope_scaling": { + "beta_fast": 32.0, + "beta_slow": 1.0, + "factor": 32.0, + "original_max_position_embeddings": 4096, + "rope_type": "yarn", + "truncate": false + }, + "rope_theta": 150000, + "router_aux_loss_coef": 0.9, + "scan_attention_layers": false, + "scan_mlp_chunk_size": 1024, + "scan_ring_attention": true, + "sequence_axis_name": "sp", + "sharding_axis_dims": [ + 1, + 1, + 1, + -1, + 1 + ], + "sharding_axis_names": [ + "dp", + "fsdp", + "ep", + "tp", + "sp" + ], + "sharding_dcn_axis_dims": null, + "sliding_window": 128, + "sp_is_ep_bound": true, + "swiglu_limit": 7.0, + "tie_word_embeddings": false, + "transformers_version": "4.57.1", + "use_cache": true, + "use_expert_tensor_mode": false, + "use_ring_of_experts": false, + "use_scan_mlp": false, + "use_sharded_kv_caching": false, + "use_sharding_constraint": false, + "vocab_size": 201088 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..4813d238ea15f92cf8cb97c9840412c9fff135f2 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 199998, + "device": null, + "do_sample": true, + "eos_token_id": [ + 200002, + 199999, + 200012 + ], + "pad_token_id": 199999, + "transformers_version": "4.57.1" +} diff --git a/model/lm_head/kernel/.zarray b/model/lm_head/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..98c56b5647f1fcd71bb255a0ba56549db869cc53 --- /dev/null +++ b/model/lm_head/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,50272],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,201088],"zarr_format":2} \ No newline at end of file diff --git a/model/lm_head/kernel/0.0 b/model/lm_head/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..ecc0246b31483f2144e431841f4c6954ec2ec9a6 --- /dev/null +++ b/model/lm_head/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a59a0697e61df795e9d452bca2567b951825a916bdb8e68de07dab2fe96a648 +size 226641977 diff --git a/model/lm_head/kernel/0.1 b/model/lm_head/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..4eafb4bc732dca553e960be541bf897ba44ed4ab --- /dev/null +++ b/model/lm_head/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:738005c53d3d3985f9e69081cb9e9e43f04cb5471a8cec5325c9cb7ab76ba644 +size 226681894 diff --git a/model/lm_head/kernel/0.2 b/model/lm_head/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..2b0b7118e9b4f1bd4255eb659f6c168317403c5d --- /dev/null +++ b/model/lm_head/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b4589e1d887a07e81513b318316dccd1f5fef87fa942d667ab4fefe7b8291b8 +size 226770968 diff --git a/model/lm_head/kernel/0.3 b/model/lm_head/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..e47726967c836dfc83a5732cce284ee567196724 --- /dev/null +++ b/model/lm_head/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e1220e3a3d6982aaae3f5bbf444b71e89adf553a954fdcde257b849a70e5f4 +size 227725079 diff --git a/model/model/embed_tokens/embedding/.zarray b/model/model/embed_tokens/embedding/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..2e937ce34f56a4298bddd411c8af91336811d2a9 --- /dev/null +++ b/model/model/embed_tokens/embedding/.zarray @@ -0,0 +1 @@ +{"chunks":[201088,720],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[201088,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/embed_tokens/embedding/0.0 b/model/model/embed_tokens/embedding/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..62a64cae8c3b53af29ba9fd577ba0cf5e58dc42e --- /dev/null +++ b/model/model/embed_tokens/embedding/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3adc019f3fca5e4a4d2f9d58ccacaa019db91b4658323093331f25f006cc9a00 +size 238375444 diff --git a/model/model/embed_tokens/embedding/0.1 b/model/model/embed_tokens/embedding/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..b4f247534d39ba02322a2c49eaa50f777e22beca --- /dev/null +++ b/model/model/embed_tokens/embedding/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d93e52183c1eaf471bf4511e12b3241ef43d3a68cc3049d4cf864388ed0d546 +size 238013629 diff --git a/model/model/embed_tokens/embedding/0.2 b/model/model/embed_tokens/embedding/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..99980025964870ecdcf7e349e64c2604ec52dc20 --- /dev/null +++ b/model/model/embed_tokens/embedding/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce50c59d118efd64f0902246f08d0313ecb7a22c2390769ace5644ff59805f00 +size 237651927 diff --git a/model/model/embed_tokens/embedding/0.3 b/model/model/embed_tokens/embedding/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..3817f37a033502a57cf4c9c4d31e7d848125f6ec --- /dev/null +++ b/model/model/embed_tokens/embedding/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15b170706b9ab63112ea73a2d78cac3ec75716a09d5bafa4c472c9631996827b +size 238261890 diff --git a/model/model/layers/0/input_layernorm/kernel/.zarray b/model/model/layers/0/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/0/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/input_layernorm/kernel/0 b/model/model/layers/0/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..06f7b37ebe557277b41a3bf32935fb62ec9638ae Binary files /dev/null and b/model/model/layers/0/input_layernorm/kernel/0 differ diff --git a/model/model/layers/0/mlp/experts/down_proj/bias/.zarray b/model/model/layers/0/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/0/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/mlp/experts/down_proj/bias/0.0 b/model/model/layers/0/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..ed875fccb4e8b139a5fd2d42847986e50fbf9180 --- /dev/null +++ b/model/model/layers/0/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aeb585a75b26b0719fd983cf91626a88e0aa9e02010c1ee5cd34bff3d004f5e +size 148544 diff --git a/model/model/layers/0/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/0/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/0/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/0/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..47d461d1037dc69b980473076b648c6516d30d46 --- /dev/null +++ b/model/model/layers/0/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ad0b1eb9f3fc213a92a640b3ba3ddfa2116c573a4f09c9e0f3a2ce56f305659 +size 205875490 diff --git a/model/model/layers/0/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/0/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/0/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/0/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..c1dbbb3d88473cbfc3b674905f17ef1e4c455769 --- /dev/null +++ b/model/model/layers/0/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73bf83d1d04f1f22ac7ee7b9c00b3bfd46dc85d0e2b8a2ab72df38a47591ed3e +size 126932 diff --git a/model/model/layers/0/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/0/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/0/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/0/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..c17cbb4150871ce45ab404cb910e08353f44e10c --- /dev/null +++ b/model/model/layers/0/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8829b36b49b61dea3877236700cc78fd3f289a7a4aabc1c90b815ed96363632 +size 176413980 diff --git a/model/model/layers/0/mlp/experts/up_proj/bias/.zarray b/model/model/layers/0/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/0/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/mlp/experts/up_proj/bias/0.0 b/model/model/layers/0/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..6f7e0a42d71c23cdedcd71699354e12343462272 --- /dev/null +++ b/model/model/layers/0/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65c6a12a90133fa6f0d2b34e49478d42e4be9523e7caf2c85b1e3fb401d30921 +size 108408 diff --git a/model/model/layers/0/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/0/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/0/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/0/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..e152091ccd39bd91217931538d9d2c2bf6a84c50 --- /dev/null +++ b/model/model/layers/0/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dfbccadccf5d0e6b3e69d45cb18c942432a1a62cc3ec245e4a346077503c98a +size 175659503 diff --git a/model/model/layers/0/mlp/router/bias/.zarray b/model/model/layers/0/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/0/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/mlp/router/bias/0 b/model/model/layers/0/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..ce554a73926934db149515972992b4157127f8eb Binary files /dev/null and b/model/model/layers/0/mlp/router/bias/0 differ diff --git a/model/model/layers/0/mlp/router/kernel/.zarray b/model/model/layers/0/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/0/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/mlp/router/kernel/0.0 b/model/model/layers/0/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..f4b8633919c222debeecde955a5d2f8d1fb7e48c --- /dev/null +++ b/model/model/layers/0/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6916637eaabd97130c84226d31c856e5ec7eba6589c5c7bd598d40ddfbf8ad41 +size 146759 diff --git a/model/model/layers/0/post_attention_layernorm/kernel/.zarray b/model/model/layers/0/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/0/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/post_attention_layernorm/kernel/0 b/model/model/layers/0/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..14fd21f383b2edfe8cd2e69eb60b89162a153c77 Binary files /dev/null and b/model/model/layers/0/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/0/self_attn/k_proj/bias/.zarray b/model/model/layers/0/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/0/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/self_attn/k_proj/bias/0 b/model/model/layers/0/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/0/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/0/self_attn/k_proj/kernel/.zarray b/model/model/layers/0/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/0/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/self_attn/k_proj/kernel/0.0 b/model/model/layers/0/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..b88e39e2df07c1520a71bea83d962c68d2caee34 --- /dev/null +++ b/model/model/layers/0/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb28d0346a7f6d995f75fc86b6ad1b97c0b08ba9697c7fcb6de652ac26721ed5 +size 591455 diff --git a/model/model/layers/0/self_attn/k_proj/kernel/0.1 b/model/model/layers/0/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..cbcb0518619fc92bb67d1dd414ef58634cba1793 --- /dev/null +++ b/model/model/layers/0/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:126aefc77772730e4601722e663c581e96b4c1a6965d7644a244e4d5a33454a7 +size 591779 diff --git a/model/model/layers/0/self_attn/k_proj/kernel/0.2 b/model/model/layers/0/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..fa15febe9285957552a1bd78cdf72b7ce0d63fee --- /dev/null +++ b/model/model/layers/0/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebef9e3d47721de81a32b985eb4808178311bde35775f25e2447686e335ef095 +size 593231 diff --git a/model/model/layers/0/self_attn/k_proj/kernel/0.3 b/model/model/layers/0/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..f42702e6e27da6f1480267a5c22e0834b73ee612 --- /dev/null +++ b/model/model/layers/0/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3ef0df3311ec6863669f88ca7f78f84cdc5f1b56682eeb304bfdd0d194cad98 +size 590638 diff --git a/model/model/layers/0/self_attn/o_proj/bias/.zarray b/model/model/layers/0/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/0/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/self_attn/o_proj/bias/0 b/model/model/layers/0/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..7c2ff577f6811667b5dd9e288b81d5a5c9963035 Binary files /dev/null and b/model/model/layers/0/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/0/self_attn/o_proj/kernel/.zarray b/model/model/layers/0/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/0/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/self_attn/o_proj/kernel/0.0 b/model/model/layers/0/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..30c758c66595570bb6ce9541e6588112910c5748 --- /dev/null +++ b/model/model/layers/0/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a1ac4e4b9b92bace048723b1910813b433c205f4de2b43aed7194e540dec035 +size 4677833 diff --git a/model/model/layers/0/self_attn/o_proj/kernel/1.0 b/model/model/layers/0/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..19ab67f6e3f97d80def8abbfa727ddb8acd326cd --- /dev/null +++ b/model/model/layers/0/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e84b5d764029feb8b973b01797488701f432f8937e813ef1c89bb6119529246e +size 4673577 diff --git a/model/model/layers/0/self_attn/o_proj/kernel/2.0 b/model/model/layers/0/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..d31ca074ea2365f54146e39a785ccad35f10cd21 --- /dev/null +++ b/model/model/layers/0/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d48de19ebb6bc364d0e4ecdb3f9da8d4a0a7fef3d56363aa0ba83181eb4a91d2 +size 4682913 diff --git a/model/model/layers/0/self_attn/o_proj/kernel/3.0 b/model/model/layers/0/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..ebd70db95b103eea3ec69c42eabb7213a4ef43f4 --- /dev/null +++ b/model/model/layers/0/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fb890ca70a46f9f014efae03b2907716c044df9c50c81d86680bede3844c5a0 +size 4695943 diff --git a/model/model/layers/0/self_attn/q_proj/bias/.zarray b/model/model/layers/0/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/0/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/self_attn/q_proj/bias/0 b/model/model/layers/0/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..d479a54752cbffad831a07444e834206a48f74b3 Binary files /dev/null and b/model/model/layers/0/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/0/self_attn/q_proj/kernel/.zarray b/model/model/layers/0/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/0/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/self_attn/q_proj/kernel/0.0 b/model/model/layers/0/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..2920ffebefdb196867db834d6f315c36b6db8bc9 --- /dev/null +++ b/model/model/layers/0/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32cc0820f294c8165a7c9f7912f5bcabc2ca6c2133e32dc0ca4fbd37572af927 +size 4762104 diff --git a/model/model/layers/0/self_attn/q_proj/kernel/0.1 b/model/model/layers/0/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..f0456e6250d1dd2c80f1656215d03e2631b13b60 --- /dev/null +++ b/model/model/layers/0/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7a0e46bbd15760bf51a8830c40ac753ae9e5d49fe4b980cd5e31268de64546f +size 4761857 diff --git a/model/model/layers/0/self_attn/q_proj/kernel/0.2 b/model/model/layers/0/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..8cf937f4ba9f9eae8f51342d39b5e50d9c9a4078 --- /dev/null +++ b/model/model/layers/0/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb3efa74184768a1c894e9cda176aa29bb99b0710fdb47969a3daf51d329dda6 +size 4795515 diff --git a/model/model/layers/0/self_attn/q_proj/kernel/0.3 b/model/model/layers/0/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..84123b651bdf38a14f4c8622ac2a5efeec388090 --- /dev/null +++ b/model/model/layers/0/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a2ec4713caca640ce0a53a7971cfc965f2fc1f5ae19002bdd5470055817685b +size 4785033 diff --git a/model/model/layers/0/self_attn/sinks/.zarray b/model/model/layers/0/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/0/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/self_attn/sinks/0 b/model/model/layers/0/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..d67af09c2127dcec382dd08c0806d456f15106b9 Binary files /dev/null and b/model/model/layers/0/self_attn/sinks/0 differ diff --git a/model/model/layers/0/self_attn/v_proj/bias/.zarray b/model/model/layers/0/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/0/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/self_attn/v_proj/bias/0 b/model/model/layers/0/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..2629ccfeb7fc131188f182c1211ce657584470d5 Binary files /dev/null and b/model/model/layers/0/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/0/self_attn/v_proj/kernel/.zarray b/model/model/layers/0/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/0/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/0/self_attn/v_proj/kernel/0.0 b/model/model/layers/0/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..9b9742961c54f9b896b656194f66e40f954ebc96 --- /dev/null +++ b/model/model/layers/0/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb0dbf337fe6cc1dcf0ab05858a325a89d07cfc7bf095b4d9c51e642db2b1811 +size 588470 diff --git a/model/model/layers/0/self_attn/v_proj/kernel/0.1 b/model/model/layers/0/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..94315574e91384ab0f08155f26398606f2985f22 --- /dev/null +++ b/model/model/layers/0/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:880485e854dcc825aac7f3bd3661474a95876b8a8a4072121e4135ecb4f38f76 +size 588085 diff --git a/model/model/layers/0/self_attn/v_proj/kernel/0.2 b/model/model/layers/0/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..a7d056781adc538c3906df3f777379cca266ab07 --- /dev/null +++ b/model/model/layers/0/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bd13d721103e7bbe3e3cf7c8f9a52283e198246372cf7b3ca840c7cb6ecead4 +size 588034 diff --git a/model/model/layers/0/self_attn/v_proj/kernel/0.3 b/model/model/layers/0/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..d10b1a7881a04c9e0ef96dcfadff8fb0b5a9e654 --- /dev/null +++ b/model/model/layers/0/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a88ab97e1231fa816aa809f0ed27ffae8bb2849eb0009e80b30a8f522db9bb4d +size 588532 diff --git a/model/model/layers/1/input_layernorm/kernel/.zarray b/model/model/layers/1/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/1/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/input_layernorm/kernel/0 b/model/model/layers/1/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..847e7f05953cb7e5eba01c0a1a3e001f565a4e08 Binary files /dev/null and b/model/model/layers/1/input_layernorm/kernel/0 differ diff --git a/model/model/layers/1/mlp/experts/down_proj/bias/.zarray b/model/model/layers/1/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/1/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/mlp/experts/down_proj/bias/0.0 b/model/model/layers/1/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..1f5294cfd541b395a30fd832c0929345c06835fd --- /dev/null +++ b/model/model/layers/1/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5649e5e7b4cb9e1a1b812ad04e74b94d23f1d9abc3aac6f74f6ebef5fe446ad8 +size 147117 diff --git a/model/model/layers/1/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/1/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/1/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/1/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..6d5e5f858c2acc950b76b921bfc149a46eed41b5 --- /dev/null +++ b/model/model/layers/1/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00503ebd53c9e1924dc86807cae423b7fa50256032f814242f0da25b44f4f02e +size 201033748 diff --git a/model/model/layers/1/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/1/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/1/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/1/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..e9499c44bc11a87fe5868d95c90ab12c3ff18c2d --- /dev/null +++ b/model/model/layers/1/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:babc7d2be6656d5643a15c105dca607660eeed490b829311caa27710d34729c5 +size 128755 diff --git a/model/model/layers/1/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/1/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/1/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/1/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..fa59f9d227d3e3e1be5b2821afd1d47fd6e6ac1b --- /dev/null +++ b/model/model/layers/1/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c22f667b6058d630848d784f80d911421c58bd331a27dd6d84f7e7c18caad8ea +size 181025907 diff --git a/model/model/layers/1/mlp/experts/up_proj/bias/.zarray b/model/model/layers/1/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/1/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/mlp/experts/up_proj/bias/0.0 b/model/model/layers/1/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..8cffcc9274a9bae4385b72b3c95ee3554612e84a --- /dev/null +++ b/model/model/layers/1/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4df8847e7bbd9d87f4870b994f0601b3638d9fcf0a3ebabb420b45899bbc3ee +size 111382 diff --git a/model/model/layers/1/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/1/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/1/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/1/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..cbe60d008eb1922360b36ead618cfa2ce644adf4 --- /dev/null +++ b/model/model/layers/1/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b597df298b17bc366351acacf7a6c204551cbaf2195fcd593e5357951fadf8e +size 178526652 diff --git a/model/model/layers/1/mlp/router/bias/.zarray b/model/model/layers/1/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/1/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/mlp/router/bias/0 b/model/model/layers/1/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..90a564d621abc0b1a9d8ba143c3a47aa712ebc3d Binary files /dev/null and b/model/model/layers/1/mlp/router/bias/0 differ diff --git a/model/model/layers/1/mlp/router/kernel/.zarray b/model/model/layers/1/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/1/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/mlp/router/kernel/0.0 b/model/model/layers/1/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..06be80faf2d5ed16b0cdf260f9c78c4160da8a36 --- /dev/null +++ b/model/model/layers/1/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5757809fd4591c839ff2d96e897612fd4301d36ecf49ba8f79b35e8489ce9a33 +size 146070 diff --git a/model/model/layers/1/post_attention_layernorm/kernel/.zarray b/model/model/layers/1/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/1/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/post_attention_layernorm/kernel/0 b/model/model/layers/1/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..9d10e6873292a6322777c4f67b32ef77eb3f37b0 Binary files /dev/null and b/model/model/layers/1/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/1/self_attn/k_proj/bias/.zarray b/model/model/layers/1/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/1/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/self_attn/k_proj/bias/0 b/model/model/layers/1/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/1/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/1/self_attn/k_proj/kernel/.zarray b/model/model/layers/1/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/1/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/self_attn/k_proj/kernel/0.0 b/model/model/layers/1/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..6b091ad73a80a0a16021dc817b757a4edaa948db --- /dev/null +++ b/model/model/layers/1/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65e1dd7473baa14308f12926ec76ff7634c66bd0bfef1ab88a8253b034d561ed +size 584973 diff --git a/model/model/layers/1/self_attn/k_proj/kernel/0.1 b/model/model/layers/1/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..033e5cd7e8490fabb53d40f531f080884d317a0d --- /dev/null +++ b/model/model/layers/1/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d071f30fe8bcabcc37c9f862714bda877c4136988b2628a81e5ea972bd634d7 +size 590175 diff --git a/model/model/layers/1/self_attn/k_proj/kernel/0.2 b/model/model/layers/1/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..9568f9a025137b8d95b41e122a472dc1bf12d245 --- /dev/null +++ b/model/model/layers/1/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dc41192f2fd1ea99e07e56929103647350f70d56684228d9e4b35a62b77d610 +size 586255 diff --git a/model/model/layers/1/self_attn/k_proj/kernel/0.3 b/model/model/layers/1/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..1f2e3abc6dbe479e5f789dc71b0808788cb3c8b4 --- /dev/null +++ b/model/model/layers/1/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:258a7efc2bc4bd93a0ab167e8c8b089a96386cac3685d8eb20915381ed0b2d1d +size 591941 diff --git a/model/model/layers/1/self_attn/o_proj/bias/.zarray b/model/model/layers/1/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/1/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/self_attn/o_proj/bias/0 b/model/model/layers/1/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..7757ac640e8b1a7d946d8cebae327938f7c106b7 Binary files /dev/null and b/model/model/layers/1/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/1/self_attn/o_proj/kernel/.zarray b/model/model/layers/1/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/1/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/self_attn/o_proj/kernel/0.0 b/model/model/layers/1/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..d4fe1ffaadf366e64b01ba6903a457af9bb39fad --- /dev/null +++ b/model/model/layers/1/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf14f5fae1f9f7d600714a2206032d03530e9f9df514b39ef4a9bb2d110d1ec6 +size 4690492 diff --git a/model/model/layers/1/self_attn/o_proj/kernel/1.0 b/model/model/layers/1/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..00e746de4015dbfe5233f26fbce4176c78ebdf30 --- /dev/null +++ b/model/model/layers/1/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d579c1b011f3049e7324715d8a25d4578faa888b728c721b1e8ca236cbddaf2 +size 4710429 diff --git a/model/model/layers/1/self_attn/o_proj/kernel/2.0 b/model/model/layers/1/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..3897fa829e509129f9efc4d4b093802233b974ad --- /dev/null +++ b/model/model/layers/1/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56e0f4c01866070f3627940607239c3902fe8e856d2d2468a5886e7a806da216 +size 4682420 diff --git a/model/model/layers/1/self_attn/o_proj/kernel/3.0 b/model/model/layers/1/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..5eb7b471aa03bcc973017da6693b3f4aec552d02 --- /dev/null +++ b/model/model/layers/1/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b97ace985bb4fe6e4338d48e926122146c32086321e11ef1544f7eee590e2f2a +size 4701890 diff --git a/model/model/layers/1/self_attn/q_proj/bias/.zarray b/model/model/layers/1/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/1/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/self_attn/q_proj/bias/0 b/model/model/layers/1/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..16454845183cd8316ffb9b33e7fcc0657c29cdc3 Binary files /dev/null and b/model/model/layers/1/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/1/self_attn/q_proj/kernel/.zarray b/model/model/layers/1/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/1/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/self_attn/q_proj/kernel/0.0 b/model/model/layers/1/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..ba10bf633b473dddfd181b912905c40d64357603 --- /dev/null +++ b/model/model/layers/1/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95954c76d8c9c829fc89ce3af024023d58c7507a71607a24324c7cc576c7ea81 +size 4738999 diff --git a/model/model/layers/1/self_attn/q_proj/kernel/0.1 b/model/model/layers/1/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..a04f3e5097d11a35909402c411528d0e58ddbb04 --- /dev/null +++ b/model/model/layers/1/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9d8758c99922759346b0522cdf30a5a09528cf9059953cb153ce894d714df94 +size 4747028 diff --git a/model/model/layers/1/self_attn/q_proj/kernel/0.2 b/model/model/layers/1/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..096ca2cec8a4b8bbe47886755cf0b5f2c616b8ef --- /dev/null +++ b/model/model/layers/1/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ef9c7be42d482fd0a5e12c72171ec47bc2fed465216a338e062ea09b7facb61 +size 4706385 diff --git a/model/model/layers/1/self_attn/q_proj/kernel/0.3 b/model/model/layers/1/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..65ec6a4fe6b851744aa14c09a7e1da673a191e32 --- /dev/null +++ b/model/model/layers/1/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69551a1598b65e5722d17f87a7e7580430bd2138df6f564fc03525f1638ee008 +size 4707929 diff --git a/model/model/layers/1/self_attn/sinks/.zarray b/model/model/layers/1/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/1/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/self_attn/sinks/0 b/model/model/layers/1/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..dd29ff8c4670b0d06ca63adcf91f551e151cc704 Binary files /dev/null and b/model/model/layers/1/self_attn/sinks/0 differ diff --git a/model/model/layers/1/self_attn/v_proj/bias/.zarray b/model/model/layers/1/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/1/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/self_attn/v_proj/bias/0 b/model/model/layers/1/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..79e0caa0118dc63d686528ab5b7d8beb8fa70429 Binary files /dev/null and b/model/model/layers/1/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/1/self_attn/v_proj/kernel/.zarray b/model/model/layers/1/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/1/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/1/self_attn/v_proj/kernel/0.0 b/model/model/layers/1/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..6661cc5de6968466b4ce1d7f2346208a5fb69689 --- /dev/null +++ b/model/model/layers/1/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4018d0e511b305f7e314488b4236decb310de4172cb49b7ecc1946854da7cad +size 580929 diff --git a/model/model/layers/1/self_attn/v_proj/kernel/0.1 b/model/model/layers/1/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..11d8550eb92e989e79a83b9bb547e5f438612ea6 --- /dev/null +++ b/model/model/layers/1/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6997c048dcc567ad5d516676e1fa9b96c6b739959fb835cf16863f9be1e38f80 +size 585198 diff --git a/model/model/layers/1/self_attn/v_proj/kernel/0.2 b/model/model/layers/1/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..cd15be3ce92f7d428b26d8cae170a32a37571163 --- /dev/null +++ b/model/model/layers/1/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d42543c9d5e113f80cc3943dc0c22f6b805e02e3a077b8181b4f40f37f7e65f +size 579885 diff --git a/model/model/layers/1/self_attn/v_proj/kernel/0.3 b/model/model/layers/1/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..8894b938c835e5ca36f0c94d69bad4dabf854266 --- /dev/null +++ b/model/model/layers/1/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76fad827dba8cc831e45b12b414b7ba2e9a8662af76ee5e1115ee8d814bb686a +size 582683 diff --git a/model/model/layers/10/input_layernorm/kernel/.zarray b/model/model/layers/10/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/10/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/input_layernorm/kernel/0 b/model/model/layers/10/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..dd1e8830411cd0ed8af97bcd6ca40645c3b9c5c3 Binary files /dev/null and b/model/model/layers/10/input_layernorm/kernel/0 differ diff --git a/model/model/layers/10/mlp/experts/down_proj/bias/.zarray b/model/model/layers/10/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/10/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/mlp/experts/down_proj/bias/0.0 b/model/model/layers/10/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..4dfc864884c3e6a8a4e6ab9572bcfc1819680d6b --- /dev/null +++ b/model/model/layers/10/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bfa16f9e8a770176f41ac85582df8e2fc013b0369cc59eca3c3dcdf37241488 +size 144419 diff --git a/model/model/layers/10/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/10/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/10/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/10/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..981f3673ff91fada4f58fe30f505e860635b6712 --- /dev/null +++ b/model/model/layers/10/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa2f17749a9e0bd85918b9b866c1aeb1971088f3048b033c9aa33799b1f508d8 +size 184773949 diff --git a/model/model/layers/10/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/10/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/10/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/10/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..2be1dbc3b8dc75d1421b3a7fb61782bbcde61006 --- /dev/null +++ b/model/model/layers/10/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba64551171f628d171f3d0d5edd3741ab3d5a38f01b22941dfc15baa251f9ca9 +size 138830 diff --git a/model/model/layers/10/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/10/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/10/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/10/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..749f3f2de833b24951d4dfd92bd8a05711235913 --- /dev/null +++ b/model/model/layers/10/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdf28397a99e2b0bdd159651bd209da834d8d57bbe4b695988a215632a340067 +size 193892799 diff --git a/model/model/layers/10/mlp/experts/up_proj/bias/.zarray b/model/model/layers/10/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/10/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/mlp/experts/up_proj/bias/0.0 b/model/model/layers/10/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..10394b101a417a8a521a011082b3a74804614d5b --- /dev/null +++ b/model/model/layers/10/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9fbab6152826f0564abcb525fe1354f58589ed54706a97fb89ed7e8db157cb9 +size 126502 diff --git a/model/model/layers/10/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/10/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/10/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/10/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..826fe2b4af7941bd0f20f86e36c7bebeeab0713b --- /dev/null +++ b/model/model/layers/10/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:532f0a2173771d302d0a82ed0595bc59e18e7c75a36497421df9ac2f104d9ff6 +size 182191060 diff --git a/model/model/layers/10/mlp/router/bias/.zarray b/model/model/layers/10/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/10/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/mlp/router/bias/0 b/model/model/layers/10/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..c27c7f67d8b5e19246b9e55de63e447dba8aba9f Binary files /dev/null and b/model/model/layers/10/mlp/router/bias/0 differ diff --git a/model/model/layers/10/mlp/router/kernel/.zarray b/model/model/layers/10/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/10/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/mlp/router/kernel/0.0 b/model/model/layers/10/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..29ad75b7768456705751725f74860434c334b080 --- /dev/null +++ b/model/model/layers/10/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ed027c86f8d11f68375cf7f36ec5b660e4511882f7eb47d6c4630561764f8c6 +size 144752 diff --git a/model/model/layers/10/post_attention_layernorm/kernel/.zarray b/model/model/layers/10/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/10/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/post_attention_layernorm/kernel/0 b/model/model/layers/10/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..ff2fc654bb51e6accddfd10b0839893fa7945f67 Binary files /dev/null and b/model/model/layers/10/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/10/self_attn/k_proj/bias/.zarray b/model/model/layers/10/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/10/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/self_attn/k_proj/bias/0 b/model/model/layers/10/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/10/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/10/self_attn/k_proj/kernel/.zarray b/model/model/layers/10/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/10/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/self_attn/k_proj/kernel/0.0 b/model/model/layers/10/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..99bef9502964cddddd0f905a73bdb8ef087a5e4b --- /dev/null +++ b/model/model/layers/10/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51424ea00fe86210a3dcbcb8079fd237d49bd1875477d2782e1d228db1d09f5a +size 581048 diff --git a/model/model/layers/10/self_attn/k_proj/kernel/0.1 b/model/model/layers/10/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..ec7ae8f1a09a1cb2f22f9f85957b05fcff5a8657 --- /dev/null +++ b/model/model/layers/10/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2f56b28a16668c599763c04e9c514156597c6743c2bbd9ccac8d07d0e95bd34 +size 582002 diff --git a/model/model/layers/10/self_attn/k_proj/kernel/0.2 b/model/model/layers/10/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..2b523e323348ee0a4e395c3fd0fc2548c2dd13e8 --- /dev/null +++ b/model/model/layers/10/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8fe950e6aaf31b6b3b368c3ee5dfc5c0a8348bb0cf56ed98e86992b98abf604 +size 581333 diff --git a/model/model/layers/10/self_attn/k_proj/kernel/0.3 b/model/model/layers/10/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..d763982b03a055162dd2e5f78a3b9b119d0aabdc --- /dev/null +++ b/model/model/layers/10/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4df92b24ca7f26cc49d86dbc0631fcb62964e48283350dd327ad231fbdd830f2 +size 586229 diff --git a/model/model/layers/10/self_attn/o_proj/bias/.zarray b/model/model/layers/10/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/10/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/self_attn/o_proj/bias/0 b/model/model/layers/10/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a32225003e1a70bf995c2e5020930848714f5c7b Binary files /dev/null and b/model/model/layers/10/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/10/self_attn/o_proj/kernel/.zarray b/model/model/layers/10/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/10/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/self_attn/o_proj/kernel/0.0 b/model/model/layers/10/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..155dc7691b5ba2b8bf75bae76417fa4fcf6efec4 --- /dev/null +++ b/model/model/layers/10/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16fecf628054d2e9eba4904ef99e9c9a784dfc331fd0645f6edd7788ca08e3e0 +size 4642314 diff --git a/model/model/layers/10/self_attn/o_proj/kernel/1.0 b/model/model/layers/10/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..cfa132f1fa961b43fbf3ddae0c70667ee27de734 --- /dev/null +++ b/model/model/layers/10/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b846ca4d0436c24dbdfe2541e9c16777583d0bde22fd6644392e9b2237cee16 +size 4634603 diff --git a/model/model/layers/10/self_attn/o_proj/kernel/2.0 b/model/model/layers/10/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..976b45e1dfaa409a98f2ad42cd29ad2107b37fa9 --- /dev/null +++ b/model/model/layers/10/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1c4292a7d53953a61227f4afc0aaa7c3c268dadf1513f64eb915a083630bced +size 4642258 diff --git a/model/model/layers/10/self_attn/o_proj/kernel/3.0 b/model/model/layers/10/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..aa3f95f977f3aeb46bf1591bfb0959b66ea517dc --- /dev/null +++ b/model/model/layers/10/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b00bc9b87da7c69088df234a103126ac0cbc593c4a52cb5e8af350d2f1817507 +size 4635714 diff --git a/model/model/layers/10/self_attn/q_proj/bias/.zarray b/model/model/layers/10/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/10/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/self_attn/q_proj/bias/0 b/model/model/layers/10/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..9cac9cbf2c3c507aebdb6cf190fb9c601daf4b1f Binary files /dev/null and b/model/model/layers/10/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/10/self_attn/q_proj/kernel/.zarray b/model/model/layers/10/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/10/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/self_attn/q_proj/kernel/0.0 b/model/model/layers/10/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..0dc3b2d168e0b61776d375985c31eb132a8ba152 --- /dev/null +++ b/model/model/layers/10/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a447e7999ae2ffd0ad1f2fc117ec9b60485abd99b3d5022e6a8c6ceaef11d831 +size 4647931 diff --git a/model/model/layers/10/self_attn/q_proj/kernel/0.1 b/model/model/layers/10/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..513ac1dba6d96579ac0179de5182a0d8ee00e7ec --- /dev/null +++ b/model/model/layers/10/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70a5e4ed42b555f33343c8139eeac2dbc2d62590f053a5638a6f80835438b4de +size 4672034 diff --git a/model/model/layers/10/self_attn/q_proj/kernel/0.2 b/model/model/layers/10/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..5cb8d14a655b364db6b3d99be924aeeb29600ad1 --- /dev/null +++ b/model/model/layers/10/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eeecc78e64a8b2d9f3f4c77f95f3f9ab1877b9a59adbac856bf8f40fd2e5294 +size 4644519 diff --git a/model/model/layers/10/self_attn/q_proj/kernel/0.3 b/model/model/layers/10/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..88fb4e4bd3062c9113cd82695c3f7210e24cea07 --- /dev/null +++ b/model/model/layers/10/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c81b50b9713b7196d339604d4dc3561b6d1a17edd0d64f334e6cb2f3fa3df4b8 +size 4671057 diff --git a/model/model/layers/10/self_attn/sinks/.zarray b/model/model/layers/10/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/10/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/self_attn/sinks/0 b/model/model/layers/10/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..30966e7fbf9d7d7fde8ba5f5a62e8e200c838bf9 Binary files /dev/null and b/model/model/layers/10/self_attn/sinks/0 differ diff --git a/model/model/layers/10/self_attn/v_proj/bias/.zarray b/model/model/layers/10/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/10/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/self_attn/v_proj/bias/0 b/model/model/layers/10/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..d113249470c917a8dd80a19112ea67930cabe4f0 Binary files /dev/null and b/model/model/layers/10/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/10/self_attn/v_proj/kernel/.zarray b/model/model/layers/10/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/10/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/10/self_attn/v_proj/kernel/0.0 b/model/model/layers/10/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..00f984f4f6126d038610e8aee178b7f4249d59e8 --- /dev/null +++ b/model/model/layers/10/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec80a234fe4beaf382769aaf39ae69d44cc2215ba434a3d865afd25b35e483bc +size 578118 diff --git a/model/model/layers/10/self_attn/v_proj/kernel/0.1 b/model/model/layers/10/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..f8907483ecf46f2ed0de9f1c666c41d271faef20 --- /dev/null +++ b/model/model/layers/10/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5acef0514356273c89d53f10707787f060adfbd136f5b4b86b2a2b8e498a3286 +size 577367 diff --git a/model/model/layers/10/self_attn/v_proj/kernel/0.2 b/model/model/layers/10/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..e9edc757013f56f7fb0216d2758b6ba78e9ccd8c --- /dev/null +++ b/model/model/layers/10/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f737ceb4a70f8d7c9124afe12a2a45cb9bb0a52b94968e444838b3e905e85aa +size 579396 diff --git a/model/model/layers/10/self_attn/v_proj/kernel/0.3 b/model/model/layers/10/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..3dad4ca630670371b68abb36687a82f181849313 --- /dev/null +++ b/model/model/layers/10/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2a7dd424e5fb5ff53bc03f232ce41d2275c505812c58ac578e67ef2a132824b +size 581267 diff --git a/model/model/layers/11/input_layernorm/kernel/.zarray b/model/model/layers/11/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/11/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/input_layernorm/kernel/0 b/model/model/layers/11/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..a6213c077c4b9b8f067bd73164f9224b9782f7e7 Binary files /dev/null and b/model/model/layers/11/input_layernorm/kernel/0 differ diff --git a/model/model/layers/11/mlp/experts/down_proj/bias/.zarray b/model/model/layers/11/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/11/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/mlp/experts/down_proj/bias/0.0 b/model/model/layers/11/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..2b11b989deb6c2ef6ad20d9a79614a40935f4ab0 --- /dev/null +++ b/model/model/layers/11/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44b7acbd7d200b8b919be49f153f76a8212bf9676c74362ccb67100da38564a +size 144634 diff --git a/model/model/layers/11/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/11/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/11/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/11/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..968263a28d239d56fdee06bce0a245b4c481477e --- /dev/null +++ b/model/model/layers/11/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9840ef07acf49c115b235ec1bb35bac2a22d4239a9d66f7360b2c965276d37a9 +size 184759197 diff --git a/model/model/layers/11/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/11/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/11/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/11/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..9862136a7979ff8764f40efccfef754a544a7f22 --- /dev/null +++ b/model/model/layers/11/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:907c8b11e48d77f09227a4a9cc44fb00abdc2852deb0aa89ea88bf34cde39d9f +size 139859 diff --git a/model/model/layers/11/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/11/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/11/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/11/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..d7c457f9657472fe03b2101a41f56cb54b5e030b --- /dev/null +++ b/model/model/layers/11/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:164c45641af2bcfe443398d12f3c2ad58183dc32847ae35f8e2cb64bcbb11887 +size 193397116 diff --git a/model/model/layers/11/mlp/experts/up_proj/bias/.zarray b/model/model/layers/11/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/11/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/mlp/experts/up_proj/bias/0.0 b/model/model/layers/11/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..2ee0522ef550707487d96aa0bd2483bd8d73786a --- /dev/null +++ b/model/model/layers/11/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:057829e05d4b8bc17a3de8118c9935f8ea7e8ec1a40e7a51f404a0f0c2a6b541 +size 126532 diff --git a/model/model/layers/11/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/11/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/11/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/11/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..c60d0b04f8362a01fc68a00dc35fb0242d603c29 --- /dev/null +++ b/model/model/layers/11/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19b319fcd5d8b568221f96ef18467ac34acd94ac2cefe56056ed79f23149edca +size 182847930 diff --git a/model/model/layers/11/mlp/router/bias/.zarray b/model/model/layers/11/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/11/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/mlp/router/bias/0 b/model/model/layers/11/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..217e797fcb4c3bff8cfe5a30f806a7eae516cddd Binary files /dev/null and b/model/model/layers/11/mlp/router/bias/0 differ diff --git a/model/model/layers/11/mlp/router/kernel/.zarray b/model/model/layers/11/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/11/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/mlp/router/kernel/0.0 b/model/model/layers/11/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..1dd787ecc3265398fbb6d64df3b24e706b43725b --- /dev/null +++ b/model/model/layers/11/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52ed0ff33e31338d3175229087788f415a4199279b881d83fc2a6056300177b4 +size 144725 diff --git a/model/model/layers/11/post_attention_layernorm/kernel/.zarray b/model/model/layers/11/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/11/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/post_attention_layernorm/kernel/0 b/model/model/layers/11/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..a998e7b50aafd80fd4be87bf894a23a2c9f60d30 Binary files /dev/null and b/model/model/layers/11/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/11/self_attn/k_proj/bias/.zarray b/model/model/layers/11/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/11/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/self_attn/k_proj/bias/0 b/model/model/layers/11/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/11/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/11/self_attn/k_proj/kernel/.zarray b/model/model/layers/11/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/11/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/self_attn/k_proj/kernel/0.0 b/model/model/layers/11/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..922574de2ddaf8f41f6db0e119002aaf05cd55e2 --- /dev/null +++ b/model/model/layers/11/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c42f9e93da62591e192632bf38f90739d882ed40953d372c6fed69d98d9b4380 +size 588987 diff --git a/model/model/layers/11/self_attn/k_proj/kernel/0.1 b/model/model/layers/11/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..ed93376fce5a8f03a51a68b4cf52a830726e18bf --- /dev/null +++ b/model/model/layers/11/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a321133e240c7a2230caa676e209775bf985bd95ed7075d1c4d061ce20245d6 +size 592866 diff --git a/model/model/layers/11/self_attn/k_proj/kernel/0.2 b/model/model/layers/11/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..ef6b44f986ad301556b611341dd403effc40f98f --- /dev/null +++ b/model/model/layers/11/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cb8e993bfbd3d780ec540fb941d36929fe8444df4b83853a180242d93ea3f4b +size 593429 diff --git a/model/model/layers/11/self_attn/k_proj/kernel/0.3 b/model/model/layers/11/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..83a745f9242ffa99c228b0593af96d87d5d5d767 --- /dev/null +++ b/model/model/layers/11/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54f5ce7d9936ca48e24f0bf049bb34b217ae7f1ad6bc155a7606392f2d62432b +size 597265 diff --git a/model/model/layers/11/self_attn/o_proj/bias/.zarray b/model/model/layers/11/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/11/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/self_attn/o_proj/bias/0 b/model/model/layers/11/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..8370fb28152f8d4ea528bf405c5010ad8ec2341a Binary files /dev/null and b/model/model/layers/11/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/11/self_attn/o_proj/kernel/.zarray b/model/model/layers/11/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/11/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/self_attn/o_proj/kernel/0.0 b/model/model/layers/11/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..3116926a4bfa6b1bbe650cc6918a7976248a7162 --- /dev/null +++ b/model/model/layers/11/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9261ffadc8575f2ed0c1beb05e3cd2fdbb98cc8237fc5ac98d5825bf19989977 +size 4646271 diff --git a/model/model/layers/11/self_attn/o_proj/kernel/1.0 b/model/model/layers/11/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..38dce8e33b0c84ace2e38abbe3f6f7352e75d847 --- /dev/null +++ b/model/model/layers/11/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e95eeefe35cb0770b4f58c97d16996cab35b03b9b38cd9d6695f9d093e4da258 +size 4647414 diff --git a/model/model/layers/11/self_attn/o_proj/kernel/2.0 b/model/model/layers/11/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..2acfed6114ede5fecd8e3a3030c8755132f5e65f --- /dev/null +++ b/model/model/layers/11/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6c8b688cf22bdc7bbae53805c9da428b5032d373fa7abb27394b0c86ac9a5a6 +size 4641642 diff --git a/model/model/layers/11/self_attn/o_proj/kernel/3.0 b/model/model/layers/11/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..e9fe4072a315224a1fc19e68e103ff5f7cd76158 --- /dev/null +++ b/model/model/layers/11/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6faebd90f7c34fca704f7ecbb7611f689dbfa4082b5c03c0c4da48442da387d1 +size 4640978 diff --git a/model/model/layers/11/self_attn/q_proj/bias/.zarray b/model/model/layers/11/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/11/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/self_attn/q_proj/bias/0 b/model/model/layers/11/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..d3822ae456d18651fce9282187fd8f680e953d93 Binary files /dev/null and b/model/model/layers/11/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/11/self_attn/q_proj/kernel/.zarray b/model/model/layers/11/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/11/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/self_attn/q_proj/kernel/0.0 b/model/model/layers/11/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..0e0fd77403123929cdbd8e662cf5ad4ab5923258 --- /dev/null +++ b/model/model/layers/11/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71c38d504006180876ff98d86ac22924b88e65bc4716a0d42737693ba433985c +size 4655268 diff --git a/model/model/layers/11/self_attn/q_proj/kernel/0.1 b/model/model/layers/11/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..10541b14bc5618a27a0e6b62c0a17d5d24d8d794 --- /dev/null +++ b/model/model/layers/11/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cd91e9949dc5953aeb7489966d2366a4b7b412246b42668a5c6712163499fd8 +size 4664910 diff --git a/model/model/layers/11/self_attn/q_proj/kernel/0.2 b/model/model/layers/11/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..17c107abd4269cfbae79449182174824a0e589dc --- /dev/null +++ b/model/model/layers/11/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a13224c303a03f65f7ee0f4d29e9bf9d4ffab8fd0d232728b95a4f84e0a0ded3 +size 4658805 diff --git a/model/model/layers/11/self_attn/q_proj/kernel/0.3 b/model/model/layers/11/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..1c6cfbfa13a6e297211d734623ba812840bbaea5 --- /dev/null +++ b/model/model/layers/11/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abd5404a862de9f0e1088aff7a1ed06c57cb14be2a7280780279c4df02b2c8de +size 4676682 diff --git a/model/model/layers/11/self_attn/sinks/.zarray b/model/model/layers/11/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/11/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/self_attn/sinks/0 b/model/model/layers/11/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..b1cb8a3078e262075262500b556c4263814d901d Binary files /dev/null and b/model/model/layers/11/self_attn/sinks/0 differ diff --git a/model/model/layers/11/self_attn/v_proj/bias/.zarray b/model/model/layers/11/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/11/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/self_attn/v_proj/bias/0 b/model/model/layers/11/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..9a8341306da8c58696d280867c79fd2cc64c8245 Binary files /dev/null and b/model/model/layers/11/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/11/self_attn/v_proj/kernel/.zarray b/model/model/layers/11/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/11/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/11/self_attn/v_proj/kernel/0.0 b/model/model/layers/11/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..cb344437e582a2759e9027491f99b89b9ae96496 --- /dev/null +++ b/model/model/layers/11/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1589843a735fd55f7b703e20563eb3546e2cdd966ca59133c90baefd4f10682 +size 579082 diff --git a/model/model/layers/11/self_attn/v_proj/kernel/0.1 b/model/model/layers/11/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..e9dd69ebf97758358a9ed9638b515f20f2d8413f --- /dev/null +++ b/model/model/layers/11/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0eaa13c1b6fa4d8dca44e30ff1c483ef17f06921115a101f216486bf84958dd +size 579884 diff --git a/model/model/layers/11/self_attn/v_proj/kernel/0.2 b/model/model/layers/11/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..c2b592c970dec1a4fe07835cb36982825677be3e --- /dev/null +++ b/model/model/layers/11/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b50f50fbd6daa8004c4b1026d4deed808675f3c1df45ad7103605fab78e21e3d +size 579215 diff --git a/model/model/layers/11/self_attn/v_proj/kernel/0.3 b/model/model/layers/11/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..edb133f357750dfc4d0b850c09ab9aa68fb99db2 --- /dev/null +++ b/model/model/layers/11/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1aa20293db0682f15d467c3b8d4a4e2ae6a5b64e63ba64cfe3f0997da135f93f +size 577934 diff --git a/model/model/layers/12/input_layernorm/kernel/.zarray b/model/model/layers/12/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/12/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/input_layernorm/kernel/0 b/model/model/layers/12/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..4cac8311a0471e930f3a0fb85c2f3aec01ad0d5f Binary files /dev/null and b/model/model/layers/12/input_layernorm/kernel/0 differ diff --git a/model/model/layers/12/mlp/experts/down_proj/bias/.zarray b/model/model/layers/12/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/12/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/mlp/experts/down_proj/bias/0.0 b/model/model/layers/12/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..a2c3b9e837ff697026977e18b1c71f7e9a1da223 --- /dev/null +++ b/model/model/layers/12/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b33b07e9b2b4598449201d9870d4ed832eadca97e72ba83087c9693530352bf1 +size 144998 diff --git a/model/model/layers/12/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/12/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/12/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/12/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..dc771ee3acac02e43454f3891fd3782006444419 --- /dev/null +++ b/model/model/layers/12/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:663dedd59ce03407349b0df97d03698df03d7a3ede52675df6aa9561d6c81ff2 +size 184491143 diff --git a/model/model/layers/12/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/12/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/12/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/12/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..91765f980fa03063ff40d07693e296153bbc4e14 --- /dev/null +++ b/model/model/layers/12/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17a29c79c82554273ec60e094e20789ce1e2c56179217a46975b4acb09e07535 +size 140672 diff --git a/model/model/layers/12/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/12/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/12/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/12/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..7cfd8283a88f11d93bf527d9dcd61f5f154ae6f1 --- /dev/null +++ b/model/model/layers/12/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66c889285beefa715ac5dd7f4a4c190f9ba90bb881672bc63f73c1b33531d97c +size 193790298 diff --git a/model/model/layers/12/mlp/experts/up_proj/bias/.zarray b/model/model/layers/12/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/12/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/mlp/experts/up_proj/bias/0.0 b/model/model/layers/12/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..0b62cfad132c0514d2596b5d74504c733f3445e5 --- /dev/null +++ b/model/model/layers/12/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37861dc166a6812cc97836336fc1228fb1bea282038ab7b04607ca640ed81e82 +size 127389 diff --git a/model/model/layers/12/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/12/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/12/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/12/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..a8dd261c808c48fa9238d08eea1636e9654ca882 --- /dev/null +++ b/model/model/layers/12/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f007e848fe278ae7c5f9d23e03765652d5b9a54feddffc95fcff8b7e28091d8a +size 183281423 diff --git a/model/model/layers/12/mlp/router/bias/.zarray b/model/model/layers/12/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/12/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/mlp/router/bias/0 b/model/model/layers/12/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..f31ec66ae5a88ac6df8ae15939c31cc205e027b3 Binary files /dev/null and b/model/model/layers/12/mlp/router/bias/0 differ diff --git a/model/model/layers/12/mlp/router/kernel/.zarray b/model/model/layers/12/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/12/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/mlp/router/kernel/0.0 b/model/model/layers/12/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..07e75ed45d62e15cdec5b9f2239293d9bca798f4 --- /dev/null +++ b/model/model/layers/12/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7944a1d7c51690be56cbb01cdea93b97702efab86ec1321e8c0767c4c8a88f06 +size 144678 diff --git a/model/model/layers/12/post_attention_layernorm/kernel/.zarray b/model/model/layers/12/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/12/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/post_attention_layernorm/kernel/0 b/model/model/layers/12/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..e20d577ea3d5346475077b06a25a8f44f905e848 Binary files /dev/null and b/model/model/layers/12/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/12/self_attn/k_proj/bias/.zarray b/model/model/layers/12/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/12/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/self_attn/k_proj/bias/0 b/model/model/layers/12/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/12/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/12/self_attn/k_proj/kernel/.zarray b/model/model/layers/12/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/12/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/self_attn/k_proj/kernel/0.0 b/model/model/layers/12/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..81bb774643c8545b430a12af8e4f97b09559c768 --- /dev/null +++ b/model/model/layers/12/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eb28d210d08ecccd02212ac0ac42018876a79e16aa702277b55126582ba535e +size 583879 diff --git a/model/model/layers/12/self_attn/k_proj/kernel/0.1 b/model/model/layers/12/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..e6457b78d825b0401804b2c7a554b48167a4d840 --- /dev/null +++ b/model/model/layers/12/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fbe88fe5c21c389f53a9e6d21f2ca7d8bcfa733705526646c789df424c7815a +size 581491 diff --git a/model/model/layers/12/self_attn/k_proj/kernel/0.2 b/model/model/layers/12/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..06574442e186614f51348b870cb921e1c4eea3e6 --- /dev/null +++ b/model/model/layers/12/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:312e4435c8ee1fef802b7fae2cbcf76f8cdbb75fe0babc83b8c7d8ecafe07c7a +size 581511 diff --git a/model/model/layers/12/self_attn/k_proj/kernel/0.3 b/model/model/layers/12/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..d36df54d3d0e2ecc309588f66f0fbe62d3bee3ca --- /dev/null +++ b/model/model/layers/12/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b98203416c0a61226de34414feb22120f6f90d84655c5436c170645ee7be0db +size 582068 diff --git a/model/model/layers/12/self_attn/o_proj/bias/.zarray b/model/model/layers/12/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/12/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/self_attn/o_proj/bias/0 b/model/model/layers/12/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..8416cc0439ed9ce0038a6d7b7650fac1a7669b1d Binary files /dev/null and b/model/model/layers/12/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/12/self_attn/o_proj/kernel/.zarray b/model/model/layers/12/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/12/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/self_attn/o_proj/kernel/0.0 b/model/model/layers/12/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..8365337258b354c53d98e17691acf736e60f7e79 --- /dev/null +++ b/model/model/layers/12/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cd96d3cf1f4a478e30669e64c3bd166901e7abfa256d82a7be0ee9d84cde864 +size 4648046 diff --git a/model/model/layers/12/self_attn/o_proj/kernel/1.0 b/model/model/layers/12/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..c0dc03e5ec888ece5060e05204a2595513cd8c08 --- /dev/null +++ b/model/model/layers/12/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5523c60d0aef7beb53cce19473138a4048d8d704aaad746e35612db7ab1a7d02 +size 4646637 diff --git a/model/model/layers/12/self_attn/o_proj/kernel/2.0 b/model/model/layers/12/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..43176a81ed85557113897b39548f7af1c442f506 --- /dev/null +++ b/model/model/layers/12/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffad21e91d7b91b3c9dd952bbc06717df3f028eb6a0fcb4f5cd2b5770783c8be +size 4632000 diff --git a/model/model/layers/12/self_attn/o_proj/kernel/3.0 b/model/model/layers/12/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..89f71b39b871a51f595c8a3ca25b42201e50b506 --- /dev/null +++ b/model/model/layers/12/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:457658f87ef54f90a2e595116d4910defaa8687093e537e9c2d3de4151e245f2 +size 4646991 diff --git a/model/model/layers/12/self_attn/q_proj/bias/.zarray b/model/model/layers/12/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/12/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/self_attn/q_proj/bias/0 b/model/model/layers/12/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..9a818c3afe6da5e7b87340c51d4e4dc0f9828e10 Binary files /dev/null and b/model/model/layers/12/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/12/self_attn/q_proj/kernel/.zarray b/model/model/layers/12/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/12/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/self_attn/q_proj/kernel/0.0 b/model/model/layers/12/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..763e70169999306ed1d6b0e840411376ed0ec447 --- /dev/null +++ b/model/model/layers/12/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e97baf06660361110706fd4fec78921e427ec9c4190315e5c985966041d86577 +size 4657399 diff --git a/model/model/layers/12/self_attn/q_proj/kernel/0.1 b/model/model/layers/12/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..067c178372265a892ef455a348541f9137b406f5 --- /dev/null +++ b/model/model/layers/12/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24a683a51afcf8500cd1c4b9935f64468324e0c6f9df4ec1bd672aadc8fc3a1d +size 4639018 diff --git a/model/model/layers/12/self_attn/q_proj/kernel/0.2 b/model/model/layers/12/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..d28efa0235f0f77d52805a345b44069c9ba71cea --- /dev/null +++ b/model/model/layers/12/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ef96e161b8091b14630fa96e9054f9398f0cdbfe5eb3e5c31859fbb16dcf477 +size 4669816 diff --git a/model/model/layers/12/self_attn/q_proj/kernel/0.3 b/model/model/layers/12/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..9c5bf1a49cb9d50699ed3c71babf0f139a9660d6 --- /dev/null +++ b/model/model/layers/12/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a110342aef6dcea258db2bd6b2990b732d85912abbb12eaed7bb205301e38324 +size 4638781 diff --git a/model/model/layers/12/self_attn/sinks/.zarray b/model/model/layers/12/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/12/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/self_attn/sinks/0 b/model/model/layers/12/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..0ba2fa585097be9597b6f01cbfbf08f6babb0470 Binary files /dev/null and b/model/model/layers/12/self_attn/sinks/0 differ diff --git a/model/model/layers/12/self_attn/v_proj/bias/.zarray b/model/model/layers/12/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/12/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/self_attn/v_proj/bias/0 b/model/model/layers/12/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..53e31052bdb53b69a33342db1302d45d3aec098a Binary files /dev/null and b/model/model/layers/12/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/12/self_attn/v_proj/kernel/.zarray b/model/model/layers/12/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/12/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/12/self_attn/v_proj/kernel/0.0 b/model/model/layers/12/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..025169aa5f6ca4d99ca9eb7821031dc848915fc9 --- /dev/null +++ b/model/model/layers/12/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0159aa7d436867ae0266437f87cc26c4682a21ff05b592387cfb916190dcf9a1 +size 577018 diff --git a/model/model/layers/12/self_attn/v_proj/kernel/0.1 b/model/model/layers/12/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..73d548f19b39b33ab39ca54a657898bb974c8cfb --- /dev/null +++ b/model/model/layers/12/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1aa34312a8a7e474484ec1870c198dfd8f48ba725ebf5b447c4a18653fcb7d2 +size 577153 diff --git a/model/model/layers/12/self_attn/v_proj/kernel/0.2 b/model/model/layers/12/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..f5d55ce0ce732f89cc2a7a355edb5c127dc4e8f4 --- /dev/null +++ b/model/model/layers/12/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ef3ad2ded6da67641bf40ecb36d27bb11e0292347c95d4654fb1c20f6633103 +size 576215 diff --git a/model/model/layers/12/self_attn/v_proj/kernel/0.3 b/model/model/layers/12/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..5e451ac15f3cd36e6cb27f4bc9ef571ccb4357a1 --- /dev/null +++ b/model/model/layers/12/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33391e395ea41d31e921fcf481fc70d917241032d27d75b7d5910aa6eeda2f85 +size 578872 diff --git a/model/model/layers/13/input_layernorm/kernel/.zarray b/model/model/layers/13/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/13/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/input_layernorm/kernel/0 b/model/model/layers/13/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..b69c8329b51a3d563627277e69b573fe8b2ead87 Binary files /dev/null and b/model/model/layers/13/input_layernorm/kernel/0 differ diff --git a/model/model/layers/13/mlp/experts/down_proj/bias/.zarray b/model/model/layers/13/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/13/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/mlp/experts/down_proj/bias/0.0 b/model/model/layers/13/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..a5a9add462dfad4fc3fed967cb42435bef5ad1f5 --- /dev/null +++ b/model/model/layers/13/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c52f2c92cc02e7e168992f43410eb376aba489ffc1e40912cfe831011905848 +size 145365 diff --git a/model/model/layers/13/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/13/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/13/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/13/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..07cf8e0b8b2af4d52fc4c489c6e407567c0d4a93 --- /dev/null +++ b/model/model/layers/13/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad6173d7a16ae103f9083c3c497fcb1195698c2af204c71545cbd27804e28083 +size 184962232 diff --git a/model/model/layers/13/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/13/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/13/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/13/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..ae6fd8b56cd0f26142759a6cefe440ad46399263 --- /dev/null +++ b/model/model/layers/13/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ff076aabd8236d94e4b69309a6fc8eddd8ebfd70ce270232202949ea4c7034f +size 141863 diff --git a/model/model/layers/13/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/13/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/13/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/13/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..35fe108c4b8ea0894e50951f87c7c574c47e0d7a --- /dev/null +++ b/model/model/layers/13/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d64d1590f3c4debc3766cc2b1e6b5703b0ff3f6eab4e888a2dc3e475617dcb3 +size 194124471 diff --git a/model/model/layers/13/mlp/experts/up_proj/bias/.zarray b/model/model/layers/13/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/13/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/mlp/experts/up_proj/bias/0.0 b/model/model/layers/13/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..2b8748fb0441124b67af2df7a721e0a941efb18e --- /dev/null +++ b/model/model/layers/13/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d068aaee874159e820270999961b4800624f811707a7b7576e81393217107179 +size 128484 diff --git a/model/model/layers/13/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/13/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/13/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/13/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..e6bd8a4d81a05302a215f2093593e9a1ace2dea7 --- /dev/null +++ b/model/model/layers/13/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cca149dd8e03133bd3a9b83ec80a2e692fc44ee96d157e38978947e7a34ae4b +size 184741779 diff --git a/model/model/layers/13/mlp/router/bias/.zarray b/model/model/layers/13/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/13/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/mlp/router/bias/0 b/model/model/layers/13/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..fd5f295f3480f18ea51d0b77650e993b86c7d97b Binary files /dev/null and b/model/model/layers/13/mlp/router/bias/0 differ diff --git a/model/model/layers/13/mlp/router/kernel/.zarray b/model/model/layers/13/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/13/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/mlp/router/kernel/0.0 b/model/model/layers/13/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..0571ebe5037c2e997a8aa802721d96002e36228c --- /dev/null +++ b/model/model/layers/13/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e481cb87053d75bc2ea1fcc8ff4d7e88a7808e3d745c818b20fd10cd30288d99 +size 144655 diff --git a/model/model/layers/13/post_attention_layernorm/kernel/.zarray b/model/model/layers/13/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/13/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/post_attention_layernorm/kernel/0 b/model/model/layers/13/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..8fee9bccf67d20bbf1d60b0989c3449f606956b9 Binary files /dev/null and b/model/model/layers/13/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/13/self_attn/k_proj/bias/.zarray b/model/model/layers/13/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/13/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/self_attn/k_proj/bias/0 b/model/model/layers/13/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/13/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/13/self_attn/k_proj/kernel/.zarray b/model/model/layers/13/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/13/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/self_attn/k_proj/kernel/0.0 b/model/model/layers/13/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..1c7a159a66fa21d2fa5749f49ab6a173b1ecef30 --- /dev/null +++ b/model/model/layers/13/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c780e9bad9c7c62e7be8d60779bed6846396095582549a43dfb576353e57e84 +size 597962 diff --git a/model/model/layers/13/self_attn/k_proj/kernel/0.1 b/model/model/layers/13/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..c35adcc56cd46bcefb6e845b4f93d8568bf3406f --- /dev/null +++ b/model/model/layers/13/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dbeb3b981f3c36a57a59819f10a140c7231f35adcfab454b553745135ad52ca +size 592831 diff --git a/model/model/layers/13/self_attn/k_proj/kernel/0.2 b/model/model/layers/13/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..061f3f4861c3184e22136d32f76fdc1ae897447a --- /dev/null +++ b/model/model/layers/13/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:191344c593189cb82eec6389e002329d2a3a275cc97a373bd952746757c4570e +size 594474 diff --git a/model/model/layers/13/self_attn/k_proj/kernel/0.3 b/model/model/layers/13/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..2a5f1537de445df19d2a31d15ce9cf8402ea4c2f --- /dev/null +++ b/model/model/layers/13/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2eb45fe5a75e340842c6cdfe688af852a67d177280bf644fe0347cdfe6225387 +size 596347 diff --git a/model/model/layers/13/self_attn/o_proj/bias/.zarray b/model/model/layers/13/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/13/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/self_attn/o_proj/bias/0 b/model/model/layers/13/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..d80046a6ae7af677c463b9b6f28e37ce7f5b5285 Binary files /dev/null and b/model/model/layers/13/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/13/self_attn/o_proj/kernel/.zarray b/model/model/layers/13/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/13/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/self_attn/o_proj/kernel/0.0 b/model/model/layers/13/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..800a5880a9a8b668fe6a09720f9fb2ea940e96e9 --- /dev/null +++ b/model/model/layers/13/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a927cb378cf80d2d1956eda3c61ef5ba93ff923f9331de788e712ec5129913e6 +size 4652042 diff --git a/model/model/layers/13/self_attn/o_proj/kernel/1.0 b/model/model/layers/13/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..fe3df158c0d81c217f2c947501e2a89b643f4033 --- /dev/null +++ b/model/model/layers/13/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1386bdbd44331e2c3e73bc09d16e93670c8c142f685571ec1c740c1fc6df7e5 +size 4650979 diff --git a/model/model/layers/13/self_attn/o_proj/kernel/2.0 b/model/model/layers/13/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..7004345612c0471b07e385e075441550d5da9ee7 --- /dev/null +++ b/model/model/layers/13/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e58280c8d9a479f7201c1a2de9d7a2e066cb442b92fbec6e6c4e43c38064a85b +size 4659869 diff --git a/model/model/layers/13/self_attn/o_proj/kernel/3.0 b/model/model/layers/13/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..2be5a81ef5cda0fca48d48becd2e03519cf2f050 --- /dev/null +++ b/model/model/layers/13/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bfba2c7b40273e664d8647af3dd18c19bc211e6d5f93e2a065bbb7417ecf335 +size 4654862 diff --git a/model/model/layers/13/self_attn/q_proj/bias/.zarray b/model/model/layers/13/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/13/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/self_attn/q_proj/bias/0 b/model/model/layers/13/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..925504050c901e57e186ed07058743a74031037e Binary files /dev/null and b/model/model/layers/13/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/13/self_attn/q_proj/kernel/.zarray b/model/model/layers/13/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/13/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/self_attn/q_proj/kernel/0.0 b/model/model/layers/13/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..662fdf6f362af3354f90aacbf3ff51b214788461 --- /dev/null +++ b/model/model/layers/13/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7fdb661df0e74e2516bf91bfc07c34fb0b98151f2fc71d547a4490f187603ff +size 4659790 diff --git a/model/model/layers/13/self_attn/q_proj/kernel/0.1 b/model/model/layers/13/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..feb81fff1450d0ca9e2d4f0cbd0539dd721e0741 --- /dev/null +++ b/model/model/layers/13/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dccee7209025ac189b17851ea8dbcad0cda8d667109ff18636c815931367710b +size 4649267 diff --git a/model/model/layers/13/self_attn/q_proj/kernel/0.2 b/model/model/layers/13/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..158e270ddd9e4d8914de0c3c73dc7282403521ef --- /dev/null +++ b/model/model/layers/13/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03cb6a7ffd765a2d21533572f2ff826af6c737152835ff2236f9318da3a4c6c6 +size 4650105 diff --git a/model/model/layers/13/self_attn/q_proj/kernel/0.3 b/model/model/layers/13/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..f6c31bd52f782d6241f5ba1a0ba552560139900f --- /dev/null +++ b/model/model/layers/13/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b4a2ddf5731ce72a66c1978166b1e841f34861406c7cd6e22a5e11915f287d +size 4670513 diff --git a/model/model/layers/13/self_attn/sinks/.zarray b/model/model/layers/13/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/13/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/self_attn/sinks/0 b/model/model/layers/13/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..0e01cbbe7ad1d9a21303a550e6a3629fd2bdc56b Binary files /dev/null and b/model/model/layers/13/self_attn/sinks/0 differ diff --git a/model/model/layers/13/self_attn/v_proj/bias/.zarray b/model/model/layers/13/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/13/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/self_attn/v_proj/bias/0 b/model/model/layers/13/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a23181060cf6eb46fdd9d988ec264b6e22ecd46a Binary files /dev/null and b/model/model/layers/13/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/13/self_attn/v_proj/kernel/.zarray b/model/model/layers/13/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/13/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/13/self_attn/v_proj/kernel/0.0 b/model/model/layers/13/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..8eff99348983f15eb7eb3d518490feee569bc7a6 --- /dev/null +++ b/model/model/layers/13/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a21573a12df52bd591af1e34d63d47571264f67e2966aab5f7e3252a894af2fa +size 576427 diff --git a/model/model/layers/13/self_attn/v_proj/kernel/0.1 b/model/model/layers/13/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..cce15a399a61349cd7fb2ac2f3a13f2bee5f546b --- /dev/null +++ b/model/model/layers/13/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8783616f17d0fd9698be1da009a00a48ed23999c0d2e0558e00d9874ba67d0ac +size 576288 diff --git a/model/model/layers/13/self_attn/v_proj/kernel/0.2 b/model/model/layers/13/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..36ba1fded5f0e61edf4e6910b9a8f69dc797b1cf --- /dev/null +++ b/model/model/layers/13/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f36981edf463ee4062c56fb2351543ed41a887e0ce42f37848931c1d476758a +size 578301 diff --git a/model/model/layers/13/self_attn/v_proj/kernel/0.3 b/model/model/layers/13/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..69eefff377b465cf995f4484030bc75fa2407a4b --- /dev/null +++ b/model/model/layers/13/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afdd0803466b78504bb7cf6dd9feade19a7690251643da91e10e7facc095e8ef +size 576732 diff --git a/model/model/layers/14/input_layernorm/kernel/.zarray b/model/model/layers/14/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/14/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/input_layernorm/kernel/0 b/model/model/layers/14/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..29298d20225dc8bf4075fa44fbf046ddb5f7a171 Binary files /dev/null and b/model/model/layers/14/input_layernorm/kernel/0 differ diff --git a/model/model/layers/14/mlp/experts/down_proj/bias/.zarray b/model/model/layers/14/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/14/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/mlp/experts/down_proj/bias/0.0 b/model/model/layers/14/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..995a913572857a22f39bef02f0e4100ff6d341be --- /dev/null +++ b/model/model/layers/14/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2439cdbd4b3abbf4a32be8f7fa92bf1401079a218031736db0e617d1054a1c9 +size 145274 diff --git a/model/model/layers/14/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/14/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/14/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/14/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..374ef246f5e85f348be1270f1c48e1e40068774e --- /dev/null +++ b/model/model/layers/14/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b75e7cc71252bb6147e117a58f0b8de5200bd8858a42cc8fccace0571e2eb7a +size 185367498 diff --git a/model/model/layers/14/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/14/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/14/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/14/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..a240acf66811ccba3e87e06ddef574e900dac3c0 --- /dev/null +++ b/model/model/layers/14/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28e97042ba52dc0dba2fd919c2bb2cb57e05ee04f22c51c1132c9fd32eec380d +size 143577 diff --git a/model/model/layers/14/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/14/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/14/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/14/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..daf658e7463320845702ddabd87471766abeff79 --- /dev/null +++ b/model/model/layers/14/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c42bd40de76a0e9ef7f6de2a5dc042b856297210c85062ba1f9bd2b7723a436 +size 193599070 diff --git a/model/model/layers/14/mlp/experts/up_proj/bias/.zarray b/model/model/layers/14/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/14/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/mlp/experts/up_proj/bias/0.0 b/model/model/layers/14/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..d0c9dfbb00e084676c76c302972d9679ff42fba4 --- /dev/null +++ b/model/model/layers/14/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:950328281ac0c15c101bb2e26bf98a7f678c82f288c62c8fb0183c0556d0f099 +size 130010 diff --git a/model/model/layers/14/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/14/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/14/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/14/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..831c53ec0bd44bd572937b7b5e6baf60c5287beb --- /dev/null +++ b/model/model/layers/14/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60955b48b061542eb8dca5aa6d8ab62c7f21150394aed881727a314b75020261 +size 185324288 diff --git a/model/model/layers/14/mlp/router/bias/.zarray b/model/model/layers/14/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/14/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/mlp/router/bias/0 b/model/model/layers/14/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..debfd16099e3f14f3bea5348487c65789391f678 Binary files /dev/null and b/model/model/layers/14/mlp/router/bias/0 differ diff --git a/model/model/layers/14/mlp/router/kernel/.zarray b/model/model/layers/14/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/14/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/mlp/router/kernel/0.0 b/model/model/layers/14/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..5d609426d1fab6c021c61e334898fc7140c16012 --- /dev/null +++ b/model/model/layers/14/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d600a513744b78585c5aaa36f13e657321ec93d206bee57cc23e4b5c5b53a25 +size 144978 diff --git a/model/model/layers/14/post_attention_layernorm/kernel/.zarray b/model/model/layers/14/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/14/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/post_attention_layernorm/kernel/0 b/model/model/layers/14/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..117709ee969f45274c771531c786ac2336500497 Binary files /dev/null and b/model/model/layers/14/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/14/self_attn/k_proj/bias/.zarray b/model/model/layers/14/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/14/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/self_attn/k_proj/bias/0 b/model/model/layers/14/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/14/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/14/self_attn/k_proj/kernel/.zarray b/model/model/layers/14/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/14/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/self_attn/k_proj/kernel/0.0 b/model/model/layers/14/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..96968fd0deff621bffdd8328130d604c81562840 --- /dev/null +++ b/model/model/layers/14/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b6b3ba8d1b317e9501543f44b2ee4034b1c3457cb364cafb73c3f926059402 +size 581533 diff --git a/model/model/layers/14/self_attn/k_proj/kernel/0.1 b/model/model/layers/14/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..e5a967270baac36d62721dc97b189fc56ef04744 --- /dev/null +++ b/model/model/layers/14/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e27bd8bcbd3640750035b5d0581e799bbb9f775718875f812eec25bcf41833e +size 581334 diff --git a/model/model/layers/14/self_attn/k_proj/kernel/0.2 b/model/model/layers/14/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..02f586c716a73738b4d190f5976e60af62a659e2 --- /dev/null +++ b/model/model/layers/14/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a041d383ad9047b6ee8d0a2a47b49e434384557d50ce6a0c8a1dcfbff0c8dbad +size 584526 diff --git a/model/model/layers/14/self_attn/k_proj/kernel/0.3 b/model/model/layers/14/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..e845df098977504a30a0bd98366d88ca1269980f --- /dev/null +++ b/model/model/layers/14/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f915fd3a56477947fb136993ac2dafb723df7d25075682f2bf9ed15b1a3f82c +size 583316 diff --git a/model/model/layers/14/self_attn/o_proj/bias/.zarray b/model/model/layers/14/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/14/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/self_attn/o_proj/bias/0 b/model/model/layers/14/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..03ceae7685f68135abfb594e28d593f56bbaafcf Binary files /dev/null and b/model/model/layers/14/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/14/self_attn/o_proj/kernel/.zarray b/model/model/layers/14/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/14/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/self_attn/o_proj/kernel/0.0 b/model/model/layers/14/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..b4dd1e01f890a171a4c7070335e6ee090409f74e --- /dev/null +++ b/model/model/layers/14/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d19bcb0709f4b5f0ef2be5cf48766fc59813e7d9144f111213574273b13a0ea2 +size 4644286 diff --git a/model/model/layers/14/self_attn/o_proj/kernel/1.0 b/model/model/layers/14/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..b9eb0e2c44f3863eb8db0c3013c89d6d96cd79a5 --- /dev/null +++ b/model/model/layers/14/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b7751856d8816599aa1662de3dc20cf0831e42562906e347ac69ea79c82a33d +size 4659358 diff --git a/model/model/layers/14/self_attn/o_proj/kernel/2.0 b/model/model/layers/14/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..1a4381b7c76ab8c26862e55f8bb199585f86fa0e --- /dev/null +++ b/model/model/layers/14/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2746288372aa4463aa003b1e09fbdbc6af409e3ad9cb6f630fa83832761fc7b3 +size 4640673 diff --git a/model/model/layers/14/self_attn/o_proj/kernel/3.0 b/model/model/layers/14/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..0b571b7f946e97b5c98dcdc9cdd12629ea73dccd --- /dev/null +++ b/model/model/layers/14/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69d7ac6c0cfa23c7e78956d64d5b5ca8a36caa9cdafc0fcd9c53df46d46bb3a3 +size 4662527 diff --git a/model/model/layers/14/self_attn/q_proj/bias/.zarray b/model/model/layers/14/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/14/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/self_attn/q_proj/bias/0 b/model/model/layers/14/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..2c04aa1b5dca01af1ba30c9a26d4e436a49276f2 Binary files /dev/null and b/model/model/layers/14/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/14/self_attn/q_proj/kernel/.zarray b/model/model/layers/14/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/14/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/self_attn/q_proj/kernel/0.0 b/model/model/layers/14/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..9952e5a7a0e6c572ad5258aec2f962d99a1a693f --- /dev/null +++ b/model/model/layers/14/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f3d75766b7e93de31bf282ee65563c8f51154b88d9c0809272046b576c39af6 +size 4668785 diff --git a/model/model/layers/14/self_attn/q_proj/kernel/0.1 b/model/model/layers/14/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..b62e963e809087e52eef305e9e814749d9b6591d --- /dev/null +++ b/model/model/layers/14/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1858a26eb8598701a973f505bd6a90e80196c20afe009d0a7122b18ba7ef51ae +size 4614710 diff --git a/model/model/layers/14/self_attn/q_proj/kernel/0.2 b/model/model/layers/14/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..69224f7bed0b6f669b917386619f83ba03b3a90b --- /dev/null +++ b/model/model/layers/14/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f2bdf4358d9cbfc0854a37f22785f63f71bb8738a9be317c4a06d5748f98562 +size 4704262 diff --git a/model/model/layers/14/self_attn/q_proj/kernel/0.3 b/model/model/layers/14/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..94d6d0e4644410253d79609a14d624f5e5408c42 --- /dev/null +++ b/model/model/layers/14/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cd788d20c4c32500da353bd86e904a54f34aea687fc720c9cd9cb8ffc3e46fb +size 4656279 diff --git a/model/model/layers/14/self_attn/sinks/.zarray b/model/model/layers/14/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/14/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/self_attn/sinks/0 b/model/model/layers/14/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..40724793afaeb25c49d978bd8acaf32aadcc8261 Binary files /dev/null and b/model/model/layers/14/self_attn/sinks/0 differ diff --git a/model/model/layers/14/self_attn/v_proj/bias/.zarray b/model/model/layers/14/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/14/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/self_attn/v_proj/bias/0 b/model/model/layers/14/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..fbbaa7081aeb64fbd86d974702636a7680c1aac5 Binary files /dev/null and b/model/model/layers/14/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/14/self_attn/v_proj/kernel/.zarray b/model/model/layers/14/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/14/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/14/self_attn/v_proj/kernel/0.0 b/model/model/layers/14/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..3898d27d5e7015d291b2bb663d4ca46004b18e05 --- /dev/null +++ b/model/model/layers/14/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19097fe8847d091d0c24287b2e2b959886c691c0dda2a44a6e30f0a4761ef3db +size 574466 diff --git a/model/model/layers/14/self_attn/v_proj/kernel/0.1 b/model/model/layers/14/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..cedebf9b5e9c0adc0528cc821e86f7d6593c34d0 --- /dev/null +++ b/model/model/layers/14/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d5c2f1a2ebacd2e80575f91d7ebfac5706267a2260ca8005b34eace9437cfcc +size 574425 diff --git a/model/model/layers/14/self_attn/v_proj/kernel/0.2 b/model/model/layers/14/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..0493c20a9a55824b9741a97873f53e216e48fb9e --- /dev/null +++ b/model/model/layers/14/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be261f2295fb7f25843a1c54e2dd9f8b6e04682ef2c1de1717161c03a1ca6989 +size 576030 diff --git a/model/model/layers/14/self_attn/v_proj/kernel/0.3 b/model/model/layers/14/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..bdf7aea2d6a135eb3201ca7f734c1cd88edbaf54 --- /dev/null +++ b/model/model/layers/14/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7de084bd49c9a2de9907b8b36f2b7d778ef4584df15dc3ff48c74dc128de501 +size 575525 diff --git a/model/model/layers/15/input_layernorm/kernel/.zarray b/model/model/layers/15/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/15/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/input_layernorm/kernel/0 b/model/model/layers/15/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..6d9752338209460c8e6a474e239c41afdb11f410 Binary files /dev/null and b/model/model/layers/15/input_layernorm/kernel/0 differ diff --git a/model/model/layers/15/mlp/experts/down_proj/bias/.zarray b/model/model/layers/15/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/15/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/mlp/experts/down_proj/bias/0.0 b/model/model/layers/15/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..16fbe63e2c7bfb37b412dced51dceb914f1c29d4 --- /dev/null +++ b/model/model/layers/15/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b61befe1aad656c422c0dce31c5fe50a7c9fd15c685f70613a02fe9bbe87d33 +size 145042 diff --git a/model/model/layers/15/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/15/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/15/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/15/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..a829fafcdcf4f100f0d60cd84d7e2dae16a53d4a --- /dev/null +++ b/model/model/layers/15/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ea702b7b31cb7d4c0b32be987261ca2e2194fa718a33ee8a8ae56db6142dcb8 +size 185671202 diff --git a/model/model/layers/15/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/15/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/15/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/15/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..e78fc6cf98afba210c6ff097a5a4a4727c3639b7 --- /dev/null +++ b/model/model/layers/15/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cc1c5330f2458b2cfee54150ccef70278209840f2782b9267dac8467766b5cb +size 144399 diff --git a/model/model/layers/15/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/15/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/15/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/15/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..42924ca0f90a6d32da2cee2927b429e11aa5255d --- /dev/null +++ b/model/model/layers/15/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54f59cdd933014e1ad0c4090802be95e3b2a99d8457b7d63361ea02d813e6459 +size 192930517 diff --git a/model/model/layers/15/mlp/experts/up_proj/bias/.zarray b/model/model/layers/15/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/15/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/mlp/experts/up_proj/bias/0.0 b/model/model/layers/15/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..6abfd1d963022b0fd7e19dc3c6f10dd368670685 --- /dev/null +++ b/model/model/layers/15/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bf8fe1d167ffc852653163c5422cfaadbda34bcf40b5c929b41e4de428f262a +size 130486 diff --git a/model/model/layers/15/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/15/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/15/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/15/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..305f40b30f0d2cf0836ccc4c6e629e9e94f4ca1d --- /dev/null +++ b/model/model/layers/15/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dd2d93f402df3f4e979f05910317272d993046611ad556100d06e5dab04a4da +size 185539953 diff --git a/model/model/layers/15/mlp/router/bias/.zarray b/model/model/layers/15/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/15/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/mlp/router/bias/0 b/model/model/layers/15/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..532ddea83041b8337f848e093f42cc413e2fe296 Binary files /dev/null and b/model/model/layers/15/mlp/router/bias/0 differ diff --git a/model/model/layers/15/mlp/router/kernel/.zarray b/model/model/layers/15/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/15/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/mlp/router/kernel/0.0 b/model/model/layers/15/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..405f3c96fc29f062a681a72f971f10cd080c40a9 --- /dev/null +++ b/model/model/layers/15/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:281442370f064eaa9546bbae269e813134ba25c98cb3df61a0b9a7b63e459b79 +size 144856 diff --git a/model/model/layers/15/post_attention_layernorm/kernel/.zarray b/model/model/layers/15/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/15/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/post_attention_layernorm/kernel/0 b/model/model/layers/15/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..b595bb2813494a658909f0afab604c1b17a7bd27 Binary files /dev/null and b/model/model/layers/15/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/15/self_attn/k_proj/bias/.zarray b/model/model/layers/15/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/15/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/self_attn/k_proj/bias/0 b/model/model/layers/15/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/15/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/15/self_attn/k_proj/kernel/.zarray b/model/model/layers/15/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/15/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/self_attn/k_proj/kernel/0.0 b/model/model/layers/15/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..aa9e97d94e81b1237265af2f9e327898e083f979 --- /dev/null +++ b/model/model/layers/15/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d13185bd3e982fe46a1214f29a46df6099d4bdc8d490d9469be7c0d964efdb9a +size 597144 diff --git a/model/model/layers/15/self_attn/k_proj/kernel/0.1 b/model/model/layers/15/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..2452d4033d8868d8f1589dbf3f4797c0ae91d4f3 --- /dev/null +++ b/model/model/layers/15/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9785b89d7e2aec1a061634337a319c638f374da9e7b1620a08828d7419c3d9c +size 599484 diff --git a/model/model/layers/15/self_attn/k_proj/kernel/0.2 b/model/model/layers/15/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..ea4797db239fad9db3ec0882c66180afc14fdbe9 --- /dev/null +++ b/model/model/layers/15/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f8a379a0b791dde9e544c83da9fa0e56c47feeb4b2e2ca0dd1ae9f8941ae9ae +size 589711 diff --git a/model/model/layers/15/self_attn/k_proj/kernel/0.3 b/model/model/layers/15/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..9ad6f90a6f76f8e2b21a46cbc32da3a66df97c7e --- /dev/null +++ b/model/model/layers/15/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:356377b5c8af4d33dc0556c24896647c505fa1c02bd191245ea7de1452aa752b +size 589061 diff --git a/model/model/layers/15/self_attn/o_proj/bias/.zarray b/model/model/layers/15/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/15/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/self_attn/o_proj/bias/0 b/model/model/layers/15/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..f8b551071367dc8e6b4f2adc1450431fd35ddc44 Binary files /dev/null and b/model/model/layers/15/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/15/self_attn/o_proj/kernel/.zarray b/model/model/layers/15/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/15/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/self_attn/o_proj/kernel/0.0 b/model/model/layers/15/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..7f7e150ce57cd3460e04e8963e90ae149c8319e9 --- /dev/null +++ b/model/model/layers/15/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48ce424ed5208fc5d1c0cf42010627bf5538f29bfbd8c9713a2712b2b30e1ba2 +size 4645928 diff --git a/model/model/layers/15/self_attn/o_proj/kernel/1.0 b/model/model/layers/15/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..44f0a86a4e25d52d3dc184fabe9521c004ad1f8f --- /dev/null +++ b/model/model/layers/15/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47cead6c4b962d95ae38f953bff1ec0272e6b7f435eea117b6c28bc401a77908 +size 4652788 diff --git a/model/model/layers/15/self_attn/o_proj/kernel/2.0 b/model/model/layers/15/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..593b955d12bf759171c47cc35c812bf25507c2b6 --- /dev/null +++ b/model/model/layers/15/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d7912e3bd8f6ea16aa1e048b0c5ee164a47cd795625a1baf09da82e3912c7d3 +size 4653518 diff --git a/model/model/layers/15/self_attn/o_proj/kernel/3.0 b/model/model/layers/15/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..699b0d08b09cfaf8aeb19ec352f4dd3957c2180f --- /dev/null +++ b/model/model/layers/15/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e6e39aaf6a9f7410231430521283130cbbb2a178872988545e547871b82a4db +size 4652160 diff --git a/model/model/layers/15/self_attn/q_proj/bias/.zarray b/model/model/layers/15/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/15/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/self_attn/q_proj/bias/0 b/model/model/layers/15/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..ec91d22a992789fbfa70bb03e1d208393a67d5b6 Binary files /dev/null and b/model/model/layers/15/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/15/self_attn/q_proj/kernel/.zarray b/model/model/layers/15/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/15/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/self_attn/q_proj/kernel/0.0 b/model/model/layers/15/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..ff514298fc687bef2b9b762f78eb8c66c947f78b --- /dev/null +++ b/model/model/layers/15/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e66595764ca9760fb2a0e8ee25f7f530467ffde8a5715fdceefd5422cb98ca2a +size 4674961 diff --git a/model/model/layers/15/self_attn/q_proj/kernel/0.1 b/model/model/layers/15/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..b9c6e4b2b43ee10c685e8d20270051fe557a2285 --- /dev/null +++ b/model/model/layers/15/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e016cc23c9d1726f0f2aace09576ee043550451d452c0dd069f09be8b20f81cd +size 4668519 diff --git a/model/model/layers/15/self_attn/q_proj/kernel/0.2 b/model/model/layers/15/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..2f0eacc3e4a3309965d4213f37de26bad62d3c5e --- /dev/null +++ b/model/model/layers/15/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c079459be8ccb91fc5df69a1e5bbf35b81e1d910200c7162292b3df42d71c720 +size 4665910 diff --git a/model/model/layers/15/self_attn/q_proj/kernel/0.3 b/model/model/layers/15/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..d8b968d1bd9df163fd5152c4eaba4cc5df744db7 --- /dev/null +++ b/model/model/layers/15/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bccc210f8c62926c82a9aaf961faa8552e8a3b75b3d7f62cf9aeca913136324d +size 4681752 diff --git a/model/model/layers/15/self_attn/sinks/.zarray b/model/model/layers/15/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/15/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/self_attn/sinks/0 b/model/model/layers/15/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..107c0369a49260914a2a2346a8ec9796c88473f9 Binary files /dev/null and b/model/model/layers/15/self_attn/sinks/0 differ diff --git a/model/model/layers/15/self_attn/v_proj/bias/.zarray b/model/model/layers/15/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/15/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/self_attn/v_proj/bias/0 b/model/model/layers/15/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..19370bec96d6b8171f9b63bc3cc77add7d4d3703 Binary files /dev/null and b/model/model/layers/15/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/15/self_attn/v_proj/kernel/.zarray b/model/model/layers/15/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/15/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/15/self_attn/v_proj/kernel/0.0 b/model/model/layers/15/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..e98607435bafc943e8e8176f37919f2fd42ee5db --- /dev/null +++ b/model/model/layers/15/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6349a3b251db26a8243bac634e190459981c8d4006a6f82630f55d0e932f6524 +size 576420 diff --git a/model/model/layers/15/self_attn/v_proj/kernel/0.1 b/model/model/layers/15/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..bfc9ee9a57fec8cfee7146be658a221ff7e6a165 --- /dev/null +++ b/model/model/layers/15/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ca2e60d79c008a4bc2fdf1a2cb68bebc90731af4e9b61d620cbc4d0650b8b7e +size 576802 diff --git a/model/model/layers/15/self_attn/v_proj/kernel/0.2 b/model/model/layers/15/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..e4a072ad09de9f876bb2691670b908698ba9f216 --- /dev/null +++ b/model/model/layers/15/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff967582004e7927ad29524544769fe2054453642c1d3560f0de12e9057fb8b2 +size 578760 diff --git a/model/model/layers/15/self_attn/v_proj/kernel/0.3 b/model/model/layers/15/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..02432b3a2cdfddf919334903cdcd383d6e37b49d --- /dev/null +++ b/model/model/layers/15/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ff403eab9d24b3f19f0eb75123dda9e5e021050e9c44a47abe7f72966586087 +size 576633 diff --git a/model/model/layers/16/input_layernorm/kernel/.zarray b/model/model/layers/16/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/16/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/input_layernorm/kernel/0 b/model/model/layers/16/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..3dfee06a2fb9e39e8710824496a5d760fe73b931 Binary files /dev/null and b/model/model/layers/16/input_layernorm/kernel/0 differ diff --git a/model/model/layers/16/mlp/experts/down_proj/bias/.zarray b/model/model/layers/16/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/16/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/mlp/experts/down_proj/bias/0.0 b/model/model/layers/16/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..3e3afb3b7e2035df8e7e09181afe5190dd531e7a --- /dev/null +++ b/model/model/layers/16/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e3f1801311a7346ba74a80b4e32a87b59e9584bbb1601ef2574a02ca4cb076d +size 145018 diff --git a/model/model/layers/16/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/16/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/16/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/16/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..8ccac939e3881f6a6c788414fe97fa15b9fe6f49 --- /dev/null +++ b/model/model/layers/16/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7afa87d91eaab1fe804ea095f2d54f2d6685a662ed92dc0ad115a763442d84ab +size 186495785 diff --git a/model/model/layers/16/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/16/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/16/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/16/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..4de3227510ee19aac3eb8688888cb0ca3387c10e --- /dev/null +++ b/model/model/layers/16/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c56b165b990d3009033cc930e59a266dca9d6f511e5c444016406774a8b715cd +size 144734 diff --git a/model/model/layers/16/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/16/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/16/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/16/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..2b773312b101d190d025d043e62e0f2c0a4d5924 --- /dev/null +++ b/model/model/layers/16/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef45cc0a36148841d6d94d18a773e1d3ed84542d5cdd61ac213149accd4c1147 +size 193099783 diff --git a/model/model/layers/16/mlp/experts/up_proj/bias/.zarray b/model/model/layers/16/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/16/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/mlp/experts/up_proj/bias/0.0 b/model/model/layers/16/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..b16fd87896a931a0f6fab437f411e9a6dee7451a --- /dev/null +++ b/model/model/layers/16/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b53b4c806085b9097d5ad1061e837ae7852b6514c1e31102ce9a78c3d89b8cf6 +size 130274 diff --git a/model/model/layers/16/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/16/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/16/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/16/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..1a697f33d497dc5df3e81d326fa631aba4f69d1d --- /dev/null +++ b/model/model/layers/16/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e652c9d2bad0d7b5749f015d8e9ae8b6f4a04cd596fc28d6921a6644942c066 +size 184066315 diff --git a/model/model/layers/16/mlp/router/bias/.zarray b/model/model/layers/16/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/16/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/mlp/router/bias/0 b/model/model/layers/16/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..5d62c00303a0a09e8fc64f28a0517564d4379d77 Binary files /dev/null and b/model/model/layers/16/mlp/router/bias/0 differ diff --git a/model/model/layers/16/mlp/router/kernel/.zarray b/model/model/layers/16/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/16/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/mlp/router/kernel/0.0 b/model/model/layers/16/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..e6ba15b65e5c029fed7258808bde88be80968df3 --- /dev/null +++ b/model/model/layers/16/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:167926c06f898b52d6f59bd0ba3c6925f02110697a4c1fd344cefd6c3ba9a3e5 +size 144690 diff --git a/model/model/layers/16/post_attention_layernorm/kernel/.zarray b/model/model/layers/16/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/16/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/post_attention_layernorm/kernel/0 b/model/model/layers/16/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..1df8215dafc91611afa38d780317c978a3e8188b Binary files /dev/null and b/model/model/layers/16/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/16/self_attn/k_proj/bias/.zarray b/model/model/layers/16/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/16/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/self_attn/k_proj/bias/0 b/model/model/layers/16/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/16/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/16/self_attn/k_proj/kernel/.zarray b/model/model/layers/16/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/16/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/self_attn/k_proj/kernel/0.0 b/model/model/layers/16/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..44ce539b84263b6f67a7fe05766d773e8eecc7db --- /dev/null +++ b/model/model/layers/16/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa2009d80be9b09271d1824269fef5a37ff4dd7cb945c029b7ba5af9f24b31dc +size 582105 diff --git a/model/model/layers/16/self_attn/k_proj/kernel/0.1 b/model/model/layers/16/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..145fdbdd698a7bda8cbbbbc4d6e04043b7621a1b --- /dev/null +++ b/model/model/layers/16/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6576aeb19fd64351cb895458a16f4af40279029965fb1a0987f9094af5553eb +size 585891 diff --git a/model/model/layers/16/self_attn/k_proj/kernel/0.2 b/model/model/layers/16/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..53be7fd6a69bcf6fd2358aef6566c714ddddf44c --- /dev/null +++ b/model/model/layers/16/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccaeef2952d9a8b4863e4ad68cea5aa3facfb400823d0f41ed41dbb10f2d43e5 +size 581335 diff --git a/model/model/layers/16/self_attn/k_proj/kernel/0.3 b/model/model/layers/16/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..071ee8ae9467d9e1e7d45caff624e1509323dc6e --- /dev/null +++ b/model/model/layers/16/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b60991b4d451e180b07d038af424df7b6b94ac7f2af1be3ba1a2a164440b9765 +size 581288 diff --git a/model/model/layers/16/self_attn/o_proj/bias/.zarray b/model/model/layers/16/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/16/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/self_attn/o_proj/bias/0 b/model/model/layers/16/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..d1eb9ae4f8f71633ebcf3c13bf10c1c7f4e80324 Binary files /dev/null and b/model/model/layers/16/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/16/self_attn/o_proj/kernel/.zarray b/model/model/layers/16/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/16/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/self_attn/o_proj/kernel/0.0 b/model/model/layers/16/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..7a709ae1f1656ad72c4a7ce994b626cd41340fcb --- /dev/null +++ b/model/model/layers/16/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22bfe164501a196915e13deb79a7d6dbca8f94907bd4753af166b31d30e7d7ad +size 4656713 diff --git a/model/model/layers/16/self_attn/o_proj/kernel/1.0 b/model/model/layers/16/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..f63539f04e5e14c027008534321c9e827b828946 --- /dev/null +++ b/model/model/layers/16/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e44717474b1e68f27ea50463603d06f89af6d4a38406a41d110aec3369bb157 +size 4660673 diff --git a/model/model/layers/16/self_attn/o_proj/kernel/2.0 b/model/model/layers/16/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..95b30f1f246657c25a5a70f6589bfe96095b2047 --- /dev/null +++ b/model/model/layers/16/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1b75539583035fabdeadbd30463ea9985dc563830f5dbf8c4e4a312827c5658 +size 4650427 diff --git a/model/model/layers/16/self_attn/o_proj/kernel/3.0 b/model/model/layers/16/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..2509ada4871ddbdd40146a189f7b8f3f9572a991 --- /dev/null +++ b/model/model/layers/16/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dae9e52898f72f4bdfa03f547b358009faa8f2a474ae0a8c34039dd0d302a0e5 +size 4660440 diff --git a/model/model/layers/16/self_attn/q_proj/bias/.zarray b/model/model/layers/16/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/16/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/self_attn/q_proj/bias/0 b/model/model/layers/16/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..8f7eb388e52cd5df9b986536aa48dec1d3af8a05 Binary files /dev/null and b/model/model/layers/16/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/16/self_attn/q_proj/kernel/.zarray b/model/model/layers/16/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/16/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/self_attn/q_proj/kernel/0.0 b/model/model/layers/16/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..c276e6e65b3491ccce033a2abf225bfc494fb118 --- /dev/null +++ b/model/model/layers/16/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56ea656496f9b847ff696705bfb78f9e9d7621f4651f44b05233b9bc2a17e486 +size 4640981 diff --git a/model/model/layers/16/self_attn/q_proj/kernel/0.1 b/model/model/layers/16/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..23e0caf3897318c23b06ef9f24161e8d31d3f044 --- /dev/null +++ b/model/model/layers/16/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b616380f1196c9ccfe0a68fac29b6453e8faeec0ed9900bd3966863f5cd49c0 +size 4708987 diff --git a/model/model/layers/16/self_attn/q_proj/kernel/0.2 b/model/model/layers/16/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..7d2bfc27c9e66011abb77b81814261e0bbc8b2c5 --- /dev/null +++ b/model/model/layers/16/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c24bc1f30b879c243d59ac0c0da373a943e5bc605cd58fb1bd53b4aeb7f2ca8 +size 4661821 diff --git a/model/model/layers/16/self_attn/q_proj/kernel/0.3 b/model/model/layers/16/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..9f9734f08dfb1806507e1af62f365b71c0cdd77a --- /dev/null +++ b/model/model/layers/16/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed4987486fd5ddbd9d52ba49990930a7c19adbcd6a2aceceeda975bb38dc1e37 +size 4670466 diff --git a/model/model/layers/16/self_attn/sinks/.zarray b/model/model/layers/16/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/16/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/self_attn/sinks/0 b/model/model/layers/16/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..4a03107e068b661337a511bf0ba1fa6fb72fec10 Binary files /dev/null and b/model/model/layers/16/self_attn/sinks/0 differ diff --git a/model/model/layers/16/self_attn/v_proj/bias/.zarray b/model/model/layers/16/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/16/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/self_attn/v_proj/bias/0 b/model/model/layers/16/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..d67d98fa4c54f891155fda44c1d03cae1866e01f Binary files /dev/null and b/model/model/layers/16/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/16/self_attn/v_proj/kernel/.zarray b/model/model/layers/16/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/16/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/16/self_attn/v_proj/kernel/0.0 b/model/model/layers/16/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..d18176a41e089074fe5ddda650953f783da2a78a --- /dev/null +++ b/model/model/layers/16/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:772a02f9a7daaa97a4cacf0e58824fd6f53b3b522623f59590c1c6e484fde064 +size 576212 diff --git a/model/model/layers/16/self_attn/v_proj/kernel/0.1 b/model/model/layers/16/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..3779043a94228e3c6492cbf6c5fbb7f751afbe99 --- /dev/null +++ b/model/model/layers/16/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4ecf754f240fdeffe103ff960eac88c66bb7d0400580e50ae188d54d2949bb1 +size 574058 diff --git a/model/model/layers/16/self_attn/v_proj/kernel/0.2 b/model/model/layers/16/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..d290fcc98c37a80239ddc0d051a555e0d6c53ea0 --- /dev/null +++ b/model/model/layers/16/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:981a9e60b39dfc3eb643359cfc2fb0a9842492cb4acb93b2141a3d5de778ff14 +size 575721 diff --git a/model/model/layers/16/self_attn/v_proj/kernel/0.3 b/model/model/layers/16/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..bccc2e563f28c44cc2c9d599fbe91e1783a9bc10 --- /dev/null +++ b/model/model/layers/16/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d139146ed9c5d05f06fc4868391377a0fe118a87ac9467d64fd07452362aaea +size 574256 diff --git a/model/model/layers/17/input_layernorm/kernel/.zarray b/model/model/layers/17/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/17/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/input_layernorm/kernel/0 b/model/model/layers/17/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..d520ceb472e0cb3e979fc72c55ec07834d9c1a1c Binary files /dev/null and b/model/model/layers/17/input_layernorm/kernel/0 differ diff --git a/model/model/layers/17/mlp/experts/down_proj/bias/.zarray b/model/model/layers/17/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/17/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/mlp/experts/down_proj/bias/0.0 b/model/model/layers/17/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..cd895935f4bf381a23fbc8a2f8b6b692f4214d8f --- /dev/null +++ b/model/model/layers/17/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:713e8391d38d8d7c23d8c9fcbf730abf89e4c93248ad8ad0b02150549db578e3 +size 145544 diff --git a/model/model/layers/17/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/17/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/17/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/17/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..59ddcc4c6569044d29bfb686df4e0ffc09340624 --- /dev/null +++ b/model/model/layers/17/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6565d091229fa5d17f458223e4ce95c5e21882b0626b268f74ef35a39e0ad1a +size 188253635 diff --git a/model/model/layers/17/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/17/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/17/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/17/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..c51b0d47e6a39fd1c3cbdf7054881f4c027b9a8d --- /dev/null +++ b/model/model/layers/17/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7341e373b87ada2ee6285fb0e77a562948422b3e484bfc147e35d499b22a922b +size 143499 diff --git a/model/model/layers/17/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/17/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/17/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/17/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..aad3cf4111011e429da0630c606dfba3ba6265ac --- /dev/null +++ b/model/model/layers/17/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:970a99df6488dea6f1679f09553831be54fa9e0961b6cad2c5edcdd117abd6e9 +size 192118800 diff --git a/model/model/layers/17/mlp/experts/up_proj/bias/.zarray b/model/model/layers/17/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/17/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/mlp/experts/up_proj/bias/0.0 b/model/model/layers/17/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..1a508e7d432f0dad862b2941dfbd7cf721a82ec9 --- /dev/null +++ b/model/model/layers/17/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcba47cbf2ae96404ddd9a405bc42a9a5b1651bd556a05e6e028be3686eb6caf +size 131551 diff --git a/model/model/layers/17/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/17/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/17/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/17/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..8f1d1e9099a578e2b90db71c77ca697462d6ba72 --- /dev/null +++ b/model/model/layers/17/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d36c7f0d7bc2e05e5b3358416c58f90dd3a818185e6dd6d1f0613cb9bc702df9 +size 184562039 diff --git a/model/model/layers/17/mlp/router/bias/.zarray b/model/model/layers/17/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/17/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/mlp/router/bias/0 b/model/model/layers/17/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..0fcaade015a901e4dc09c09cfbea06624f49b25a Binary files /dev/null and b/model/model/layers/17/mlp/router/bias/0 differ diff --git a/model/model/layers/17/mlp/router/kernel/.zarray b/model/model/layers/17/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/17/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/mlp/router/kernel/0.0 b/model/model/layers/17/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..7f71ea1d68a1dbd830b02a4e15c25c614e579b38 --- /dev/null +++ b/model/model/layers/17/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a956ef09b22c3045e1aa5459da2407ae52c083f842203eb0eb918364f00f6d61 +size 144771 diff --git a/model/model/layers/17/post_attention_layernorm/kernel/.zarray b/model/model/layers/17/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/17/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/post_attention_layernorm/kernel/0 b/model/model/layers/17/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..413c03851fbc6637cc7bd16a8e32e8afa09c101b Binary files /dev/null and b/model/model/layers/17/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/17/self_attn/k_proj/bias/.zarray b/model/model/layers/17/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/17/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/self_attn/k_proj/bias/0 b/model/model/layers/17/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/17/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/17/self_attn/k_proj/kernel/.zarray b/model/model/layers/17/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/17/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/self_attn/k_proj/kernel/0.0 b/model/model/layers/17/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..ba803a5e7deac6428bd7b66f8997da084d5028f9 --- /dev/null +++ b/model/model/layers/17/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b650cd527c93b3a67cdfd42ccebbfd75bcc9a619b817ceca576ca67d9c559d9b +size 608996 diff --git a/model/model/layers/17/self_attn/k_proj/kernel/0.1 b/model/model/layers/17/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..78c7df6bf591b757928e0994e2f144161db28121 --- /dev/null +++ b/model/model/layers/17/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9776896cc201cc248fa4913a42bc10abed0af516d744029ee64814cca03c2352 +size 594599 diff --git a/model/model/layers/17/self_attn/k_proj/kernel/0.2 b/model/model/layers/17/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..3a54b4b0a814d60b15571577e7956b267a15504f --- /dev/null +++ b/model/model/layers/17/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:953f50893416580310f31fb69c7c848b6eed7c5d91d2901a2c9278fae3238960 +size 600601 diff --git a/model/model/layers/17/self_attn/k_proj/kernel/0.3 b/model/model/layers/17/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..dd3d917c4d77626401c5c4e15311690523bcd153 --- /dev/null +++ b/model/model/layers/17/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1bc841ebb6fa22054040d7b80ee4d39440aeffc5325ba2624a07d7674d38ea6 +size 599590 diff --git a/model/model/layers/17/self_attn/o_proj/bias/.zarray b/model/model/layers/17/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/17/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/self_attn/o_proj/bias/0 b/model/model/layers/17/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..0f97f3653e24fd3f843e46d501efaa11442a5cb5 Binary files /dev/null and b/model/model/layers/17/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/17/self_attn/o_proj/kernel/.zarray b/model/model/layers/17/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/17/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/self_attn/o_proj/kernel/0.0 b/model/model/layers/17/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..c3e485b7f0ccf2f160b1e71c39c3819d8802e5bf --- /dev/null +++ b/model/model/layers/17/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48320bfbf3767ca77c65d8a8d945ee7bbc4b0d304a40f4ca6020f1f65b3f9653 +size 4660196 diff --git a/model/model/layers/17/self_attn/o_proj/kernel/1.0 b/model/model/layers/17/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..f062dcf8732aa41a076e2a038837d268db3876d9 --- /dev/null +++ b/model/model/layers/17/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5e4ccd97101599bef070f9d60de9fc7f790af1d96b0332945d2502cd3ab751c +size 4665872 diff --git a/model/model/layers/17/self_attn/o_proj/kernel/2.0 b/model/model/layers/17/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..ff06e8659c4439cf94df155740ee0bd253660de0 --- /dev/null +++ b/model/model/layers/17/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71355201ec75a5a9a76b53f50502f6dd4c9c55fd55b1ea40bc41320f773f9d32 +size 4672372 diff --git a/model/model/layers/17/self_attn/o_proj/kernel/3.0 b/model/model/layers/17/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..0712fbb1a2ccf5da9f5ff2e9e459c25d5558c9c1 --- /dev/null +++ b/model/model/layers/17/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fa03e27dabe0baa67a62a2a3db672d1f057acae34fe6e3a7b17480c0b7d0d30 +size 4667491 diff --git a/model/model/layers/17/self_attn/q_proj/bias/.zarray b/model/model/layers/17/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/17/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/self_attn/q_proj/bias/0 b/model/model/layers/17/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..67a54144f8a89932527cdf86b7b0203f920842cf Binary files /dev/null and b/model/model/layers/17/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/17/self_attn/q_proj/kernel/.zarray b/model/model/layers/17/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/17/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/self_attn/q_proj/kernel/0.0 b/model/model/layers/17/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..ecda8580398fb8d01f511cc6e221968835db0b78 --- /dev/null +++ b/model/model/layers/17/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc37077cb71790448acc397a3de9f663e5afc95963404fdb9076b110b0e5215b +size 4707673 diff --git a/model/model/layers/17/self_attn/q_proj/kernel/0.1 b/model/model/layers/17/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..590064964852906367cf6c288c0fac0059000410 --- /dev/null +++ b/model/model/layers/17/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0fb55ef26dea78dc5240366fd2de17c81be8c101ae23e5f35ee25d766e394af +size 4678261 diff --git a/model/model/layers/17/self_attn/q_proj/kernel/0.2 b/model/model/layers/17/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..0e47aa745ad73a17399c782c4756ec4cc10c39c5 --- /dev/null +++ b/model/model/layers/17/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00fe779d3fbf2841f52e2d8d9621502fe58091cda9195b6abd539dd42769f5d3 +size 4686267 diff --git a/model/model/layers/17/self_attn/q_proj/kernel/0.3 b/model/model/layers/17/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..b1f2fc4d2fb33a47719b3c5578b25dca7c33997c --- /dev/null +++ b/model/model/layers/17/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25d9631918f0295e49abee6cbf1dcb45426edb8af0bb78cf2c27b25ea670dab5 +size 4670120 diff --git a/model/model/layers/17/self_attn/sinks/.zarray b/model/model/layers/17/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/17/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/self_attn/sinks/0 b/model/model/layers/17/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..cf4bb0f4a9b73f53049bedaedc95471720c177ad Binary files /dev/null and b/model/model/layers/17/self_attn/sinks/0 differ diff --git a/model/model/layers/17/self_attn/v_proj/bias/.zarray b/model/model/layers/17/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/17/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/self_attn/v_proj/bias/0 b/model/model/layers/17/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..eb8046b6563ec450ca83d22eadac3522c808e914 Binary files /dev/null and b/model/model/layers/17/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/17/self_attn/v_proj/kernel/.zarray b/model/model/layers/17/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/17/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/17/self_attn/v_proj/kernel/0.0 b/model/model/layers/17/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..72cd6227740809a80152bfb806f4df9bf9d7fb2d --- /dev/null +++ b/model/model/layers/17/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3605d34316f290f78b72e998143c68334a204ecb9f32bb758e4c05230e9d997e +size 576493 diff --git a/model/model/layers/17/self_attn/v_proj/kernel/0.1 b/model/model/layers/17/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..08d82aae19f4af2c398a442b642ba55a0deb5b41 --- /dev/null +++ b/model/model/layers/17/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bca889bac81791a7879a447ec3d7159f90f9a8b222594e2a9ad1d94ffdf27c4d +size 576180 diff --git a/model/model/layers/17/self_attn/v_proj/kernel/0.2 b/model/model/layers/17/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..a83dedb23d54dda29e9a13ce98c83b95061959d1 --- /dev/null +++ b/model/model/layers/17/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29dfd14ea5d9f2beaed62f46d0cbc6e96fee64eb1cbd2574ed8cff2ec71c2d93 +size 576186 diff --git a/model/model/layers/17/self_attn/v_proj/kernel/0.3 b/model/model/layers/17/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..388b9c248c0389e48b2fe9c1498db659d8156d5b --- /dev/null +++ b/model/model/layers/17/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec2db45c1c43e3e8e63855c1b1089b5bf045c4d6b207e514d85499c8b535ed0a +size 576184 diff --git a/model/model/layers/18/input_layernorm/kernel/.zarray b/model/model/layers/18/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/18/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/input_layernorm/kernel/0 b/model/model/layers/18/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..139fa180041c499de68b1defa8bf9fcb0f812030 Binary files /dev/null and b/model/model/layers/18/input_layernorm/kernel/0 differ diff --git a/model/model/layers/18/mlp/experts/down_proj/bias/.zarray b/model/model/layers/18/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/18/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/mlp/experts/down_proj/bias/0.0 b/model/model/layers/18/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..77baeae806b4a82938d4267cedceb2d053d2acbb --- /dev/null +++ b/model/model/layers/18/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ec3c1795ef1acc9e06f4a9ce69ac5b8634a0cce44d61ed883cc4f28dfc2b4b8 +size 145790 diff --git a/model/model/layers/18/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/18/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/18/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/18/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..2ba8f3352be6772b5402a2afbcab12cbafa175b1 --- /dev/null +++ b/model/model/layers/18/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c7a3a7a52224b65f06510f3e29c6e8a96b4d357d748db79dee9f8d6b769c3c3c +size 188054737 diff --git a/model/model/layers/18/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/18/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/18/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/18/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..c840cf6cafdc33b6ab585aeda8a738d319f12d50 --- /dev/null +++ b/model/model/layers/18/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ad4763345f673454433fca17b4dbb1dd9a0c2aef4138b9749408a4f18cbc122 +size 144589 diff --git a/model/model/layers/18/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/18/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/18/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/18/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..f1177e42ec590dcc852d9d0d394842890464116b --- /dev/null +++ b/model/model/layers/18/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:138c42109261695d6ec44b0d231823d4abf80a6b8ce03de6f0ee9fed0a148497 +size 193390636 diff --git a/model/model/layers/18/mlp/experts/up_proj/bias/.zarray b/model/model/layers/18/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/18/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/mlp/experts/up_proj/bias/0.0 b/model/model/layers/18/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..001e46160ce644040d43e07255522a0b69e5f92e --- /dev/null +++ b/model/model/layers/18/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebbb080c1d1bb6746b9ce9d16cc24315c392ee2e9c086d4b77aff19674db2db5 +size 132694 diff --git a/model/model/layers/18/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/18/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/18/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/18/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..f6e84aa96ff617f1a1a6b53ddca270e060b1d24c --- /dev/null +++ b/model/model/layers/18/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:820ef2ef331be19eb06ab774b28079b37271b8ea1d7eb909345c288ae45c3f67 +size 184790671 diff --git a/model/model/layers/18/mlp/router/bias/.zarray b/model/model/layers/18/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/18/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/mlp/router/bias/0 b/model/model/layers/18/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..2fd0973aad0c39c0247da285e266e05ab15311c2 Binary files /dev/null and b/model/model/layers/18/mlp/router/bias/0 differ diff --git a/model/model/layers/18/mlp/router/kernel/.zarray b/model/model/layers/18/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/18/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/mlp/router/kernel/0.0 b/model/model/layers/18/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..4a2ab5c326e8ca703f25858519596a3dcaf6e210 --- /dev/null +++ b/model/model/layers/18/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1aef8e2b081b065313eebf5e520b0221da1304065a95d6480fa482b463e52af3 +size 144787 diff --git a/model/model/layers/18/post_attention_layernorm/kernel/.zarray b/model/model/layers/18/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/18/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/post_attention_layernorm/kernel/0 b/model/model/layers/18/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..a44ceef8426d4f16242de2f6e4746fe0b45a18e1 Binary files /dev/null and b/model/model/layers/18/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/18/self_attn/k_proj/bias/.zarray b/model/model/layers/18/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/18/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/self_attn/k_proj/bias/0 b/model/model/layers/18/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/18/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/18/self_attn/k_proj/kernel/.zarray b/model/model/layers/18/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/18/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/self_attn/k_proj/kernel/0.0 b/model/model/layers/18/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..d4db39b49ea4568e8d3a6116866826c8341dc67c --- /dev/null +++ b/model/model/layers/18/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1c17e630a95c1eab11d763d463991930116c4594d62738f9fcee9d9244e0eda +size 583088 diff --git a/model/model/layers/18/self_attn/k_proj/kernel/0.1 b/model/model/layers/18/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..f00bd1ef3e32be11744777780f702ee034ebad72 --- /dev/null +++ b/model/model/layers/18/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f89cb3df17507f30b54ca27d096d3176df92530ad039d4afaf4af63d4d684f07 +size 581571 diff --git a/model/model/layers/18/self_attn/k_proj/kernel/0.2 b/model/model/layers/18/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..be63236faa6fdcc89adf985082eebed0a40f1b54 --- /dev/null +++ b/model/model/layers/18/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f03399f355ea7cc1e245aece0575a5b01e0ccb8f266d964f5048230a6782f66 +size 581202 diff --git a/model/model/layers/18/self_attn/k_proj/kernel/0.3 b/model/model/layers/18/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..817445a4f90023f93345b9ad90e1f5c8bd808d6c --- /dev/null +++ b/model/model/layers/18/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c2e4eb4a2e95c94ec64428a41d3344534e0135d90e0f12be4b209b6fcc0f476 +size 585272 diff --git a/model/model/layers/18/self_attn/o_proj/bias/.zarray b/model/model/layers/18/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/18/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/self_attn/o_proj/bias/0 b/model/model/layers/18/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..3a9c1f15d682c6115a21e902ef31718f4453c886 Binary files /dev/null and b/model/model/layers/18/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/18/self_attn/o_proj/kernel/.zarray b/model/model/layers/18/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/18/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/self_attn/o_proj/kernel/0.0 b/model/model/layers/18/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..fe7617a1c89fbdcda6c67c2a34f3de9471476125 --- /dev/null +++ b/model/model/layers/18/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:460bed0a5b33d2a22c5568f403c5c53115be0f0399fc416cd4b56119923edd9e +size 4663610 diff --git a/model/model/layers/18/self_attn/o_proj/kernel/1.0 b/model/model/layers/18/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..fdb4c47a3978d6295e9a58bdeba1bcf5dd8e1489 --- /dev/null +++ b/model/model/layers/18/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0409e8130fd057f411d49b1c0e2f8e92c8da35eaf610d02e29ee72dda90bad3 +size 4660008 diff --git a/model/model/layers/18/self_attn/o_proj/kernel/2.0 b/model/model/layers/18/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..7f7be72d5df610b16a8c9bcc3613671bf7df3bbb --- /dev/null +++ b/model/model/layers/18/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7e1b27646a24738e649dde44176622ff1f38cc790d87a93c175e2872c798cc9 +size 4658659 diff --git a/model/model/layers/18/self_attn/o_proj/kernel/3.0 b/model/model/layers/18/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..c1b4a305bbca75c8ab5e7b917c9a0cacdb007744 --- /dev/null +++ b/model/model/layers/18/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cee979f0d36d877345fc80d039154f93c947c72246afa9d09f12ad554fa27ec0 +size 4656175 diff --git a/model/model/layers/18/self_attn/q_proj/bias/.zarray b/model/model/layers/18/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/18/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/self_attn/q_proj/bias/0 b/model/model/layers/18/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..59ff642d7fc27f8fba11947315e77dd42032002c Binary files /dev/null and b/model/model/layers/18/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/18/self_attn/q_proj/kernel/.zarray b/model/model/layers/18/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/18/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/self_attn/q_proj/kernel/0.0 b/model/model/layers/18/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..3d6feab44aa4ea0ea407d82d28c437f9b6551997 --- /dev/null +++ b/model/model/layers/18/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f37aa530577c4004b4a5276e63ec29407dd017c5fbd91df660288a0a7f3199f1 +size 4667435 diff --git a/model/model/layers/18/self_attn/q_proj/kernel/0.1 b/model/model/layers/18/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..349b17e29aaff41aa1caebb7bfef037fef3d26ca --- /dev/null +++ b/model/model/layers/18/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b5807ecd3c000b6e531beb8cb0ec25cbef185566189486459bd2e544f187981 +size 4656981 diff --git a/model/model/layers/18/self_attn/q_proj/kernel/0.2 b/model/model/layers/18/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..6501a67a5fc6e964df5da017df76858362bb7793 --- /dev/null +++ b/model/model/layers/18/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:620e227ade11cc40756ec30b3576f225b577edbf84e90d8e7d693ccec56435bc +size 4651460 diff --git a/model/model/layers/18/self_attn/q_proj/kernel/0.3 b/model/model/layers/18/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..5f485cd8e19c025ee7fc55525d28a0c390194aeb --- /dev/null +++ b/model/model/layers/18/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd26f0fa198d1772836cc5c6373ebf71e7f276121891dad2b47e59586676cd8c +size 4741506 diff --git a/model/model/layers/18/self_attn/sinks/.zarray b/model/model/layers/18/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/18/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/self_attn/sinks/0 b/model/model/layers/18/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..5588b7e033d970c3be2cb9d96e51a214006eebdc Binary files /dev/null and b/model/model/layers/18/self_attn/sinks/0 differ diff --git a/model/model/layers/18/self_attn/v_proj/bias/.zarray b/model/model/layers/18/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/18/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/self_attn/v_proj/bias/0 b/model/model/layers/18/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..70620eed20f1dd93ef5f51deba9efa530df11bd8 Binary files /dev/null and b/model/model/layers/18/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/18/self_attn/v_proj/kernel/.zarray b/model/model/layers/18/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/18/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/18/self_attn/v_proj/kernel/0.0 b/model/model/layers/18/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..3f1b5558d574121b28f63009bb1cf9e1fcd0b79e --- /dev/null +++ b/model/model/layers/18/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c28ee7d379fef7187bf14ec9abc515c1e8ed0d20eea4fcde7ce82e77247bd0f8 +size 576662 diff --git a/model/model/layers/18/self_attn/v_proj/kernel/0.1 b/model/model/layers/18/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..7a606f743a8fba525d78dffdda393d7b75c9319a --- /dev/null +++ b/model/model/layers/18/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fbbe0b85c23bb07f1fa95ad1af002066bc01742270b651aa118dd947ec2bdb4 +size 575034 diff --git a/model/model/layers/18/self_attn/v_proj/kernel/0.2 b/model/model/layers/18/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..8d555934307cdf44632228b1967b0f66d84e773f --- /dev/null +++ b/model/model/layers/18/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45055ae599f09355cfd55d4d907f9459088e8e0e8a9ec256b32ca9fb8d329f4b +size 576393 diff --git a/model/model/layers/18/self_attn/v_proj/kernel/0.3 b/model/model/layers/18/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..504171ad207583d1c6e142bf56520f5c90bf2c32 --- /dev/null +++ b/model/model/layers/18/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea813189d7c381314b30bbb521cb30ca7c7aefda75edf91b3a0b10dcfc489295 +size 577994 diff --git a/model/model/layers/19/input_layernorm/kernel/.zarray b/model/model/layers/19/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/19/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/input_layernorm/kernel/0 b/model/model/layers/19/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..a93ae1872dee533cd1356a67e28bfd63084cd1bb Binary files /dev/null and b/model/model/layers/19/input_layernorm/kernel/0 differ diff --git a/model/model/layers/19/mlp/experts/down_proj/bias/.zarray b/model/model/layers/19/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/19/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/mlp/experts/down_proj/bias/0.0 b/model/model/layers/19/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..072c7f9fb39f212cedad00c38e7073d38a28decf --- /dev/null +++ b/model/model/layers/19/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e164a8a103a581dbe1d8f8eefdcd5eb9b3aabe5c2d55ae32b492cefa1474fa88 +size 145904 diff --git a/model/model/layers/19/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/19/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/19/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/19/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..e0a8d0d7ba5db025a36c96b88075c16ccc923e20 --- /dev/null +++ b/model/model/layers/19/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f82f4b7e7eb33ff3006e9726c797923c8b98464a35b85234c59dacb8d4c0170 +size 187628522 diff --git a/model/model/layers/19/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/19/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/19/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/19/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..441c85e70ca99019ccbed0df5813bbc31d164bb4 --- /dev/null +++ b/model/model/layers/19/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e33a78520c9200e46c37c281ac7d3f4245d9d2f1472aa649a933827ccdffd1d +size 142602 diff --git a/model/model/layers/19/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/19/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/19/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/19/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..34670ac5e5f287822b1a023f35f84ede28ac62cf --- /dev/null +++ b/model/model/layers/19/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:915d7cbb82b8926401c34ddcc170dd027afa51a31c4941d5ef6fa5d1f23681c1 +size 191857307 diff --git a/model/model/layers/19/mlp/experts/up_proj/bias/.zarray b/model/model/layers/19/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/19/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/mlp/experts/up_proj/bias/0.0 b/model/model/layers/19/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..0f70c4a6ef01f7a6a81646935bcd98329ca681fd --- /dev/null +++ b/model/model/layers/19/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0355d6d762c0927b40b7f0f11a4114b107a2498df60ef1c084a6a62ec5e51480 +size 132320 diff --git a/model/model/layers/19/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/19/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/19/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/19/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..78e886a903aa5ec76000c000ec4a37fc4ecd1cc8 --- /dev/null +++ b/model/model/layers/19/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:533daeba2498fe7294dbfde4545606be6bee4ce6bd57497ac0416649159edfd0 +size 184777159 diff --git a/model/model/layers/19/mlp/router/bias/.zarray b/model/model/layers/19/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/19/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/mlp/router/bias/0 b/model/model/layers/19/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..bf33bbbb9ec134bbe93a294dfe1870bbbef40833 Binary files /dev/null and b/model/model/layers/19/mlp/router/bias/0 differ diff --git a/model/model/layers/19/mlp/router/kernel/.zarray b/model/model/layers/19/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/19/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/mlp/router/kernel/0.0 b/model/model/layers/19/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..9a6ec9ae362ba60a492c5c98887753af7ccc2bef --- /dev/null +++ b/model/model/layers/19/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dbafd0df9632deff8180ae7dd8804ae2a7610bcda60cfbd34ca7c7e01b4741a +size 144425 diff --git a/model/model/layers/19/post_attention_layernorm/kernel/.zarray b/model/model/layers/19/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/19/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/post_attention_layernorm/kernel/0 b/model/model/layers/19/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..fa5b4113eb7ce0a14773c09b7b3f64e68587b056 Binary files /dev/null and b/model/model/layers/19/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/19/self_attn/k_proj/bias/.zarray b/model/model/layers/19/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/19/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/self_attn/k_proj/bias/0 b/model/model/layers/19/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/19/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/19/self_attn/k_proj/kernel/.zarray b/model/model/layers/19/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/19/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/self_attn/k_proj/kernel/0.0 b/model/model/layers/19/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..d6989153539bd9612c4127bc28c01d8b771fff23 --- /dev/null +++ b/model/model/layers/19/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e1510d880ef528accc3d81d5801fe9e9b11328d62b60d81cf8ddc344c05787c +size 608984 diff --git a/model/model/layers/19/self_attn/k_proj/kernel/0.1 b/model/model/layers/19/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..891e47d981a6ec470b095d48e49e86308afe2c79 --- /dev/null +++ b/model/model/layers/19/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e798212eb5c45852885930e821b1ca97592d7dbfc7407f6bda15091432f171d3 +size 602039 diff --git a/model/model/layers/19/self_attn/k_proj/kernel/0.2 b/model/model/layers/19/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..cfaf002f233197fbcc4e9658ddfee376bff5e9b5 --- /dev/null +++ b/model/model/layers/19/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:804333b8bfeff0a6d3bf23debab521ac62e4548a11c1fdda63d27ce9a7e13a90 +size 604382 diff --git a/model/model/layers/19/self_attn/k_proj/kernel/0.3 b/model/model/layers/19/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..991eb4165f580d9002cab9065456e424202b39e4 --- /dev/null +++ b/model/model/layers/19/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70f6dfdcb2193d95751503f2a1aaa8b4cb0a758ef218bb5fd562f76811fca018 +size 601727 diff --git a/model/model/layers/19/self_attn/o_proj/bias/.zarray b/model/model/layers/19/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/19/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/self_attn/o_proj/bias/0 b/model/model/layers/19/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..7b29db9c3655b780d065274a57a70946dbef36dc Binary files /dev/null and b/model/model/layers/19/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/19/self_attn/o_proj/kernel/.zarray b/model/model/layers/19/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/19/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/self_attn/o_proj/kernel/0.0 b/model/model/layers/19/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..36b5e0e41d081d7f04894ca209b3175789504aac --- /dev/null +++ b/model/model/layers/19/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ace594c7c6370544e6ebe4a69baed6336be9acba82ecec888b10e2ada2b45a40 +size 4674629 diff --git a/model/model/layers/19/self_attn/o_proj/kernel/1.0 b/model/model/layers/19/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..25265cde956b78e88e930f33ecf67f3da6e32387 --- /dev/null +++ b/model/model/layers/19/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4869d11c936f0a77b17cecb325a07a7cb804fce68dd0850bfe75e90135d467ad +size 4662776 diff --git a/model/model/layers/19/self_attn/o_proj/kernel/2.0 b/model/model/layers/19/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..beda726633e7f1b2a1f60fb0fe8ee8054c7b2da5 --- /dev/null +++ b/model/model/layers/19/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5243fcec64d161debf6d1b00e78e5d4b1640c986b1e75ee1e850f41f2ff04166 +size 4672286 diff --git a/model/model/layers/19/self_attn/o_proj/kernel/3.0 b/model/model/layers/19/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..d44e62ee05f14bf1b177668198a551a1db5b627a --- /dev/null +++ b/model/model/layers/19/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc6d0f9774197d021b548ebd6261ad90860410fef9547e4fc1a3251d09b732df +size 4668456 diff --git a/model/model/layers/19/self_attn/q_proj/bias/.zarray b/model/model/layers/19/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/19/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/self_attn/q_proj/bias/0 b/model/model/layers/19/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..fce1b661f6c0d9365902337c439b65964b1643b5 Binary files /dev/null and b/model/model/layers/19/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/19/self_attn/q_proj/kernel/.zarray b/model/model/layers/19/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/19/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/self_attn/q_proj/kernel/0.0 b/model/model/layers/19/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..97e50011908bf0483b2f01b3d6e1cbcee9594457 --- /dev/null +++ b/model/model/layers/19/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b04b8a739e6e1b45b5c66f4388c2f2f816e61814dd30c0e64b89e2feb2a9a790 +size 4719939 diff --git a/model/model/layers/19/self_attn/q_proj/kernel/0.1 b/model/model/layers/19/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..7925daf02a3270c51c257bce7add3ee2a5a73bb5 --- /dev/null +++ b/model/model/layers/19/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67179af33546fd5905f6aec93dbc920d52d3e02d574f1350ef23fdb38c8993c8 +size 4712153 diff --git a/model/model/layers/19/self_attn/q_proj/kernel/0.2 b/model/model/layers/19/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..46b350aef060c1c57c6de7de82ef33da7d0ca3f1 --- /dev/null +++ b/model/model/layers/19/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49bd375be5331f294410d8b454ac2df0dfff2ff9ef37ea33ab8deeb366bae3a5 +size 4721489 diff --git a/model/model/layers/19/self_attn/q_proj/kernel/0.3 b/model/model/layers/19/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..3cde0789018d6933c3536d8e910d9e977f035801 --- /dev/null +++ b/model/model/layers/19/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fff7cb8e00cc42a14c3fb3e0dc48dd8f03601655b70c4b6e8ae63dcce21a913 +size 4749214 diff --git a/model/model/layers/19/self_attn/sinks/.zarray b/model/model/layers/19/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/19/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/self_attn/sinks/0 b/model/model/layers/19/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..3b10d707fed07e17322d54ee5b8120a90cc7b77a Binary files /dev/null and b/model/model/layers/19/self_attn/sinks/0 differ diff --git a/model/model/layers/19/self_attn/v_proj/bias/.zarray b/model/model/layers/19/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/19/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/self_attn/v_proj/bias/0 b/model/model/layers/19/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..379d1a0fb0430bf129f43bce83ae6298f57ac49c Binary files /dev/null and b/model/model/layers/19/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/19/self_attn/v_proj/kernel/.zarray b/model/model/layers/19/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/19/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/19/self_attn/v_proj/kernel/0.0 b/model/model/layers/19/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..ed1e8e41e2611cbb08f1dbd3b55796641ce4a437 --- /dev/null +++ b/model/model/layers/19/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1beae4e95df49ae2128b9b5de03463f45f315ec3c23e57f116c4ca5e8cadde86 +size 579222 diff --git a/model/model/layers/19/self_attn/v_proj/kernel/0.1 b/model/model/layers/19/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..467dd55e5161ac950fdb4697c1e5c850cab207d3 --- /dev/null +++ b/model/model/layers/19/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb09da7042a1f57623f4da20f2730964970ab8c0da5b483b78a1cf9d3d380c37 +size 580075 diff --git a/model/model/layers/19/self_attn/v_proj/kernel/0.2 b/model/model/layers/19/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..f3af1d2a4bb7d163f28366eb59a27e9fdc92a872 --- /dev/null +++ b/model/model/layers/19/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b70ff10fe5472bd3eaab15b04c4fcc9635567b8ff78c0fe6890082b5821519 +size 580257 diff --git a/model/model/layers/19/self_attn/v_proj/kernel/0.3 b/model/model/layers/19/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..ad48a2e7443b403e9fb5af1753c3677dd3cc0fdc --- /dev/null +++ b/model/model/layers/19/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a82509f5e697e1814b220562de074e4a1d11083ededfb8734bb4df6c9e74614 +size 577279 diff --git a/model/model/layers/2/input_layernorm/kernel/.zarray b/model/model/layers/2/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/2/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/input_layernorm/kernel/0 b/model/model/layers/2/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..87e36db147980d9fbf60dfb59875b603b6f8631f Binary files /dev/null and b/model/model/layers/2/input_layernorm/kernel/0 differ diff --git a/model/model/layers/2/mlp/experts/down_proj/bias/.zarray b/model/model/layers/2/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/2/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/mlp/experts/down_proj/bias/0.0 b/model/model/layers/2/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..4593b7627bac1fddf90bc77cdc9f626a1782a061 --- /dev/null +++ b/model/model/layers/2/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a25550d6b14cd92d2172a95b7b0adf624c0aec5c96ee265cdf19fdd69faa258 +size 146376 diff --git a/model/model/layers/2/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/2/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/2/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/2/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..a72a82966d5a31255888f3e8c35c94f3b5c223f0 --- /dev/null +++ b/model/model/layers/2/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8440feb21ecb379da2e5aac02fb26e6c4b7e1f11051a55469141593fd06468b6 +size 196952279 diff --git a/model/model/layers/2/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/2/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/2/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/2/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..9ff403c8bfd5a402e375a3f7da78f0e8b5d4b30f --- /dev/null +++ b/model/model/layers/2/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a27c70454a7dc6ac1e27a215b0df08c1b3b6c6743289c91cf12483d5e1e6b01c +size 130012 diff --git a/model/model/layers/2/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/2/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/2/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/2/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..0f926d4e4c51d6865d4b3368fa0dcd644660c99c --- /dev/null +++ b/model/model/layers/2/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bd900d4ba483de3f358f82024af704dd8f7c9bdc24df05a6b64a97c35649653 +size 184292341 diff --git a/model/model/layers/2/mlp/experts/up_proj/bias/.zarray b/model/model/layers/2/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/2/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/mlp/experts/up_proj/bias/0.0 b/model/model/layers/2/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..4a249cb60bc118a7b8dc7b193db1e6ae5a9a9bec --- /dev/null +++ b/model/model/layers/2/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b436a6c71a120d0cc6c21579260a97261df8036aebe8247d1def25475a048f2 +size 114503 diff --git a/model/model/layers/2/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/2/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/2/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/2/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..26ad9e8bbc0de53f165798cb0c13b1b4b58673a7 --- /dev/null +++ b/model/model/layers/2/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f2ead1f5693d8d49a7eb2c31568b3288e01e5745cf13bf41a60cd3df8e0d3a6 +size 178833950 diff --git a/model/model/layers/2/mlp/router/bias/.zarray b/model/model/layers/2/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/2/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/mlp/router/bias/0 b/model/model/layers/2/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..112d4883c6041f44997fb22c0d78eeeed6065e36 Binary files /dev/null and b/model/model/layers/2/mlp/router/bias/0 differ diff --git a/model/model/layers/2/mlp/router/kernel/.zarray b/model/model/layers/2/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/2/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/mlp/router/kernel/0.0 b/model/model/layers/2/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..6f9c1be28c09a2aac13176691e27b11d9e097132 --- /dev/null +++ b/model/model/layers/2/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66bcf0bc130485efa416c3e68662d681a7e11fcaa392ff28e4d280698e641e79 +size 145715 diff --git a/model/model/layers/2/post_attention_layernorm/kernel/.zarray b/model/model/layers/2/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/2/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/post_attention_layernorm/kernel/0 b/model/model/layers/2/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..3c055fac46453d59dc5bf2ad00cc060191381651 Binary files /dev/null and b/model/model/layers/2/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/2/self_attn/k_proj/bias/.zarray b/model/model/layers/2/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/2/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/self_attn/k_proj/bias/0 b/model/model/layers/2/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/2/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/2/self_attn/k_proj/kernel/.zarray b/model/model/layers/2/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/2/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/self_attn/k_proj/kernel/0.0 b/model/model/layers/2/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..7b8a28f0da84f6c1188e7437bc57851938d3a8a0 --- /dev/null +++ b/model/model/layers/2/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af43b30121d55d070496b7a56001a380240e04515b055b21e1f26b39ab166d64 +size 581918 diff --git a/model/model/layers/2/self_attn/k_proj/kernel/0.1 b/model/model/layers/2/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..d744ea78f9af75abb0e0c237246f51740e77f17d --- /dev/null +++ b/model/model/layers/2/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63674f82d4afdf5fe950bbd320a21ff2560053372fb10ee8cc1a15c40bfacc3b +size 582290 diff --git a/model/model/layers/2/self_attn/k_proj/kernel/0.2 b/model/model/layers/2/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..a3247fa82364b53b9ed8ca0ed3b95ac07ae25f1d --- /dev/null +++ b/model/model/layers/2/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5214f473c275bf639b90eca3e9dc0fa6186a063782b14c2b1f3bdf835bbc13ca +size 583456 diff --git a/model/model/layers/2/self_attn/k_proj/kernel/0.3 b/model/model/layers/2/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..860272e545de2d6d69dc68abe1fb4e07fc68ae3f --- /dev/null +++ b/model/model/layers/2/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a248328ff27d32444ae588a2f8894c841899008f97f7e8a4ebc88013b6833141 +size 581498 diff --git a/model/model/layers/2/self_attn/o_proj/bias/.zarray b/model/model/layers/2/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/2/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/self_attn/o_proj/bias/0 b/model/model/layers/2/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..5eb7298582bb7363ca8fb036f9bd22326cf57922 Binary files /dev/null and b/model/model/layers/2/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/2/self_attn/o_proj/kernel/.zarray b/model/model/layers/2/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/2/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/self_attn/o_proj/kernel/0.0 b/model/model/layers/2/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..a724f0df60fe38c7b154b0489297ddeb4bf61a06 --- /dev/null +++ b/model/model/layers/2/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:698084eb90b0c69b34dffe5ba8f00bf9ade752349d3c55962515bd6f4909b55f +size 4694354 diff --git a/model/model/layers/2/self_attn/o_proj/kernel/1.0 b/model/model/layers/2/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..bc6f0446649c04f12014310e3bcc7890d281ce94 --- /dev/null +++ b/model/model/layers/2/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d15dacbb3b465932af44a7dca30b0bf46930305c1df5f91d19e04b9ca2c706d1 +size 4682100 diff --git a/model/model/layers/2/self_attn/o_proj/kernel/2.0 b/model/model/layers/2/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..178e10abdc2f7203fa002930a9b86b53fdf3a487 --- /dev/null +++ b/model/model/layers/2/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d76e107812f340d504d866c2a5b838728fbec3d4b90ad02c8929d9a4eec5ca04 +size 4686815 diff --git a/model/model/layers/2/self_attn/o_proj/kernel/3.0 b/model/model/layers/2/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..3ac9492df4cf69940bbe922ac8002ad7dc83aafc --- /dev/null +++ b/model/model/layers/2/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2931a12d095d4117f727f1b70638d6ca472ce50a464517029c699c89c7b605a5 +size 4687135 diff --git a/model/model/layers/2/self_attn/q_proj/bias/.zarray b/model/model/layers/2/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/2/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/self_attn/q_proj/bias/0 b/model/model/layers/2/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..da631646d3ce22d380592fbc008d069cddf90440 Binary files /dev/null and b/model/model/layers/2/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/2/self_attn/q_proj/kernel/.zarray b/model/model/layers/2/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/2/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/self_attn/q_proj/kernel/0.0 b/model/model/layers/2/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..37305c790ba225e9a4efdf741f7d6bda5cfcfa89 --- /dev/null +++ b/model/model/layers/2/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a1d65878209dfb966bfef936a15798fc5a42583273f4bf6dae2ef83bf84b96 +size 4709478 diff --git a/model/model/layers/2/self_attn/q_proj/kernel/0.1 b/model/model/layers/2/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..afd04e9f0093511065002860f430b732666ac294 --- /dev/null +++ b/model/model/layers/2/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82c3b6ea2e9933404792c4230036906920e52315cb7639ca89ee99119197059f +size 4684562 diff --git a/model/model/layers/2/self_attn/q_proj/kernel/0.2 b/model/model/layers/2/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..0df906ab52690fb21b837137720f7f1de6a9c978 --- /dev/null +++ b/model/model/layers/2/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5538eab787c754cbe9d2fb4c3aa6c28fa8a3c7e5151cc9a5e7456e6e89f6032 +size 4688284 diff --git a/model/model/layers/2/self_attn/q_proj/kernel/0.3 b/model/model/layers/2/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..f1ed76b246d1520823441ef052e24f37d1822e50 --- /dev/null +++ b/model/model/layers/2/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf7f12d1263f2ce2c7446880a93c1501123736d90386a643ee6d1bde191b15d5 +size 4683978 diff --git a/model/model/layers/2/self_attn/sinks/.zarray b/model/model/layers/2/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/2/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/self_attn/sinks/0 b/model/model/layers/2/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..b587ba1138422d7f94689ac9aad25613617e24b8 Binary files /dev/null and b/model/model/layers/2/self_attn/sinks/0 differ diff --git a/model/model/layers/2/self_attn/v_proj/bias/.zarray b/model/model/layers/2/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/2/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/self_attn/v_proj/bias/0 b/model/model/layers/2/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..05515af8641a85b2463316dd703178a9b76cca6f Binary files /dev/null and b/model/model/layers/2/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/2/self_attn/v_proj/kernel/.zarray b/model/model/layers/2/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/2/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/2/self_attn/v_proj/kernel/0.0 b/model/model/layers/2/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..5a4d2516ee0fdcf1fca4a182fd589180bb4712a0 --- /dev/null +++ b/model/model/layers/2/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3410663f8fa234181fcf676f4eb4877c8873a03a07e994ebe87013c6405cc8c +size 581396 diff --git a/model/model/layers/2/self_attn/v_proj/kernel/0.1 b/model/model/layers/2/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..e107fd33abac22cad557546c32bde9ac4df1a4ca --- /dev/null +++ b/model/model/layers/2/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a11e1f878797fa159775ffb68136fd4fdbaa6130a816abb4d7a8de50cd7ec03 +size 581252 diff --git a/model/model/layers/2/self_attn/v_proj/kernel/0.2 b/model/model/layers/2/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..05394b8d570fa90ef7197696e7a0907c16fdfe31 --- /dev/null +++ b/model/model/layers/2/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7332be518dca1b9a9bf11557c5f4573963b7f82e0a2bf84c95dbb375999e065f +size 580609 diff --git a/model/model/layers/2/self_attn/v_proj/kernel/0.3 b/model/model/layers/2/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..e2d4d0f82f2d7fff103cc5d35743e7bd00892c4d --- /dev/null +++ b/model/model/layers/2/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:281b96537fdc6cd9394c6bf7864c2fc7c8c3f6c68f9ce1bfa39343d6ac2c93e8 +size 578320 diff --git a/model/model/layers/20/input_layernorm/kernel/.zarray b/model/model/layers/20/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/20/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/input_layernorm/kernel/0 b/model/model/layers/20/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..7b9383790524c847cc2925334acdcfc2b5b4150c Binary files /dev/null and b/model/model/layers/20/input_layernorm/kernel/0 differ diff --git a/model/model/layers/20/mlp/experts/down_proj/bias/.zarray b/model/model/layers/20/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/20/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/mlp/experts/down_proj/bias/0.0 b/model/model/layers/20/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..47964ad160212f60380ef9665b13e07986198321 --- /dev/null +++ b/model/model/layers/20/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d969fc8f64ffb4a96572e3f9e13253683766efdad01edd4917a486d4d822658 +size 145346 diff --git a/model/model/layers/20/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/20/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/20/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/20/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..a90d6ac675cf2d69c4500c099f41ffca6df17c73 --- /dev/null +++ b/model/model/layers/20/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e074d5e3175cd3fc8d5f4062332a5f50057f61cf0fc853946447ee6af0002b42 +size 186924596 diff --git a/model/model/layers/20/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/20/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/20/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/20/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..b94c21026079ac5473f1520a5bd552fe387f6a92 --- /dev/null +++ b/model/model/layers/20/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fecea610c089b0d005cfaf0eac576b71dc7070ff5585648c96acb5c060aed463 +size 141582 diff --git a/model/model/layers/20/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/20/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/20/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/20/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..5fd06fb8a9a6d8a0df4e8c423813b6d5e6c46a1b --- /dev/null +++ b/model/model/layers/20/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0213d0dab893516a3b6b40017f287d1a437a5b71e3f9d4abe5223ad964e40d09 +size 190979242 diff --git a/model/model/layers/20/mlp/experts/up_proj/bias/.zarray b/model/model/layers/20/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/20/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/mlp/experts/up_proj/bias/0.0 b/model/model/layers/20/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..059d090f28d76451947ec0bbab8c88e338bdd3d5 --- /dev/null +++ b/model/model/layers/20/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7af57529cff78e68b16897a279ed2071ad5bbc92acc935bf1c7ffa54a3abb761 +size 132573 diff --git a/model/model/layers/20/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/20/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/20/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/20/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..1a411cdd69a16ab088c353deac62a07549815891 --- /dev/null +++ b/model/model/layers/20/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba712f650735e1c7819c30a3d23c50e0981410882ec51dbc9f33376d40e3aa15 +size 184013457 diff --git a/model/model/layers/20/mlp/router/bias/.zarray b/model/model/layers/20/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/20/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/mlp/router/bias/0 b/model/model/layers/20/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a2ac5c7513d444a6b35d42c32930d5a855e2944d Binary files /dev/null and b/model/model/layers/20/mlp/router/bias/0 differ diff --git a/model/model/layers/20/mlp/router/kernel/.zarray b/model/model/layers/20/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/20/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/mlp/router/kernel/0.0 b/model/model/layers/20/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..ee245fa39bcdc9067abb4545af0fbd14cc11cf78 --- /dev/null +++ b/model/model/layers/20/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb84aee90ea3f27d15e73230c629e7325bace0d326586d8ea8f4ab0281c2042e +size 144642 diff --git a/model/model/layers/20/post_attention_layernorm/kernel/.zarray b/model/model/layers/20/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/20/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/post_attention_layernorm/kernel/0 b/model/model/layers/20/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..6a3a7b2f015e5e2e703b36ab6c5c98023ca5967d Binary files /dev/null and b/model/model/layers/20/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/20/self_attn/k_proj/bias/.zarray b/model/model/layers/20/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/20/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/self_attn/k_proj/bias/0 b/model/model/layers/20/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/20/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/20/self_attn/k_proj/kernel/.zarray b/model/model/layers/20/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/20/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/self_attn/k_proj/kernel/0.0 b/model/model/layers/20/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..47142ca81b42d95f446ed0a10fc841e0e77ee533 --- /dev/null +++ b/model/model/layers/20/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:614251f112c6265e0cf8ebfa96f7f443356c10efa68855ce3e96990807cda692 +size 583438 diff --git a/model/model/layers/20/self_attn/k_proj/kernel/0.1 b/model/model/layers/20/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..4db376b4c1e252c61368cc7daa2a5727aff89d31 --- /dev/null +++ b/model/model/layers/20/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00f1aea33944098e4f9ffa4a75c71e583d9d909e29b9cd0ded2e457f7bbd6b6a +size 585354 diff --git a/model/model/layers/20/self_attn/k_proj/kernel/0.2 b/model/model/layers/20/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..ec174fe11a61f92f49e428d4e62e6c0a1e3a075e --- /dev/null +++ b/model/model/layers/20/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3a073a22677f14b16fbc77bd72f0577ac52342a294e2e4ebce5cee3628825e6 +size 587888 diff --git a/model/model/layers/20/self_attn/k_proj/kernel/0.3 b/model/model/layers/20/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..b1e6bcb2d5801a3c9644a571f292c62bd4dff0bf --- /dev/null +++ b/model/model/layers/20/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eb31972552ad349885885f68ad0f19c988a7151a99c1d3c4e36f6e92db9f707 +size 585616 diff --git a/model/model/layers/20/self_attn/o_proj/bias/.zarray b/model/model/layers/20/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/20/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/self_attn/o_proj/bias/0 b/model/model/layers/20/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..7c7663929f05e9c7779eb8fc84dddfd789235101 Binary files /dev/null and b/model/model/layers/20/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/20/self_attn/o_proj/kernel/.zarray b/model/model/layers/20/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/20/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/self_attn/o_proj/kernel/0.0 b/model/model/layers/20/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..9f6a07a519899ab2ad8131f1348b786f1ff87223 --- /dev/null +++ b/model/model/layers/20/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bb9001a62d9227b144baa2400d4e891efabf513a43d3da916026366c4bfd948 +size 4657637 diff --git a/model/model/layers/20/self_attn/o_proj/kernel/1.0 b/model/model/layers/20/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..6271cdea59ceb0819669e44956417c327315fb79 --- /dev/null +++ b/model/model/layers/20/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dc5416e970c85e84e951546c15cb79078a29abe34fcacea56e9fdedc32929f2 +size 4669311 diff --git a/model/model/layers/20/self_attn/o_proj/kernel/2.0 b/model/model/layers/20/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..32bf895a611907fb888428f097613de19b5e52c6 --- /dev/null +++ b/model/model/layers/20/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c0112814cbcd074b287a25f5612e8b7bb4de86be41f6447ea62c27fb02da40d +size 4660986 diff --git a/model/model/layers/20/self_attn/o_proj/kernel/3.0 b/model/model/layers/20/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..164e816cabff9bf6915a9e0c984ee4c8125623e7 --- /dev/null +++ b/model/model/layers/20/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60e2b2d9ebfe400ed53b610e9c65ba567406229c01498fb22a2a9f5ffc507ff +size 4660243 diff --git a/model/model/layers/20/self_attn/q_proj/bias/.zarray b/model/model/layers/20/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/20/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/self_attn/q_proj/bias/0 b/model/model/layers/20/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..1fe9d27b0079cd0d339433f1ee50a25dace91d7c Binary files /dev/null and b/model/model/layers/20/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/20/self_attn/q_proj/kernel/.zarray b/model/model/layers/20/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/20/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/self_attn/q_proj/kernel/0.0 b/model/model/layers/20/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..7c202b238a71940fbb69b229407a067f73bc72df --- /dev/null +++ b/model/model/layers/20/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:985ccb8594530849bd6c7d1f8211bab2271b8d936603d1f7ad69ba2e597e3e04 +size 4692449 diff --git a/model/model/layers/20/self_attn/q_proj/kernel/0.1 b/model/model/layers/20/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..434388815dc02fa930a932347fad0c04fac357ef --- /dev/null +++ b/model/model/layers/20/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a566882baa19752035f86ccf2b8089a3b530a37713dc53145c297fecf9176f41 +size 4679693 diff --git a/model/model/layers/20/self_attn/q_proj/kernel/0.2 b/model/model/layers/20/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..c8cfc7312193fc155c01cb0314a57486b1994d2a --- /dev/null +++ b/model/model/layers/20/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a53c4377e355f83bf5df7487d0f2fadeb5628bdff18a82195335b9fe169ec5a +size 4693327 diff --git a/model/model/layers/20/self_attn/q_proj/kernel/0.3 b/model/model/layers/20/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..f5c95b3811dfd77d8d3daceef6a98ba01c76619e --- /dev/null +++ b/model/model/layers/20/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9cac819d9bb0c993128a3490c5f3bb9bd13ff5560b6f7ac81f25bbe9c8a869e +size 4667019 diff --git a/model/model/layers/20/self_attn/sinks/.zarray b/model/model/layers/20/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/20/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/self_attn/sinks/0 b/model/model/layers/20/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..390057a3eec61671ddbd450b5c748201a13ad1a9 Binary files /dev/null and b/model/model/layers/20/self_attn/sinks/0 differ diff --git a/model/model/layers/20/self_attn/v_proj/bias/.zarray b/model/model/layers/20/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/20/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/self_attn/v_proj/bias/0 b/model/model/layers/20/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..2869544837aac8961a773c26e4666249ddd4e1c1 Binary files /dev/null and b/model/model/layers/20/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/20/self_attn/v_proj/kernel/.zarray b/model/model/layers/20/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/20/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/20/self_attn/v_proj/kernel/0.0 b/model/model/layers/20/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..b4f51ebd87e16553e18c5509ad26d4cff04057e9 --- /dev/null +++ b/model/model/layers/20/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e816840135ddd91207a3445acbcf328fc4870fef991012c524b4a1bcda7a5e2 +size 577745 diff --git a/model/model/layers/20/self_attn/v_proj/kernel/0.1 b/model/model/layers/20/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..ef3d6f5c83c3543bcf4cee9da982944d90f81ebd --- /dev/null +++ b/model/model/layers/20/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95ac61cab2aac4151ce2a32bd09e8420780a615ff4fbd5232c98d5d18be97fda +size 576811 diff --git a/model/model/layers/20/self_attn/v_proj/kernel/0.2 b/model/model/layers/20/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..c8967d648ce05e797ed993eb537214a1f535b46a --- /dev/null +++ b/model/model/layers/20/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caab83994984fb861fca5982c91ed8885e8b429ae1c90bfa39cc9161abd981cc +size 580628 diff --git a/model/model/layers/20/self_attn/v_proj/kernel/0.3 b/model/model/layers/20/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..f9a6b51ea35dd5d83496ff683406684bbd64324b --- /dev/null +++ b/model/model/layers/20/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d128c8d62b76f1f85a13f0d239b8a5f8417614da7163d6ce05f5c6a1ee5ae310 +size 580194 diff --git a/model/model/layers/21/input_layernorm/kernel/.zarray b/model/model/layers/21/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/21/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/input_layernorm/kernel/0 b/model/model/layers/21/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..f6651135ed18dfc6ad41cb20a882310006d55b0b Binary files /dev/null and b/model/model/layers/21/input_layernorm/kernel/0 differ diff --git a/model/model/layers/21/mlp/experts/down_proj/bias/.zarray b/model/model/layers/21/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/21/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/mlp/experts/down_proj/bias/0.0 b/model/model/layers/21/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..a18778e38acdcab2e89f97d8cd2432a65043f5b1 --- /dev/null +++ b/model/model/layers/21/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfe880e08a877098f87fb4c6d073b2b8a55b596d3665342a9c6ecf1d7550379c +size 145125 diff --git a/model/model/layers/21/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/21/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/21/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/21/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..e3e346d49e1a368a0f8d982ff0aa2259aa2be78a --- /dev/null +++ b/model/model/layers/21/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56fb1afe5a8ae69b1c6a0f3cbbb312adf041d4dd78a256c071aa0139cfe27565 +size 185243131 diff --git a/model/model/layers/21/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/21/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/21/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/21/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..9fa6e2ddabadfe99858465ba80ac5bd01391419c --- /dev/null +++ b/model/model/layers/21/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8ff34784e33ca211130c6f2ae8e0f7ad632ab52a793d0912043861bed0140a3 +size 139524 diff --git a/model/model/layers/21/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/21/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/21/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/21/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..dc0007575af43f8e1a7afb769d5da5cbfa627a0c --- /dev/null +++ b/model/model/layers/21/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93c4d8ba59ec630bf915f9d7cfa7ba1b563ac77ea19ed59f5c66648a293290bb +size 188846231 diff --git a/model/model/layers/21/mlp/experts/up_proj/bias/.zarray b/model/model/layers/21/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/21/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/mlp/experts/up_proj/bias/0.0 b/model/model/layers/21/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..efd3fb98416569c4892552562ae4c853032b46e7 --- /dev/null +++ b/model/model/layers/21/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:364576b2c889a64d3e5963de9bfc8efdfb6959d2e9ae92c4cbb9de5f7a6bc6fc +size 130274 diff --git a/model/model/layers/21/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/21/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/21/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/21/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..a3471df7c10c1ad3ad6210cf97fca4d9c9ccb429 --- /dev/null +++ b/model/model/layers/21/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d43a1821ec974b6c0b19b2f547bdf3fdcf53676174d81274900bc8851af23bb +size 183436569 diff --git a/model/model/layers/21/mlp/router/bias/.zarray b/model/model/layers/21/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/21/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/mlp/router/bias/0 b/model/model/layers/21/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..3a27bdc28b7592320b76515073d1c23a329721da Binary files /dev/null and b/model/model/layers/21/mlp/router/bias/0 differ diff --git a/model/model/layers/21/mlp/router/kernel/.zarray b/model/model/layers/21/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/21/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/mlp/router/kernel/0.0 b/model/model/layers/21/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..7462f8d8f34276ef61cc3f69935b064d2fd521c3 --- /dev/null +++ b/model/model/layers/21/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:016cf9e9d45fbdd53f94a9a7132432e897ed3a0b388130664280bb30fc0e9d0f +size 144549 diff --git a/model/model/layers/21/post_attention_layernorm/kernel/.zarray b/model/model/layers/21/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/21/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/post_attention_layernorm/kernel/0 b/model/model/layers/21/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..a3d30fb7738d4101d852f980fc57b1c0b0086057 Binary files /dev/null and b/model/model/layers/21/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/21/self_attn/k_proj/bias/.zarray b/model/model/layers/21/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/21/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/self_attn/k_proj/bias/0 b/model/model/layers/21/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/21/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/21/self_attn/k_proj/kernel/.zarray b/model/model/layers/21/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/21/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/self_attn/k_proj/kernel/0.0 b/model/model/layers/21/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..2973f0ae013e2f8787ae8f027c8026ff5e337792 --- /dev/null +++ b/model/model/layers/21/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ccbb605a6a36446bf80d0ad1126718a6c037c5b8b612b64b1c4e340bc4d16c3 +size 603333 diff --git a/model/model/layers/21/self_attn/k_proj/kernel/0.1 b/model/model/layers/21/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..dd17f3869fc3dde6de56183a173ae639d2a24dd3 --- /dev/null +++ b/model/model/layers/21/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f02020c93dd2f856c7941bfa0a914b6898601c4a6b67b75b029bf58f3d2fd0b8 +size 609771 diff --git a/model/model/layers/21/self_attn/k_proj/kernel/0.2 b/model/model/layers/21/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..21b79b93251ff7f2337c9d5b9f2cf461d09bbf14 --- /dev/null +++ b/model/model/layers/21/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45ed11545eb93612cd537a93f9ca113ac89a00d828874c9da3bde2531ed606fc +size 610385 diff --git a/model/model/layers/21/self_attn/k_proj/kernel/0.3 b/model/model/layers/21/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..7ef1d16b7089eb97e1e74385b6bf166a2d461dca --- /dev/null +++ b/model/model/layers/21/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b1b742f33be30ce9616b4c5cb6490e48ccdde07b2ac8b1d7016e8666cc251f9 +size 594405 diff --git a/model/model/layers/21/self_attn/o_proj/bias/.zarray b/model/model/layers/21/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/21/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/self_attn/o_proj/bias/0 b/model/model/layers/21/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..2ef13c8a59f31c531d9d44bc843aba1c1df843fc Binary files /dev/null and b/model/model/layers/21/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/21/self_attn/o_proj/kernel/.zarray b/model/model/layers/21/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/21/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/self_attn/o_proj/kernel/0.0 b/model/model/layers/21/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..c0f6efc4cf4925deb2ea96234c84f31a4e0d0187 --- /dev/null +++ b/model/model/layers/21/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e310553e823408d8696b5312df073f57262ae082de9d003f76fba53d16352805 +size 4656438 diff --git a/model/model/layers/21/self_attn/o_proj/kernel/1.0 b/model/model/layers/21/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..98d2ca63e6d3ec64101213d5cfca49da17d15a63 --- /dev/null +++ b/model/model/layers/21/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df432a0ae8b5000d27230d9b9b33ca5a0b8dec6bca6f1f152890b7d16f9c0c4c +size 4659035 diff --git a/model/model/layers/21/self_attn/o_proj/kernel/2.0 b/model/model/layers/21/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..b58730669414b62097e38abb307d611edaf12464 --- /dev/null +++ b/model/model/layers/21/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bce7e8a9f189c9c003350162d00e29418f8280af6e6663ed04dfa382b50681d1 +size 4652838 diff --git a/model/model/layers/21/self_attn/o_proj/kernel/3.0 b/model/model/layers/21/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..f0f75001e0863b70d95100a81e60d36075e87764 --- /dev/null +++ b/model/model/layers/21/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55a2c642ad547b061dc78907229d341b787b0b5e2ffebba8819d5f29792fe916 +size 4647277 diff --git a/model/model/layers/21/self_attn/q_proj/bias/.zarray b/model/model/layers/21/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/21/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/self_attn/q_proj/bias/0 b/model/model/layers/21/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a34bea02f42f817ef4a46552a20662dc074f5996 Binary files /dev/null and b/model/model/layers/21/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/21/self_attn/q_proj/kernel/.zarray b/model/model/layers/21/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/21/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/self_attn/q_proj/kernel/0.0 b/model/model/layers/21/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..9c581da24a1d5b3e45d50e8a2ce60600d1770605 --- /dev/null +++ b/model/model/layers/21/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2541f8c07c34ca19a9ba62ee66c07672f6c89fd5bf49019cbac148af77c2583 +size 4727470 diff --git a/model/model/layers/21/self_attn/q_proj/kernel/0.1 b/model/model/layers/21/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..344cff5d4c1c240f50194319f619a9e086cd0152 --- /dev/null +++ b/model/model/layers/21/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:593a9903b27f40b9ec4730b564c0dc64c5d93badd5ccdad615f305e9b3b20376 +size 4701866 diff --git a/model/model/layers/21/self_attn/q_proj/kernel/0.2 b/model/model/layers/21/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..48f1f429343ea575e97c35fca24dc722c1a756e5 --- /dev/null +++ b/model/model/layers/21/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f323e7247e63c85d4824f479ba0a71775a6fcc7ce02c2b2c34aec599f7b1de2d +size 4742848 diff --git a/model/model/layers/21/self_attn/q_proj/kernel/0.3 b/model/model/layers/21/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..d35f0992fc5eb4fa223d97b9cb1ea4563764ce25 --- /dev/null +++ b/model/model/layers/21/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14db25dc9593bc04b5c0695f054c9a1d1b8e89fa9235cb5bbfb7b5af442ef9c3 +size 4724218 diff --git a/model/model/layers/21/self_attn/sinks/.zarray b/model/model/layers/21/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/21/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/self_attn/sinks/0 b/model/model/layers/21/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..c8c8a28febef6bcff85ca07d40aab0d958f5b830 Binary files /dev/null and b/model/model/layers/21/self_attn/sinks/0 differ diff --git a/model/model/layers/21/self_attn/v_proj/bias/.zarray b/model/model/layers/21/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/21/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/self_attn/v_proj/bias/0 b/model/model/layers/21/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..d984aa2273660850821e863c2ef822bf2f450100 Binary files /dev/null and b/model/model/layers/21/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/21/self_attn/v_proj/kernel/.zarray b/model/model/layers/21/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/21/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/21/self_attn/v_proj/kernel/0.0 b/model/model/layers/21/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..76a51a2d51392091dbd76c4033a5becdf8812473 --- /dev/null +++ b/model/model/layers/21/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0d153d9e6713f6a69c85663430a615f8ffeaa01492e645d91e9068171cc9989 +size 579069 diff --git a/model/model/layers/21/self_attn/v_proj/kernel/0.1 b/model/model/layers/21/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..4ee13d030944c8bc2be7a1b3652d879f72f8ef8f --- /dev/null +++ b/model/model/layers/21/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd25db4e160aa5f80e09804a7ef8285d49d2ac9f1b6afd7d9a8e52e9bd74dcf7 +size 579692 diff --git a/model/model/layers/21/self_attn/v_proj/kernel/0.2 b/model/model/layers/21/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..f4eb28aac281620258230b406ababb52e80d01d8 --- /dev/null +++ b/model/model/layers/21/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a42e0f648ff2b27a15cebe6b3b3424a2828562067c2fa914083d8c83d146c2fa +size 579961 diff --git a/model/model/layers/21/self_attn/v_proj/kernel/0.3 b/model/model/layers/21/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..280d05490aaa7806af4aedfb9d4f456149e800cb --- /dev/null +++ b/model/model/layers/21/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:228785ad06a241316fd3d6ddc7b77f4e745a3a4dfb2682be121f70f7f98df155 +size 578320 diff --git a/model/model/layers/22/input_layernorm/kernel/.zarray b/model/model/layers/22/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/22/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/input_layernorm/kernel/0 b/model/model/layers/22/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..84dcc3c6802cd8b0380e7c66729068c54ed1ee01 Binary files /dev/null and b/model/model/layers/22/input_layernorm/kernel/0 differ diff --git a/model/model/layers/22/mlp/experts/down_proj/bias/.zarray b/model/model/layers/22/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/22/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/mlp/experts/down_proj/bias/0.0 b/model/model/layers/22/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..c01e7e497f483d4a46193173ece6322735e258ce --- /dev/null +++ b/model/model/layers/22/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6f90c6ae16962ec71852e82bfa348d364036e7f7a6c25cb8e0eb15b1e74dc14 +size 144752 diff --git a/model/model/layers/22/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/22/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/22/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/22/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..9bbe28c727b47bcd37b63383690baa3fe860533f --- /dev/null +++ b/model/model/layers/22/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a87ccc6178f71c9c625d3e3613bcc6404c0307f881db91dab377d1f25438bae +size 184420897 diff --git a/model/model/layers/22/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/22/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/22/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/22/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..a108edda46febfa332b649e6c9ec0517a3b87522 --- /dev/null +++ b/model/model/layers/22/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9119e690c02df60f707afa0814a19af5c6fa39dd7cc1c900757524a611e78f60 +size 140912 diff --git a/model/model/layers/22/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/22/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/22/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/22/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..8c847b76326456b9dacc47e262d327bdc4dff5d9 --- /dev/null +++ b/model/model/layers/22/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06aa968a7a09a024c3d83d799fdee3d98dbd311a21044dfe95b1109f60002b22 +size 188480067 diff --git a/model/model/layers/22/mlp/experts/up_proj/bias/.zarray b/model/model/layers/22/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/22/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/mlp/experts/up_proj/bias/0.0 b/model/model/layers/22/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..257495687d95a9e4d953003930d6c42324fa6e4e --- /dev/null +++ b/model/model/layers/22/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c924f19c50e2c743bcf693ed03978cda437352c05ce40602ccad9604760b43e +size 130728 diff --git a/model/model/layers/22/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/22/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/22/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/22/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..a2aae06acef9861488d6c834a3cf4e9888fe0c9a --- /dev/null +++ b/model/model/layers/22/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9a70ac5da6191b14345723ed7f0fc9b7889b001b875294ad021aa7afb9d2fe5 +size 182888151 diff --git a/model/model/layers/22/mlp/router/bias/.zarray b/model/model/layers/22/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/22/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/mlp/router/bias/0 b/model/model/layers/22/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..8d281ebd753819d27876e185e32da4d18f081116 Binary files /dev/null and b/model/model/layers/22/mlp/router/bias/0 differ diff --git a/model/model/layers/22/mlp/router/kernel/.zarray b/model/model/layers/22/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/22/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/mlp/router/kernel/0.0 b/model/model/layers/22/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..2b6908297b8b5d9469e6e6694237b1783969589b --- /dev/null +++ b/model/model/layers/22/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e089cd3817e8f79275109fa922b930d649fe617d7ba3131e9d73346bc39fe485 +size 144705 diff --git a/model/model/layers/22/post_attention_layernorm/kernel/.zarray b/model/model/layers/22/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/22/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/post_attention_layernorm/kernel/0 b/model/model/layers/22/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..f90924e729492df1c5bcb831150f97f71741f6d1 Binary files /dev/null and b/model/model/layers/22/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/22/self_attn/k_proj/bias/.zarray b/model/model/layers/22/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/22/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/self_attn/k_proj/bias/0 b/model/model/layers/22/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/22/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/22/self_attn/k_proj/kernel/.zarray b/model/model/layers/22/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/22/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/self_attn/k_proj/kernel/0.0 b/model/model/layers/22/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..f52b206f0f290e6bb2af28c2faa559c322b4f2fb --- /dev/null +++ b/model/model/layers/22/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80efbfb3d978fa41b92adfd550a3e5ce1202fabf193a47da531c8f864ae845c0 +size 580332 diff --git a/model/model/layers/22/self_attn/k_proj/kernel/0.1 b/model/model/layers/22/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..c7155927274436b9355cb46b48056b03daec042f --- /dev/null +++ b/model/model/layers/22/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5dba610f0961ccc5de6fb5aed118e0cd746a16ca42fe32105b4d96a4e1de309 +size 585281 diff --git a/model/model/layers/22/self_attn/k_proj/kernel/0.2 b/model/model/layers/22/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..14a8eaf088d0b7d31eb349d65f8ef67a59a4ef57 --- /dev/null +++ b/model/model/layers/22/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9e25ff9af50d93d92104bb1fb08aca37c04454d1132979910d896c2133a5166 +size 580861 diff --git a/model/model/layers/22/self_attn/k_proj/kernel/0.3 b/model/model/layers/22/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..74e6373da5e45d9fb566814f840cdbcc305ad4ab --- /dev/null +++ b/model/model/layers/22/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b4013f1ce881798148fb2ecf84cb4e91a98f1a075796a0a82b44be920ac1e8a +size 587303 diff --git a/model/model/layers/22/self_attn/o_proj/bias/.zarray b/model/model/layers/22/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/22/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/self_attn/o_proj/bias/0 b/model/model/layers/22/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..77d65704404d624fb2635e9b4a229e5092f6a090 Binary files /dev/null and b/model/model/layers/22/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/22/self_attn/o_proj/kernel/.zarray b/model/model/layers/22/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/22/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/self_attn/o_proj/kernel/0.0 b/model/model/layers/22/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..cf53a5ee8efabe87768ec507be61f7a380c4717b --- /dev/null +++ b/model/model/layers/22/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df998c39c5402d768a72381d512da776de3578b4ffd5aea0a2d4e8c0e0a2e073 +size 4653125 diff --git a/model/model/layers/22/self_attn/o_proj/kernel/1.0 b/model/model/layers/22/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..97750a771a702f879bca1de73916bfa9651d62c0 --- /dev/null +++ b/model/model/layers/22/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f697fa17f56371cc2c03808c5bd3754d077bf34dedfd1c6f0bb7b23c84882a37 +size 4643660 diff --git a/model/model/layers/22/self_attn/o_proj/kernel/2.0 b/model/model/layers/22/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..f109b497cb102b577110684218f42919e8bb2cb8 --- /dev/null +++ b/model/model/layers/22/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48d44f3b7ab9848888096f8222be74c64c6920f5aa8b19448dc6e6a7201cefa9 +size 4650840 diff --git a/model/model/layers/22/self_attn/o_proj/kernel/3.0 b/model/model/layers/22/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..997bd4ed4c565e59a4bf0f574f3996710a2d0f33 --- /dev/null +++ b/model/model/layers/22/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2763f2de5c3e539f7bd7ac9966706c206ca60d34a5438883cd0ba4335dae25f6 +size 4643901 diff --git a/model/model/layers/22/self_attn/q_proj/bias/.zarray b/model/model/layers/22/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/22/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/self_attn/q_proj/bias/0 b/model/model/layers/22/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..b5aa054d1bcd9a090c26a34a88e6792074ceea45 Binary files /dev/null and b/model/model/layers/22/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/22/self_attn/q_proj/kernel/.zarray b/model/model/layers/22/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/22/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/self_attn/q_proj/kernel/0.0 b/model/model/layers/22/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..8a5aa5d2312460ec089d69c9fdb63fecdd071958 --- /dev/null +++ b/model/model/layers/22/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6f63354c690490a7744b7770c2fe63e42daed60c0e12059e549bf1105a40943 +size 4670827 diff --git a/model/model/layers/22/self_attn/q_proj/kernel/0.1 b/model/model/layers/22/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..3740586e6df8bca53230f9c0e87f60d99014cddb --- /dev/null +++ b/model/model/layers/22/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d0eae65d8ce8f4d51cf80f3c9e6f36223b030a65e97f0b9e58cdf56ac57b65e +size 4669869 diff --git a/model/model/layers/22/self_attn/q_proj/kernel/0.2 b/model/model/layers/22/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..4160f78c8db6c9eb42d3c54187c95b45876da8a9 --- /dev/null +++ b/model/model/layers/22/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9f920a0bce8ccbfc4c5db185ac011b5ba0ca38876dee68379e972783219cf3b +size 4660855 diff --git a/model/model/layers/22/self_attn/q_proj/kernel/0.3 b/model/model/layers/22/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..4317bb4f398f414f3c2dc03c2b938973981d0be5 --- /dev/null +++ b/model/model/layers/22/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34a0ce05f388b6f744d4f9540c74267fd5016e76c53ff9bd7bbe04adf664b70e +size 4700050 diff --git a/model/model/layers/22/self_attn/sinks/.zarray b/model/model/layers/22/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/22/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/self_attn/sinks/0 b/model/model/layers/22/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..7dd1f74464145cd765696725ce8ae35e93a65145 Binary files /dev/null and b/model/model/layers/22/self_attn/sinks/0 differ diff --git a/model/model/layers/22/self_attn/v_proj/bias/.zarray b/model/model/layers/22/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/22/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/self_attn/v_proj/bias/0 b/model/model/layers/22/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..f3895ef53b8684239b2faf2ada1e794ca7372af5 Binary files /dev/null and b/model/model/layers/22/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/22/self_attn/v_proj/kernel/.zarray b/model/model/layers/22/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/22/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/22/self_attn/v_proj/kernel/0.0 b/model/model/layers/22/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..68bd85a4f950c723bfd4efd249bec95239417b14 --- /dev/null +++ b/model/model/layers/22/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c1e4a614d9d64a4a134a3ab8b9fced4f05f2fc1f8d78b9f89e1918b70054eac +size 575110 diff --git a/model/model/layers/22/self_attn/v_proj/kernel/0.1 b/model/model/layers/22/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..26cc914c41394c635d442a55b01d76a7483fea4c --- /dev/null +++ b/model/model/layers/22/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a1676f85541ecfa1dac3d2b43a413571243da2e9e0e7dc73d427c0285d65af8 +size 577631 diff --git a/model/model/layers/22/self_attn/v_proj/kernel/0.2 b/model/model/layers/22/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..5f35621d2acff0eb34cc35d311b16de150be8be9 --- /dev/null +++ b/model/model/layers/22/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36dcfababb044269c38e00df1a19ffb58c27f2d95bcfddb91431efdf13daf167 +size 575778 diff --git a/model/model/layers/22/self_attn/v_proj/kernel/0.3 b/model/model/layers/22/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..7f8b5002aae028561728ba8493f73a0f96802992 --- /dev/null +++ b/model/model/layers/22/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47f6d8717dde1da9f9330a041550e4ebf3742fec95f0be971ad716e24ba1ed96 +size 579106 diff --git a/model/model/layers/23/input_layernorm/kernel/.zarray b/model/model/layers/23/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/23/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/input_layernorm/kernel/0 b/model/model/layers/23/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..7048a10d3788ce79c67f95bb3688f9d23c105cec Binary files /dev/null and b/model/model/layers/23/input_layernorm/kernel/0 differ diff --git a/model/model/layers/23/mlp/experts/down_proj/bias/.zarray b/model/model/layers/23/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/23/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/mlp/experts/down_proj/bias/0.0 b/model/model/layers/23/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..26469316c25cb9ef4d317bb23fa314a40adfa511 --- /dev/null +++ b/model/model/layers/23/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d59cdd6e6cdb04604d3d28ad434ce9d0d1bbc919232523b39fafc3a54e9cb38 +size 144106 diff --git a/model/model/layers/23/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/23/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/23/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/23/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..ca5e626b424d26533b3278cce76dbcc07f50f687 --- /dev/null +++ b/model/model/layers/23/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:819f9af3c851ea1d7fafbb5e2c5559959ee6828aa0c043c7d627a83dc00db868 +size 177577438 diff --git a/model/model/layers/23/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/23/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/23/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/23/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..9e84bc98b154982c1cd89b84a3b616774f898c00 --- /dev/null +++ b/model/model/layers/23/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18e67cb61f0cabf2d0ced5f74e945b550a394547869fd2078ab6e800e9dd07ef +size 138207 diff --git a/model/model/layers/23/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/23/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/23/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/23/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..6d188ce0d60f85e4db321d739a7091434999f554 --- /dev/null +++ b/model/model/layers/23/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6ca60f635ea38cadb835e65dc120130b542dc2043cf791c899a41ae1f551d53 +size 187458501 diff --git a/model/model/layers/23/mlp/experts/up_proj/bias/.zarray b/model/model/layers/23/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/23/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/mlp/experts/up_proj/bias/0.0 b/model/model/layers/23/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..a34f53ebdbf5c8ecdf8a582e9ff9ac3c65728a82 --- /dev/null +++ b/model/model/layers/23/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:302913d3f238227ecacc34e4fbab13ec1a2790f019c30881b57e7f9f1c2ca807 +size 132222 diff --git a/model/model/layers/23/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/23/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/23/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/23/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..9ad7dfc3651b9eae69008a556d6c6d910fb3da6b --- /dev/null +++ b/model/model/layers/23/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14bd3250905fa745b0dd24be650d7a5d49c59d5359964077020a50f854b446f1 +size 181905124 diff --git a/model/model/layers/23/mlp/router/bias/.zarray b/model/model/layers/23/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/23/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/mlp/router/bias/0 b/model/model/layers/23/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..cfced3478b8c7446a671c6d1a5ab3d24a943a986 Binary files /dev/null and b/model/model/layers/23/mlp/router/bias/0 differ diff --git a/model/model/layers/23/mlp/router/kernel/.zarray b/model/model/layers/23/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/23/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/mlp/router/kernel/0.0 b/model/model/layers/23/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..673eaa3be464fb589901618436447fa11b2077af --- /dev/null +++ b/model/model/layers/23/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:128df59ffbc44b098fcb1d699c3986678ed56744bd8590d226da5d186b598477 +size 144710 diff --git a/model/model/layers/23/post_attention_layernorm/kernel/.zarray b/model/model/layers/23/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/23/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/post_attention_layernorm/kernel/0 b/model/model/layers/23/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..fada91fdff4a82e0979c4a573eff1ff9901b2db7 Binary files /dev/null and b/model/model/layers/23/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/23/self_attn/k_proj/bias/.zarray b/model/model/layers/23/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/23/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/self_attn/k_proj/bias/0 b/model/model/layers/23/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/23/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/23/self_attn/k_proj/kernel/.zarray b/model/model/layers/23/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/23/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/self_attn/k_proj/kernel/0.0 b/model/model/layers/23/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..d7e168c2124b09436d16692c61542e699b99b3f6 --- /dev/null +++ b/model/model/layers/23/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e7b7a8bd5a26e4b35b8c1e04f71f82f6c5302be7d2f83ced49047f3043432c1 +size 587335 diff --git a/model/model/layers/23/self_attn/k_proj/kernel/0.1 b/model/model/layers/23/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..a9e1c5ba0bf1a870ff1aca4e84ce782da9967bed --- /dev/null +++ b/model/model/layers/23/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52788f32497ba6e0283a6518fd56daea6a43163502148020273e00a723b09d7a +size 603601 diff --git a/model/model/layers/23/self_attn/k_proj/kernel/0.2 b/model/model/layers/23/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..4efc53893a895540ad3834d29d4a643f9f50e9e9 --- /dev/null +++ b/model/model/layers/23/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb8707fee0b71c88e7e15fbc2078f49837a6a55371324edebd7478528ff7304d +size 606547 diff --git a/model/model/layers/23/self_attn/k_proj/kernel/0.3 b/model/model/layers/23/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..cec47e59f706d97e2ec245b9d20014b7ee8b3779 --- /dev/null +++ b/model/model/layers/23/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a278ede98e86c9a29b0ebba7dae4cd3fed3f3cdde701225fafaae4fdd50ac06 +size 599958 diff --git a/model/model/layers/23/self_attn/o_proj/bias/.zarray b/model/model/layers/23/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/23/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/self_attn/o_proj/bias/0 b/model/model/layers/23/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..55242dc5f6ffce653575f2c02d195a039fd3b05e Binary files /dev/null and b/model/model/layers/23/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/23/self_attn/o_proj/kernel/.zarray b/model/model/layers/23/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/23/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/self_attn/o_proj/kernel/0.0 b/model/model/layers/23/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..9dc3a6857ca9d03a7099ece82274b413dd9a0b76 --- /dev/null +++ b/model/model/layers/23/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b26e6bc2561822be2dffa65e7c170dc87d6500a290ad7ebb84f0b13e8d68442a +size 4624838 diff --git a/model/model/layers/23/self_attn/o_proj/kernel/1.0 b/model/model/layers/23/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..53ec614e7ad0698a417a9bfb76482b29faeafb02 --- /dev/null +++ b/model/model/layers/23/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c42fb0cede6c485da5582b63bf661298299e7be5ee82a96666ac7210eb1fee9 +size 4628922 diff --git a/model/model/layers/23/self_attn/o_proj/kernel/2.0 b/model/model/layers/23/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..6be88df9495ca4caab5f80cea880ee505d914bcd --- /dev/null +++ b/model/model/layers/23/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0cfa72732f71a922460bb667c84e2eacd48d4fb4fe72575f2c5701b44ae7d92 +size 4630823 diff --git a/model/model/layers/23/self_attn/o_proj/kernel/3.0 b/model/model/layers/23/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..b42c301c51f74a282c3e9a621eb6eca5c4166f6c --- /dev/null +++ b/model/model/layers/23/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c865b056af8171b09da03411a378e1ad94ab71fedc4ccc96c8eb7cae6c5e1d1 +size 4628439 diff --git a/model/model/layers/23/self_attn/q_proj/bias/.zarray b/model/model/layers/23/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/23/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/self_attn/q_proj/bias/0 b/model/model/layers/23/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..ec4961546cb2fd09d02789e6342e206e49c3a765 Binary files /dev/null and b/model/model/layers/23/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/23/self_attn/q_proj/kernel/.zarray b/model/model/layers/23/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/23/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/self_attn/q_proj/kernel/0.0 b/model/model/layers/23/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..b4c6aa851f2bb90d39ce85feb0eac21f37ee7e79 --- /dev/null +++ b/model/model/layers/23/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e68255569295024f69ced36a19e97f563c7005c85e3bdde8ee009a7031211327 +size 4789326 diff --git a/model/model/layers/23/self_attn/q_proj/kernel/0.1 b/model/model/layers/23/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..b2d0aa663bf9c39407bb0d8d64562c32baa16859 --- /dev/null +++ b/model/model/layers/23/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dae46db3a1d9031a324f2a93bbe2046ec135000ca2e239155d409c64ee1e77a5 +size 4730386 diff --git a/model/model/layers/23/self_attn/q_proj/kernel/0.2 b/model/model/layers/23/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..1409574a0fd35cd6d4596971ac37c83cf53291b5 --- /dev/null +++ b/model/model/layers/23/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da700537faebbce4ae9fbc682a89242516ffbaf65cd04079c95f37c6ed3b4c9b +size 4717734 diff --git a/model/model/layers/23/self_attn/q_proj/kernel/0.3 b/model/model/layers/23/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..d364a35d6cb08baced3b82450ca9861c3b59184d --- /dev/null +++ b/model/model/layers/23/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf3a4188199b23ae5972d165f5fba2c762d8714ae0f2a98e5aa9f5cf8f8723a5 +size 4702703 diff --git a/model/model/layers/23/self_attn/sinks/.zarray b/model/model/layers/23/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/23/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/self_attn/sinks/0 b/model/model/layers/23/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..385e740a5d21a9a8c8d5b134ed4a57505489d55a Binary files /dev/null and b/model/model/layers/23/self_attn/sinks/0 differ diff --git a/model/model/layers/23/self_attn/v_proj/bias/.zarray b/model/model/layers/23/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/23/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/self_attn/v_proj/bias/0 b/model/model/layers/23/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..110b6f6c5ce6b46c3379340d69b9710b68153ceb Binary files /dev/null and b/model/model/layers/23/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/23/self_attn/v_proj/kernel/.zarray b/model/model/layers/23/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/23/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/23/self_attn/v_proj/kernel/0.0 b/model/model/layers/23/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..20590c67eb65aa2433c8ace668b85928d74a6ab1 --- /dev/null +++ b/model/model/layers/23/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f18234ee823784f004b62d36c1554e747929081a2793da3a4aa592215532525 +size 576836 diff --git a/model/model/layers/23/self_attn/v_proj/kernel/0.1 b/model/model/layers/23/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..7eed3c29b18c30b3bfe79f481cf6f8858ab90577 --- /dev/null +++ b/model/model/layers/23/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eae0acc569030d1807b55ae2956556bc3ac3ea51a251faa0a15480ece9178f6 +size 579010 diff --git a/model/model/layers/23/self_attn/v_proj/kernel/0.2 b/model/model/layers/23/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..318114faba94cd5ce16e12e6a6d882b45ed3908b --- /dev/null +++ b/model/model/layers/23/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79e9b9ae886b5bb56e83df37cb4265be35634e3b1f48d85b0b6b425e83a5e401 +size 580154 diff --git a/model/model/layers/23/self_attn/v_proj/kernel/0.3 b/model/model/layers/23/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..b86b54364df5886893e38f47f7cc476fa94c6715 --- /dev/null +++ b/model/model/layers/23/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53fe5ef8f7bf63e9be240d1538ad8b0b89cc895239e6acdc2b477007494608d1 +size 578470 diff --git a/model/model/layers/3/input_layernorm/kernel/.zarray b/model/model/layers/3/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/3/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/input_layernorm/kernel/0 b/model/model/layers/3/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..988493575627ae6292dbd5383799cda65142d44d Binary files /dev/null and b/model/model/layers/3/input_layernorm/kernel/0 differ diff --git a/model/model/layers/3/mlp/experts/down_proj/bias/.zarray b/model/model/layers/3/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/3/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/mlp/experts/down_proj/bias/0.0 b/model/model/layers/3/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..ad6857e88796340ef86a13256e1b6ebd9ee0f1c3 --- /dev/null +++ b/model/model/layers/3/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59d0348a4cfadbdbcf6f29f16092464ff1f0919d4c500c5710968229e8bb746d +size 146677 diff --git a/model/model/layers/3/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/3/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/3/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/3/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..31fe695fd5a6578c41b6002249e4df679e236090 --- /dev/null +++ b/model/model/layers/3/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:199ed66a5aa3b1c3766be7325055f113e6d76eb4e367f9531b28aa08bc194605 +size 195283771 diff --git a/model/model/layers/3/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/3/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/3/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/3/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..ae882d052d880be64af8f86e3ced7cab27ae28d1 --- /dev/null +++ b/model/model/layers/3/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0055511285e9bc351ba42cca35580c0b7212f825765225bb26d9e6a292031584 +size 131854 diff --git a/model/model/layers/3/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/3/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/3/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/3/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..f004f236b3d0b6aae03302f7397321e4c5fa4521 --- /dev/null +++ b/model/model/layers/3/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e912752ebf9c945b90554ad6fb27a24220d320ab0636b73bd5166bdaa25b07b1 +size 186910769 diff --git a/model/model/layers/3/mlp/experts/up_proj/bias/.zarray b/model/model/layers/3/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/3/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/mlp/experts/up_proj/bias/0.0 b/model/model/layers/3/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..d320d83481f6e256fff4b5f5bb4e0788dafdc5aa --- /dev/null +++ b/model/model/layers/3/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d794e6b0b6d2fb46df376ff66ffc90f0cab9ecd241cb9da05f5532ab89837f80 +size 114948 diff --git a/model/model/layers/3/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/3/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/3/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/3/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..fdb8579bc91a8997dd1a39b6284ad59ea326f75c --- /dev/null +++ b/model/model/layers/3/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5bd3b9723c21e70c04ac6ccb48e270ee689752f89024eb944eb59b0f8ab6a4c +size 179160443 diff --git a/model/model/layers/3/mlp/router/bias/.zarray b/model/model/layers/3/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/3/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/mlp/router/bias/0 b/model/model/layers/3/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..2beac032523713b5bc258a7520133ec2b310ed0d Binary files /dev/null and b/model/model/layers/3/mlp/router/bias/0 differ diff --git a/model/model/layers/3/mlp/router/kernel/.zarray b/model/model/layers/3/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/3/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/mlp/router/kernel/0.0 b/model/model/layers/3/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..67917b811718d7165476b71acd7b029e69b9792e --- /dev/null +++ b/model/model/layers/3/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a5a9828906ae1dd5a0bc5eb9bf59cd98440d95eb95f4be18d02ed68da982926 +size 145387 diff --git a/model/model/layers/3/post_attention_layernorm/kernel/.zarray b/model/model/layers/3/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/3/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/post_attention_layernorm/kernel/0 b/model/model/layers/3/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..62291e3eb5856b29d2a8592b76cfb38d092f118d Binary files /dev/null and b/model/model/layers/3/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/3/self_attn/k_proj/bias/.zarray b/model/model/layers/3/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/3/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/self_attn/k_proj/bias/0 b/model/model/layers/3/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/3/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/3/self_attn/k_proj/kernel/.zarray b/model/model/layers/3/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/3/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/self_attn/k_proj/kernel/0.0 b/model/model/layers/3/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..9cb4ace7a52a211497d51b64eca7d93361e38120 --- /dev/null +++ b/model/model/layers/3/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43195e38e36c60b2fd5bf4fa30331cd227de389858fd7d9708874305a79aa500 +size 586463 diff --git a/model/model/layers/3/self_attn/k_proj/kernel/0.1 b/model/model/layers/3/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..66d464177b5b4d8b273dd48db69c8f541f121bac --- /dev/null +++ b/model/model/layers/3/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1bd6ded59e5c63a0671df067127dd4943b694e218ef08906fbd1bf6946858f9 +size 589909 diff --git a/model/model/layers/3/self_attn/k_proj/kernel/0.2 b/model/model/layers/3/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..27f3ec1922f2d0e32c5b9da6bd1eea231c2c4863 --- /dev/null +++ b/model/model/layers/3/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00520cdc7a6a573f93d443634d5024fadb2da1921cf3b4a87737a4bde26b87dd +size 585703 diff --git a/model/model/layers/3/self_attn/k_proj/kernel/0.3 b/model/model/layers/3/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..3e8bddcea13cc6ce6eb6e95239a1fe002a5e8085 --- /dev/null +++ b/model/model/layers/3/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bdaac6dd949ee6345bbefde40331a2285709f75b79f6bcddb51938866ae1c16 +size 589240 diff --git a/model/model/layers/3/self_attn/o_proj/bias/.zarray b/model/model/layers/3/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/3/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/self_attn/o_proj/bias/0 b/model/model/layers/3/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..b379a7b7a3d2aae2626acde2ca7a1e1073899a1c Binary files /dev/null and b/model/model/layers/3/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/3/self_attn/o_proj/kernel/.zarray b/model/model/layers/3/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/3/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/self_attn/o_proj/kernel/0.0 b/model/model/layers/3/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..f6e1bc5773ee09f3d7cfb99907c6b531843bc148 --- /dev/null +++ b/model/model/layers/3/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c24c6f7e80f1c36629c4a361ca2a94ae6543b4c40efeef825edd64131dc77e8 +size 4665029 diff --git a/model/model/layers/3/self_attn/o_proj/kernel/1.0 b/model/model/layers/3/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..82773dc1f7ed7441ad46cbaaf862a55907e2ff60 --- /dev/null +++ b/model/model/layers/3/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc6508732b01efe2e9618900ab4fba9e5cc2630c4a1f2ce0dabdfed0adabc508 +size 4677025 diff --git a/model/model/layers/3/self_attn/o_proj/kernel/2.0 b/model/model/layers/3/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..52e073c2501de3e2b737b6e494e025a46d99a49e --- /dev/null +++ b/model/model/layers/3/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44f5cc21e59ab39a7ec700ccd6662f7f6011f846d9da5988957fc5a3c902f4fa +size 4683832 diff --git a/model/model/layers/3/self_attn/o_proj/kernel/3.0 b/model/model/layers/3/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..15795e1b7c7acb3e6fec03280fe83ba3f473ff81 --- /dev/null +++ b/model/model/layers/3/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42f375a24b6a6bbfb41c034282aa5652bbe9d8b11091b2d732b5d1c7673d6dd9 +size 4672564 diff --git a/model/model/layers/3/self_attn/q_proj/bias/.zarray b/model/model/layers/3/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/3/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/self_attn/q_proj/bias/0 b/model/model/layers/3/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..493771fa080c5bab7876bfad1be5ed441973fdab Binary files /dev/null and b/model/model/layers/3/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/3/self_attn/q_proj/kernel/.zarray b/model/model/layers/3/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/3/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/self_attn/q_proj/kernel/0.0 b/model/model/layers/3/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..83cd55896679b0e0deb5cf3ba3a33462b75826ee --- /dev/null +++ b/model/model/layers/3/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6907605638d319905a893769d55185c604ee9c73cab76ceb7e0065944710b8b3 +size 4679930 diff --git a/model/model/layers/3/self_attn/q_proj/kernel/0.1 b/model/model/layers/3/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..4d9243409fc7ed831b9821df9011443efbd222d4 --- /dev/null +++ b/model/model/layers/3/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d83b3d53d344f068ecea73654732ccfd60b88f4471af74239231c310015cb46b +size 4683775 diff --git a/model/model/layers/3/self_attn/q_proj/kernel/0.2 b/model/model/layers/3/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..cceec44f5142399ddab51115660d59423814d9c9 --- /dev/null +++ b/model/model/layers/3/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3faf91152e19f9b34cfa30a2c88813626baf046203f79ddd2c46189712b45f2 +size 4680600 diff --git a/model/model/layers/3/self_attn/q_proj/kernel/0.3 b/model/model/layers/3/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..e6e4907e73f5bc2f2d672d0b51f39c352e0d87b4 --- /dev/null +++ b/model/model/layers/3/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91ef257a683458036375f66be93997303e9d988cd7aca6e17db8ccaa0eb7826f +size 4664141 diff --git a/model/model/layers/3/self_attn/sinks/.zarray b/model/model/layers/3/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/3/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/self_attn/sinks/0 b/model/model/layers/3/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..56559e8dc215f939417749bb4f5d92aa6b832147 Binary files /dev/null and b/model/model/layers/3/self_attn/sinks/0 differ diff --git a/model/model/layers/3/self_attn/v_proj/bias/.zarray b/model/model/layers/3/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/3/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/self_attn/v_proj/bias/0 b/model/model/layers/3/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..83ff60976cad8652a1e6e590fe0c4909d2f78521 Binary files /dev/null and b/model/model/layers/3/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/3/self_attn/v_proj/kernel/.zarray b/model/model/layers/3/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/3/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/3/self_attn/v_proj/kernel/0.0 b/model/model/layers/3/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..cb57a32e8575cb83a58978bc2ce0bd4deed96615 --- /dev/null +++ b/model/model/layers/3/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c1b7245928f798fbfe5900db664bfacd5c66f8d6a858cd9695d3434670c99e9 +size 581836 diff --git a/model/model/layers/3/self_attn/v_proj/kernel/0.1 b/model/model/layers/3/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..7ad0cf7325533d35eb5e0cfa237a9169eb03ca91 --- /dev/null +++ b/model/model/layers/3/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfb141f13f298e4c2bed57ae28938cc87eb68f1502309a03b007e812095185bd +size 585205 diff --git a/model/model/layers/3/self_attn/v_proj/kernel/0.2 b/model/model/layers/3/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..10ad983c2d7d5fa7be9d18ddcf66b0e55d141ecf --- /dev/null +++ b/model/model/layers/3/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ee305d296f4104e4844365b0bb78a1477153898903bb77deec916021e17ed4b +size 587681 diff --git a/model/model/layers/3/self_attn/v_proj/kernel/0.3 b/model/model/layers/3/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..5d4cc25792487bd3d60468cec543c4a048cfa087 --- /dev/null +++ b/model/model/layers/3/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:750fbb4d22fac3ab69f3afd879897a2235b418bd1c76375fdd3473e81d3896a6 +size 579936 diff --git a/model/model/layers/4/input_layernorm/kernel/.zarray b/model/model/layers/4/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/4/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/input_layernorm/kernel/0 b/model/model/layers/4/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..2753aa0feda06d528e9f425cd659f87754483f35 Binary files /dev/null and b/model/model/layers/4/input_layernorm/kernel/0 differ diff --git a/model/model/layers/4/mlp/experts/down_proj/bias/.zarray b/model/model/layers/4/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/4/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/mlp/experts/down_proj/bias/0.0 b/model/model/layers/4/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..3b28bff86379a512e139a98fbdc327dfdec08878 --- /dev/null +++ b/model/model/layers/4/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34210f4cb9cf30a4477f3f6bc385232f2d8bedd7bd291e72f3dec0940d998eba +size 146262 diff --git a/model/model/layers/4/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/4/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/4/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/4/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..fcb664fe5b200bff723b1fa04ab684e5cd5c381e --- /dev/null +++ b/model/model/layers/4/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa1894342073904a3c55fc2d1e713bc4d0d9f8ae467b6e67f9c6d23ebb80d340 +size 194125551 diff --git a/model/model/layers/4/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/4/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/4/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/4/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..6e1acc620c9da6a7c68874aca61294aa36232371 --- /dev/null +++ b/model/model/layers/4/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20cbe9d616ca788d87c931050d6652867f645537125df8d911b8523da6268501 +size 132049 diff --git a/model/model/layers/4/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/4/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/4/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/4/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..15be5a3f1a1795d5935cc00c29903d10a3791b29 --- /dev/null +++ b/model/model/layers/4/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae6be5e6030c4b1ecaf9141f4833b26abdd171b01af18a58578c0ee6416d424a +size 187501888 diff --git a/model/model/layers/4/mlp/experts/up_proj/bias/.zarray b/model/model/layers/4/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/4/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/mlp/experts/up_proj/bias/0.0 b/model/model/layers/4/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..3eb586224836b829f102b9b224b742f6857cdf08 --- /dev/null +++ b/model/model/layers/4/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23fff917c3f02c8aadb237d2f975002a99c53c56a4795949f1158322a93ef492 +size 115772 diff --git a/model/model/layers/4/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/4/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/4/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/4/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..f58bc101acddb7f11154ca7c344abc10add07c27 --- /dev/null +++ b/model/model/layers/4/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27edcfcb7f2c1fa083b91885b28c128c210eddbbc4db15a9269293e42ce0d69e +size 179127971 diff --git a/model/model/layers/4/mlp/router/bias/.zarray b/model/model/layers/4/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/4/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/mlp/router/bias/0 b/model/model/layers/4/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..57c1dac2eede7c365a516781ac90eded270e0bee Binary files /dev/null and b/model/model/layers/4/mlp/router/bias/0 differ diff --git a/model/model/layers/4/mlp/router/kernel/.zarray b/model/model/layers/4/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/4/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/mlp/router/kernel/0.0 b/model/model/layers/4/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..dde577e8e34bc0d33e8785a013241a55eeac499b --- /dev/null +++ b/model/model/layers/4/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35787d0f4aee47c6d00b316fbe117ee083ed08358a778bd28550d848c5122274 +size 145086 diff --git a/model/model/layers/4/post_attention_layernorm/kernel/.zarray b/model/model/layers/4/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/4/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/post_attention_layernorm/kernel/0 b/model/model/layers/4/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..552fe32da7e88f88e45857c829d333b33b94cb15 Binary files /dev/null and b/model/model/layers/4/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/4/self_attn/k_proj/bias/.zarray b/model/model/layers/4/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/4/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/self_attn/k_proj/bias/0 b/model/model/layers/4/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/4/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/4/self_attn/k_proj/kernel/.zarray b/model/model/layers/4/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/4/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/self_attn/k_proj/kernel/0.0 b/model/model/layers/4/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..59745f775e2aab319151ddadd6fcbfb443ea16ad --- /dev/null +++ b/model/model/layers/4/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d8d95cce07a83f8202b1aee3ec4f7171b6b7dcb15f3d51358a007903a7df984 +size 582632 diff --git a/model/model/layers/4/self_attn/k_proj/kernel/0.1 b/model/model/layers/4/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..1a9b730b3ca2e7b06b646eb69fc77348f769546b --- /dev/null +++ b/model/model/layers/4/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73a7ab527f70e3eecc80a585fda88bb46353af2df24557f3690f4a0fa2ea3278 +size 582724 diff --git a/model/model/layers/4/self_attn/k_proj/kernel/0.2 b/model/model/layers/4/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..c791d01575123fa55f66ea7592605a9193076d4c --- /dev/null +++ b/model/model/layers/4/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eba5ed126ec894ac79e16075c87bbfa395a246c430ec223a4e4dd4e819608bd +size 580276 diff --git a/model/model/layers/4/self_attn/k_proj/kernel/0.3 b/model/model/layers/4/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..3a3a6e3c418b6706fb31ccc9793ec2eec0a8c45c --- /dev/null +++ b/model/model/layers/4/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:422c52946a7290d30679c619f6cca0c2f8c6dafbc62290f8bcc81b8562af19f0 +size 581073 diff --git a/model/model/layers/4/self_attn/o_proj/bias/.zarray b/model/model/layers/4/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/4/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/self_attn/o_proj/bias/0 b/model/model/layers/4/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..f667a699bf733d31a31e5aaa7fcfc05b44e1a581 Binary files /dev/null and b/model/model/layers/4/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/4/self_attn/o_proj/kernel/.zarray b/model/model/layers/4/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/4/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/self_attn/o_proj/kernel/0.0 b/model/model/layers/4/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..19ab5205393994499e3328da80e6c302dda8cd50 --- /dev/null +++ b/model/model/layers/4/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b06ead1dd82c7d0191b6b6312696785db3ab661796e6a822b9478b84ac804fd0 +size 4668323 diff --git a/model/model/layers/4/self_attn/o_proj/kernel/1.0 b/model/model/layers/4/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..90909aea011dc7cfd79b183cffeaafbecb774500 --- /dev/null +++ b/model/model/layers/4/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da8e692cae31c120a72943fb41faed6430bf5471b37c3d2fffa04d1540c56328 +size 4685953 diff --git a/model/model/layers/4/self_attn/o_proj/kernel/2.0 b/model/model/layers/4/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..58787cef215503ef47c74b8c2038440fd4a87bfb --- /dev/null +++ b/model/model/layers/4/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ac48639389910343c531d32632622dc8c2dbd6bcfa1b695948c9a134b728485 +size 4676564 diff --git a/model/model/layers/4/self_attn/o_proj/kernel/3.0 b/model/model/layers/4/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..fb96daf69aca1d9de09d69e6dd36380acdae841c --- /dev/null +++ b/model/model/layers/4/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d446ff3b5935057919af39588191ad055749d1c9cacd0b2b46f968999c538ce +size 4666526 diff --git a/model/model/layers/4/self_attn/q_proj/bias/.zarray b/model/model/layers/4/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/4/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/self_attn/q_proj/bias/0 b/model/model/layers/4/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..5680aaceac56b9eef5de10be463d8c10a1606622 Binary files /dev/null and b/model/model/layers/4/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/4/self_attn/q_proj/kernel/.zarray b/model/model/layers/4/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/4/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/self_attn/q_proj/kernel/0.0 b/model/model/layers/4/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..2fefdb6d754435f9c1a745933d79300997c4c291 --- /dev/null +++ b/model/model/layers/4/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efd8171c905083806e50ad8b46efaeb763b4e76ddad476947a3bf8dfead039e4 +size 4665115 diff --git a/model/model/layers/4/self_attn/q_proj/kernel/0.1 b/model/model/layers/4/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..20ba1717acb36e42006b2a3910bb323eb1fa3ad1 --- /dev/null +++ b/model/model/layers/4/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60baa15193771e2f4e09cae5a40e263da94f39546cbc6ab92495488d56f3928b +size 4682230 diff --git a/model/model/layers/4/self_attn/q_proj/kernel/0.2 b/model/model/layers/4/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..ce7992d7ce0a56db60850cec2ab262a70f8245c1 --- /dev/null +++ b/model/model/layers/4/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0a61eb3bf118d58f2a5654fbd35eb3268a3f7c006f12939cfca338fbe40b95c +size 4727251 diff --git a/model/model/layers/4/self_attn/q_proj/kernel/0.3 b/model/model/layers/4/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..77cbc63fd9670197c2bda35e7a636d8691d31e23 --- /dev/null +++ b/model/model/layers/4/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d3574526d06719b3f07a4de06f1523276893ff54163cf12d3009237dd508ce9 +size 4651006 diff --git a/model/model/layers/4/self_attn/sinks/.zarray b/model/model/layers/4/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/4/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/self_attn/sinks/0 b/model/model/layers/4/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..4b06de6d4726d970ee54ba38e26158fba9cd2c43 Binary files /dev/null and b/model/model/layers/4/self_attn/sinks/0 differ diff --git a/model/model/layers/4/self_attn/v_proj/bias/.zarray b/model/model/layers/4/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/4/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/self_attn/v_proj/bias/0 b/model/model/layers/4/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..cacfe200098c814f430ee607f72593ea8355a6c1 Binary files /dev/null and b/model/model/layers/4/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/4/self_attn/v_proj/kernel/.zarray b/model/model/layers/4/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/4/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/4/self_attn/v_proj/kernel/0.0 b/model/model/layers/4/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..24220fbce4db3ed2d3aab99e78b390a262e5e403 --- /dev/null +++ b/model/model/layers/4/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f03472f9841aaff40d21f5eab5470003b38adc491bdaf5a5208d785023eaa002 +size 581243 diff --git a/model/model/layers/4/self_attn/v_proj/kernel/0.1 b/model/model/layers/4/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..38e0b7aafaa7d8dcf706a9ce02d72a2c45b009a0 --- /dev/null +++ b/model/model/layers/4/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:996965725d87696a1ad0891c40cae2b911ce925e247c700c1e23740856006564 +size 580831 diff --git a/model/model/layers/4/self_attn/v_proj/kernel/0.2 b/model/model/layers/4/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..3ab96e7b8e240a4dde46f488cd7ff39b68c6f07b --- /dev/null +++ b/model/model/layers/4/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50f37e7f2cbd5a0d4b2115e303e10e97077b6dd53d4d45a6cfdf624051fe0db9 +size 578146 diff --git a/model/model/layers/4/self_attn/v_proj/kernel/0.3 b/model/model/layers/4/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..b9c5e0727d4b2dd0b674ad5e2261532f174af88c --- /dev/null +++ b/model/model/layers/4/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c85303f5be9f86ddc3652b426aee36fe96f1d55ab2df247db79c194e857652e6 +size 580020 diff --git a/model/model/layers/5/input_layernorm/kernel/.zarray b/model/model/layers/5/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/5/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/input_layernorm/kernel/0 b/model/model/layers/5/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..8890238131805780e3d99a0d2fdee418365358c2 Binary files /dev/null and b/model/model/layers/5/input_layernorm/kernel/0 differ diff --git a/model/model/layers/5/mlp/experts/down_proj/bias/.zarray b/model/model/layers/5/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/5/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/mlp/experts/down_proj/bias/0.0 b/model/model/layers/5/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..e12d9535878a6371162ad7e7fc0ce9d903a79ae3 --- /dev/null +++ b/model/model/layers/5/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a639f3a303047367f3fab645590371ceabffb565df3e28d87d4ca099951dc954 +size 146147 diff --git a/model/model/layers/5/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/5/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/5/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/5/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..723d809d0bf4634b63ee2b2e3c72155240bdca7f --- /dev/null +++ b/model/model/layers/5/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ba4a9e7ee7f7bac6130700c935b24e75de17e9c5928352d17c8d4609dc68701 +size 193157010 diff --git a/model/model/layers/5/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/5/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/5/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/5/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..217b0cb7df81d0dac4b36cb007d3a7af19b1ee5c --- /dev/null +++ b/model/model/layers/5/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c27c73586cbb3d171d3fbe38fe796e21ce3f90c21961367d214f3e742e364ec6 +size 131415 diff --git a/model/model/layers/5/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/5/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/5/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/5/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..68b15cbfe259f5cd32b7e52823649d571d4541be --- /dev/null +++ b/model/model/layers/5/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83ffdc30a7e3277f90b70ba698b3a064d2e643c7ac4c817bbd446d3f3ce4ea69 +size 186432248 diff --git a/model/model/layers/5/mlp/experts/up_proj/bias/.zarray b/model/model/layers/5/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/5/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/mlp/experts/up_proj/bias/0.0 b/model/model/layers/5/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..59c7ca0597b232536d57388b0157e2dcb5da80a0 --- /dev/null +++ b/model/model/layers/5/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e01e2425d26b6930a7d0ac9e8c4b580bc5ded0f8963cdf09cd60ec6e764789b5 +size 114223 diff --git a/model/model/layers/5/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/5/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/5/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/5/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..c56889f945a0278acde15714f1d01449f99af3a6 --- /dev/null +++ b/model/model/layers/5/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92c18c1c58043be91f2c9026529c173ae33452c6206ac5cfd7613c22ce313b9b +size 178816816 diff --git a/model/model/layers/5/mlp/router/bias/.zarray b/model/model/layers/5/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/5/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/mlp/router/bias/0 b/model/model/layers/5/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..0242f98d272763dca6f299149905e9151417d863 Binary files /dev/null and b/model/model/layers/5/mlp/router/bias/0 differ diff --git a/model/model/layers/5/mlp/router/kernel/.zarray b/model/model/layers/5/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/5/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/mlp/router/kernel/0.0 b/model/model/layers/5/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..17daf691dc0d0f36843998733105759e6bd56ece --- /dev/null +++ b/model/model/layers/5/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c983e6b66eb2910f4ec88eb5c9c0891c1bae79f38a56b13e45516c0b3db2ab68 +size 145307 diff --git a/model/model/layers/5/post_attention_layernorm/kernel/.zarray b/model/model/layers/5/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/5/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/post_attention_layernorm/kernel/0 b/model/model/layers/5/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..6d7442cbe2cd4e55caecfc80757bd106debdb9d7 Binary files /dev/null and b/model/model/layers/5/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/5/self_attn/k_proj/bias/.zarray b/model/model/layers/5/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/5/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/self_attn/k_proj/bias/0 b/model/model/layers/5/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/5/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/5/self_attn/k_proj/kernel/.zarray b/model/model/layers/5/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/5/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/self_attn/k_proj/kernel/0.0 b/model/model/layers/5/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..258280702c1e9710f52f9b9f660bfa6e39ce96f4 --- /dev/null +++ b/model/model/layers/5/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2376b34806f3603dd59295a796ab0fd8d54315f49f74500385971a21f4c5c200 +size 585765 diff --git a/model/model/layers/5/self_attn/k_proj/kernel/0.1 b/model/model/layers/5/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..c49b657ce1f0568d2673f44d9b029fdc6204d1fa --- /dev/null +++ b/model/model/layers/5/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c28a436f667b46ded9c3a40d3cb3755fb919924b81da3c57a4e04c55a494f6bd +size 581916 diff --git a/model/model/layers/5/self_attn/k_proj/kernel/0.2 b/model/model/layers/5/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..1696513cd22564b125e8b1adfc1ae74eb6ce3515 --- /dev/null +++ b/model/model/layers/5/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d19f8eec2c302cd563e595a96aa765e3edb36980ed305221c8213d36ee6eab2f +size 587086 diff --git a/model/model/layers/5/self_attn/k_proj/kernel/0.3 b/model/model/layers/5/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..7a973d4754214d2ecadc369c7dff2743d875f6a0 --- /dev/null +++ b/model/model/layers/5/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d2dd8b59d9e346b82eff65b3e1467a1addc9b25c00a0e1a1a8967bb0d37910f +size 584051 diff --git a/model/model/layers/5/self_attn/o_proj/bias/.zarray b/model/model/layers/5/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/5/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/self_attn/o_proj/bias/0 b/model/model/layers/5/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..251b36ba3e1b22147e83b13da4e7feceeab50d16 Binary files /dev/null and b/model/model/layers/5/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/5/self_attn/o_proj/kernel/.zarray b/model/model/layers/5/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/5/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/self_attn/o_proj/kernel/0.0 b/model/model/layers/5/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..859926f5669fb89334fde3fcc458b9e08dd0bfba --- /dev/null +++ b/model/model/layers/5/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9722266b7a1517e4557719594f3b9c69897bdc28a317421026d1fc18ffeae87 +size 4662178 diff --git a/model/model/layers/5/self_attn/o_proj/kernel/1.0 b/model/model/layers/5/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..165a4ed4c9e51881a614f1e51ede705a830dc350 --- /dev/null +++ b/model/model/layers/5/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e22ee4370196b797eb0e1779e5d1a7e00a9b17f42d1a6820cb283da8a0af88b +size 4668080 diff --git a/model/model/layers/5/self_attn/o_proj/kernel/2.0 b/model/model/layers/5/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..f45907a9f0607cb4ae676bb28018f9936dd525fd --- /dev/null +++ b/model/model/layers/5/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60d85444396c0b82453d31283a4d6790a30c49161c15e6aaede68d3c394d8b48 +size 4681788 diff --git a/model/model/layers/5/self_attn/o_proj/kernel/3.0 b/model/model/layers/5/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..6711c08606c2f91d8569234f64516d6cc5844cea --- /dev/null +++ b/model/model/layers/5/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f8acb42136b181783c47479f5c3acf4787c88c9ccd57138d1a19c7451bee2d1 +size 4673169 diff --git a/model/model/layers/5/self_attn/q_proj/bias/.zarray b/model/model/layers/5/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/5/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/self_attn/q_proj/bias/0 b/model/model/layers/5/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..9ab3487052f9bcb5293ccdbf7cdb126f689636ef Binary files /dev/null and b/model/model/layers/5/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/5/self_attn/q_proj/kernel/.zarray b/model/model/layers/5/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/5/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/self_attn/q_proj/kernel/0.0 b/model/model/layers/5/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..fe9a22c8f14a6e350bf2138fd034541e75886ce3 --- /dev/null +++ b/model/model/layers/5/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4a82f69da634d23d191c38f7e5cc7cc1a435d391c9e5266ab21ced100495429 +size 4663331 diff --git a/model/model/layers/5/self_attn/q_proj/kernel/0.1 b/model/model/layers/5/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..1ed19ee417d68d6d4549fb0022b1aef285110349 --- /dev/null +++ b/model/model/layers/5/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:539281bf3542f35eaef41692c245ba3267dd893426fe9fa392e6b32f01d5d6e6 +size 4682436 diff --git a/model/model/layers/5/self_attn/q_proj/kernel/0.2 b/model/model/layers/5/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..32847c9161e443e01d777843aebb9db3a2fc0040 --- /dev/null +++ b/model/model/layers/5/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0c7448f14af9f6a22deb81d20efc7a97616e5bebe35ce9aa5d46f2a176e2a10 +size 4669032 diff --git a/model/model/layers/5/self_attn/q_proj/kernel/0.3 b/model/model/layers/5/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..34c8cc396bf6469f6ba0357cd477fbed126e1aca --- /dev/null +++ b/model/model/layers/5/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:147116cc05a00ac8c5a394256b486c8784787463243b7dbfbe729ad23d168100 +size 4706567 diff --git a/model/model/layers/5/self_attn/sinks/.zarray b/model/model/layers/5/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/5/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/self_attn/sinks/0 b/model/model/layers/5/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..9c91e7ebce4dfd49a157f852eff6097355cb3bf6 Binary files /dev/null and b/model/model/layers/5/self_attn/sinks/0 differ diff --git a/model/model/layers/5/self_attn/v_proj/bias/.zarray b/model/model/layers/5/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/5/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/self_attn/v_proj/bias/0 b/model/model/layers/5/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..f4abe572a4d14ba3b9355e0e74b2bd60df5be46f Binary files /dev/null and b/model/model/layers/5/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/5/self_attn/v_proj/kernel/.zarray b/model/model/layers/5/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/5/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/5/self_attn/v_proj/kernel/0.0 b/model/model/layers/5/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..b96800d1437776166d9068631438af3676b87429 --- /dev/null +++ b/model/model/layers/5/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5694292c896dcb22b1f9ab408ea5eaddcbfd5300bde4e6ca36d895ee7f5f51c +size 580703 diff --git a/model/model/layers/5/self_attn/v_proj/kernel/0.1 b/model/model/layers/5/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..9ac538b6444bf8f40d59a96ef61f6e40b7cc71ad --- /dev/null +++ b/model/model/layers/5/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40ab5a5b18a2f0e29cf43116866802accc331398c8f74f1d10c9f91b2083e1d2 +size 580929 diff --git a/model/model/layers/5/self_attn/v_proj/kernel/0.2 b/model/model/layers/5/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..8215aea4c7e0b678f8a9abbb592c5b0e91f92a88 --- /dev/null +++ b/model/model/layers/5/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40743da90030557138f98297fbd73a84ee70dee75b0f69e0269aa34816c8caad +size 580640 diff --git a/model/model/layers/5/self_attn/v_proj/kernel/0.3 b/model/model/layers/5/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..8bcdb6856e72e82ec39d6c27698048a3c84b0b10 --- /dev/null +++ b/model/model/layers/5/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77f3c7e583554a0b16ff0f4c2eb381c299470fff3b53645fa8dad5fde9a4eeda +size 579614 diff --git a/model/model/layers/6/input_layernorm/kernel/.zarray b/model/model/layers/6/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/6/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/input_layernorm/kernel/0 b/model/model/layers/6/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..0d31c503fa3047fece68e8cbb1bd72e339d1942c Binary files /dev/null and b/model/model/layers/6/input_layernorm/kernel/0 differ diff --git a/model/model/layers/6/mlp/experts/down_proj/bias/.zarray b/model/model/layers/6/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/6/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/mlp/experts/down_proj/bias/0.0 b/model/model/layers/6/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..7225d919d6b7ca3d75649ced7139a4a0b3a7e444 --- /dev/null +++ b/model/model/layers/6/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c765af451251639d099dff100aa793493baf89d4348ade305d7065c743f2e802 +size 145708 diff --git a/model/model/layers/6/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/6/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/6/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/6/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..7fc4c4f55583f519d81dcc0a256fc3a06a5f258d --- /dev/null +++ b/model/model/layers/6/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9882bd27b3c42a81d185a830047083cab5b84365bccbd1268e196c48c63b77ef +size 191658570 diff --git a/model/model/layers/6/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/6/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/6/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/6/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..7b4391de361f170d6f4ed2ccc6f785bf4a231bd2 --- /dev/null +++ b/model/model/layers/6/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d133a6a7c046efde5a3caf034793a1879e265d9ff1c90af62f819efc8c94c0d7 +size 134138 diff --git a/model/model/layers/6/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/6/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/6/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/6/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..8bba7dddcf808d047985f07827481d252889877c --- /dev/null +++ b/model/model/layers/6/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14e83f2879da60beb40e2ab44e620a101104d6a33225f33ea5352bf0a5beb14a +size 188059294 diff --git a/model/model/layers/6/mlp/experts/up_proj/bias/.zarray b/model/model/layers/6/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/6/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/mlp/experts/up_proj/bias/0.0 b/model/model/layers/6/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..085a6f0abf8a34585e32944cb4ac0f1492aa46c3 --- /dev/null +++ b/model/model/layers/6/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d0d2336657a3d82305dfda00a12189a3e5a2c9d16c4b22e33a281f15ec30bfe +size 117059 diff --git a/model/model/layers/6/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/6/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/6/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/6/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..185ad26d25606244dcf85d9a23fa2a12ee832b6c --- /dev/null +++ b/model/model/layers/6/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55c735fed004ab1fd3aa1d513801651d5a291724e7bc5b2747cf50ea1b988ad6 +size 179576419 diff --git a/model/model/layers/6/mlp/router/bias/.zarray b/model/model/layers/6/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/6/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/mlp/router/bias/0 b/model/model/layers/6/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..cc4a2a7f7520de314c517173f5f602a93bbf0756 Binary files /dev/null and b/model/model/layers/6/mlp/router/bias/0 differ diff --git a/model/model/layers/6/mlp/router/kernel/.zarray b/model/model/layers/6/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/6/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/mlp/router/kernel/0.0 b/model/model/layers/6/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..55517ca8623f991c4f53112a7fbfb832641643fb --- /dev/null +++ b/model/model/layers/6/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2763e618bb2849a681e1aec9ffca73e51fbf6e5dffcf0de77fca5b0e9b07ec5f +size 145187 diff --git a/model/model/layers/6/post_attention_layernorm/kernel/.zarray b/model/model/layers/6/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/6/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/post_attention_layernorm/kernel/0 b/model/model/layers/6/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..eee8eb7d90d82af1a89c671cb8542555e5949a1a Binary files /dev/null and b/model/model/layers/6/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/6/self_attn/k_proj/bias/.zarray b/model/model/layers/6/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/6/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/self_attn/k_proj/bias/0 b/model/model/layers/6/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/6/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/6/self_attn/k_proj/kernel/.zarray b/model/model/layers/6/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/6/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/self_attn/k_proj/kernel/0.0 b/model/model/layers/6/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..57e12ee4786ddabd58b2b54b4e123d917bee3665 --- /dev/null +++ b/model/model/layers/6/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70cf82ae70cafbe1b9f8786d4223dca94981e1985c69ad36a2398559cef2fbf7 +size 583571 diff --git a/model/model/layers/6/self_attn/k_proj/kernel/0.1 b/model/model/layers/6/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..fbe0a81ad7076c1bbc605e60b912caae951b08fa --- /dev/null +++ b/model/model/layers/6/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7fc09d7c7ccd6ec4be26b8a42a00c21311347e5d5f3af2daf0d7d1b33cceb5f +size 580204 diff --git a/model/model/layers/6/self_attn/k_proj/kernel/0.2 b/model/model/layers/6/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..001bb5142d51841545e9e769fbc4093edc38d425 --- /dev/null +++ b/model/model/layers/6/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47daa3dd034a919cc0b872d297999d6bac3da9e84c32a703c4ce5003861b8f9c +size 579817 diff --git a/model/model/layers/6/self_attn/k_proj/kernel/0.3 b/model/model/layers/6/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..d4bb02d66002b5f2d728b1c8bf75b01eb0e371cb --- /dev/null +++ b/model/model/layers/6/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d8bbb14d7c3cff42079561f6707f5eee93a6ff14267ddce5e6bb095c9b18695 +size 586498 diff --git a/model/model/layers/6/self_attn/o_proj/bias/.zarray b/model/model/layers/6/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/6/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/self_attn/o_proj/bias/0 b/model/model/layers/6/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..4dc655afd2fbc1b1c9584125ebe0fbab84ba5a72 Binary files /dev/null and b/model/model/layers/6/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/6/self_attn/o_proj/kernel/.zarray b/model/model/layers/6/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/6/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/self_attn/o_proj/kernel/0.0 b/model/model/layers/6/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..5f39fbe888ace6746d17cbc6d4be15237b445960 --- /dev/null +++ b/model/model/layers/6/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9b54c9cdc1634375ef8363987ac84511fc807fb8d62de9c1d628fc1771bdb75 +size 4656007 diff --git a/model/model/layers/6/self_attn/o_proj/kernel/1.0 b/model/model/layers/6/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..5a3ce3376b56a7d61bde753d95928d777886322c --- /dev/null +++ b/model/model/layers/6/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:262a108aae0dc7df12101bc2a2bce31b9699c47e201d0935f3d365f717f89040 +size 4663594 diff --git a/model/model/layers/6/self_attn/o_proj/kernel/2.0 b/model/model/layers/6/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..5f586126b38e7ac79e99275d173329c9fb9207ba --- /dev/null +++ b/model/model/layers/6/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e1334d65272e311e6c81af5aa3962b0a4c5797fe9c4ab70c2ec84f782753cbe +size 4654992 diff --git a/model/model/layers/6/self_attn/o_proj/kernel/3.0 b/model/model/layers/6/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..53392262c68575402195a34a57ae02d0d5a68396 --- /dev/null +++ b/model/model/layers/6/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6185a2e672a2f3463114a96c08795f1b7228cedbc960758c181acb3e557568de +size 4671321 diff --git a/model/model/layers/6/self_attn/q_proj/bias/.zarray b/model/model/layers/6/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/6/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/self_attn/q_proj/bias/0 b/model/model/layers/6/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..5ec064c884521a1945ab305260b006b9e9749e1c Binary files /dev/null and b/model/model/layers/6/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/6/self_attn/q_proj/kernel/.zarray b/model/model/layers/6/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/6/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/self_attn/q_proj/kernel/0.0 b/model/model/layers/6/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..04a350e56beb06e3c578d7e76971bca9f6bf200e --- /dev/null +++ b/model/model/layers/6/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6d71d9c7ea21879734e2cb10191f6177196556a66b77c37042d99918700d5bb +size 4663523 diff --git a/model/model/layers/6/self_attn/q_proj/kernel/0.1 b/model/model/layers/6/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..317ed10d452ac16ecedc800e0044b22689fa14aa --- /dev/null +++ b/model/model/layers/6/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ffe4da12491185756eb29627a8e8cfcdf8f1bebdb8f8ac904728e614a7f2486 +size 4663499 diff --git a/model/model/layers/6/self_attn/q_proj/kernel/0.2 b/model/model/layers/6/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..c4cfc474c83fd12c9c69c1706b0767ba03f9b433 --- /dev/null +++ b/model/model/layers/6/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:823d92d73c162b145dbcb7b3d9a26e48717179c9a6541796d72b52939cde824e +size 4664428 diff --git a/model/model/layers/6/self_attn/q_proj/kernel/0.3 b/model/model/layers/6/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..fa85c125c458fbc83fedcf19a2592a01152dcfae --- /dev/null +++ b/model/model/layers/6/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:276e44e5382ce11f451f742d49aa4b35969481ebc3170674c9c7091c837d96ff +size 4680964 diff --git a/model/model/layers/6/self_attn/sinks/.zarray b/model/model/layers/6/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/6/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/self_attn/sinks/0 b/model/model/layers/6/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..afeec42251ec217e20d557422fcffd31b437a186 Binary files /dev/null and b/model/model/layers/6/self_attn/sinks/0 differ diff --git a/model/model/layers/6/self_attn/v_proj/bias/.zarray b/model/model/layers/6/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/6/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/self_attn/v_proj/bias/0 b/model/model/layers/6/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..947529fdd5eee36a3a1d413e4d633937cabdfac0 Binary files /dev/null and b/model/model/layers/6/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/6/self_attn/v_proj/kernel/.zarray b/model/model/layers/6/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/6/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/6/self_attn/v_proj/kernel/0.0 b/model/model/layers/6/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..076df6d7b2d2b7a01b76854112f83df83a66b663 --- /dev/null +++ b/model/model/layers/6/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da34ff3368a49542ccd52c09f9efc54ac0bf0c42d0f5bb9e013710788b0dc023 +size 580678 diff --git a/model/model/layers/6/self_attn/v_proj/kernel/0.1 b/model/model/layers/6/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..a58cead55cedf20ed1b3988d9e15223bd4feb71e --- /dev/null +++ b/model/model/layers/6/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbd672657a64696bbee55802704343909c44c107c091ef8a019eca86acea1a76 +size 577804 diff --git a/model/model/layers/6/self_attn/v_proj/kernel/0.2 b/model/model/layers/6/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..44374e9d0b03f9c544f7f7f37bf334a57fa60fb1 --- /dev/null +++ b/model/model/layers/6/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7933b22a54eaf0e6a95ef62939ae04bd2d76ed8c7cdea638db33496188e6921 +size 577562 diff --git a/model/model/layers/6/self_attn/v_proj/kernel/0.3 b/model/model/layers/6/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..b40d5915a59a9746a80c05754e64ae89432f22a8 --- /dev/null +++ b/model/model/layers/6/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65cf25e848b7b8c36100c74898f8081d755870a8cbeca002294d28708ca97d40 +size 578639 diff --git a/model/model/layers/7/input_layernorm/kernel/.zarray b/model/model/layers/7/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/7/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/input_layernorm/kernel/0 b/model/model/layers/7/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..7978968e5233fdb01deae217baa29f3a03e3efff Binary files /dev/null and b/model/model/layers/7/input_layernorm/kernel/0 differ diff --git a/model/model/layers/7/mlp/experts/down_proj/bias/.zarray b/model/model/layers/7/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/7/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/mlp/experts/down_proj/bias/0.0 b/model/model/layers/7/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..b8e1900c1030c879e495374f89ae0773634b63e0 --- /dev/null +++ b/model/model/layers/7/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95e2909fc8720d3d17fff7e90689a5dfc31d35a49c7823129fd634bd907c02a7 +size 145714 diff --git a/model/model/layers/7/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/7/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/7/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/7/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..3eddd642acb70c7417b1f2af6fc7640a31e1f082 --- /dev/null +++ b/model/model/layers/7/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9df682ad630b45bcadb667a0dcaf23c94e7a471221a88ad5a0d625b9218fa94a +size 190097027 diff --git a/model/model/layers/7/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/7/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/7/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/7/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..7538d7cbe0f79442c447a15fb0fd31faed3e399f --- /dev/null +++ b/model/model/layers/7/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d2c70957f343625ff1dd156e719d3d4f21c6f59731900cac637f466885644eb +size 136229 diff --git a/model/model/layers/7/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/7/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/7/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/7/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..447f8cc0ef6497049fa7bcfc9641fa42bfe05260 --- /dev/null +++ b/model/model/layers/7/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4c90f6fa9288f0cd5170e4e413cfd78558dd2b2909431d9361765a0536acc95 +size 190211870 diff --git a/model/model/layers/7/mlp/experts/up_proj/bias/.zarray b/model/model/layers/7/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/7/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/mlp/experts/up_proj/bias/0.0 b/model/model/layers/7/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..5a30a48bfed72bbdcd20f9d2bc097d507c247861 --- /dev/null +++ b/model/model/layers/7/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b94fc28e6ef1fc9c90dc8674692b5f382e153ed60009b682f6e348577de25d4 +size 120695 diff --git a/model/model/layers/7/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/7/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/7/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/7/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..b9a83368e50ba603329afc918fd59cc77be3c613 --- /dev/null +++ b/model/model/layers/7/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da81a5fc1d1f71740c360aa8b31b0638451d82117e471e4b0e57d58143df9a30 +size 180645204 diff --git a/model/model/layers/7/mlp/router/bias/.zarray b/model/model/layers/7/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/7/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/mlp/router/bias/0 b/model/model/layers/7/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a66daea72c7b584eabfb5b3f2824c97c364c3ecf Binary files /dev/null and b/model/model/layers/7/mlp/router/bias/0 differ diff --git a/model/model/layers/7/mlp/router/kernel/.zarray b/model/model/layers/7/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/7/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/mlp/router/kernel/0.0 b/model/model/layers/7/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..c6287b4a6fda0745c476a6932b77cc371dfe633c --- /dev/null +++ b/model/model/layers/7/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e877fb71b6e6e5c0d45e26c2caefa3fc2a337c5a7fad9175b19bfae4eed15435 +size 144995 diff --git a/model/model/layers/7/post_attention_layernorm/kernel/.zarray b/model/model/layers/7/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/7/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/post_attention_layernorm/kernel/0 b/model/model/layers/7/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..599494600acd90b50733b61687a49ad8c5693ba5 Binary files /dev/null and b/model/model/layers/7/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/7/self_attn/k_proj/bias/.zarray b/model/model/layers/7/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/7/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/self_attn/k_proj/bias/0 b/model/model/layers/7/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/7/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/7/self_attn/k_proj/kernel/.zarray b/model/model/layers/7/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/7/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/self_attn/k_proj/kernel/0.0 b/model/model/layers/7/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..8260a0748d27253932dca15bd2bd97ade34058f9 --- /dev/null +++ b/model/model/layers/7/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c7cc43881eb416ba01f8988459ec1df31e13dde1f273362a7d7a1b58a46251b +size 594832 diff --git a/model/model/layers/7/self_attn/k_proj/kernel/0.1 b/model/model/layers/7/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..a81b09322802a6796d283b2dafae1f008333d347 --- /dev/null +++ b/model/model/layers/7/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:834a3978660aa4ddae74bc81948ea4f02eb43524093fafcde71218e57ddf8cad +size 584340 diff --git a/model/model/layers/7/self_attn/k_proj/kernel/0.2 b/model/model/layers/7/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..a9750f209fd8658275df211ec223aa93df02fb85 --- /dev/null +++ b/model/model/layers/7/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:831634b7c975b64cda8044f41d4eda75605e65c30cda818843d4e30c762a7109 +size 585034 diff --git a/model/model/layers/7/self_attn/k_proj/kernel/0.3 b/model/model/layers/7/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..5b91cb2918510d66ddb5fa6e0dce1613795c1e2c --- /dev/null +++ b/model/model/layers/7/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcb5451ccc3b727c55878fe64949e8763f9cc01a518aa6d55417625626790fff +size 595604 diff --git a/model/model/layers/7/self_attn/o_proj/bias/.zarray b/model/model/layers/7/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/7/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/self_attn/o_proj/bias/0 b/model/model/layers/7/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..b9cfd6052a2bbd520d46bfd4b92c92bb30340173 Binary files /dev/null and b/model/model/layers/7/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/7/self_attn/o_proj/kernel/.zarray b/model/model/layers/7/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/7/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/self_attn/o_proj/kernel/0.0 b/model/model/layers/7/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..5f6ca70ff9b9aec68cb2cebbd89c0c9487de6ad4 --- /dev/null +++ b/model/model/layers/7/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a7b12321b4ad43d17cbbca930dffdd9c91d313145e81a32b5d7ed13c42b4d6b +size 4674251 diff --git a/model/model/layers/7/self_attn/o_proj/kernel/1.0 b/model/model/layers/7/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..b89be1465d9351fad47d11e4998b74556482f126 --- /dev/null +++ b/model/model/layers/7/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29916803982592303d43c0f9c214a5f6ef749486abb245e9b3984389a5c54967 +size 4650733 diff --git a/model/model/layers/7/self_attn/o_proj/kernel/2.0 b/model/model/layers/7/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..893cc6f4e07b6ec625d710c14aec84b5cab10253 --- /dev/null +++ b/model/model/layers/7/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21e681f1e2be9c0ff4ce1a97cbb02270276cc7a332ed2c72daa2f1bd997ec8c3 +size 4665462 diff --git a/model/model/layers/7/self_attn/o_proj/kernel/3.0 b/model/model/layers/7/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..947ca1c86c122d11367eb7fe5779bd3106f7af60 --- /dev/null +++ b/model/model/layers/7/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68a66f5879f2a84efa875400ae555707fbea29960fc8208dc62e28457551cd0f +size 4659216 diff --git a/model/model/layers/7/self_attn/q_proj/bias/.zarray b/model/model/layers/7/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/7/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/self_attn/q_proj/bias/0 b/model/model/layers/7/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..940e54fc9fa60c24ee443f7cdca4fe0e23393d33 Binary files /dev/null and b/model/model/layers/7/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/7/self_attn/q_proj/kernel/.zarray b/model/model/layers/7/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/7/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/self_attn/q_proj/kernel/0.0 b/model/model/layers/7/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..83a5d8e83ecc053add8e3cecdd1da1c7fe4f4c07 --- /dev/null +++ b/model/model/layers/7/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0e69324693d3d4bc48c634be581c34c5cce5528002d1876e3c3aeea6cb2d780 +size 4675772 diff --git a/model/model/layers/7/self_attn/q_proj/kernel/0.1 b/model/model/layers/7/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..9f179b65f6f9db0989c20dd3d302f8ed6883cc86 --- /dev/null +++ b/model/model/layers/7/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f60a74008a2fd56a080e7a1ca871ae38301ce3f95e46fcf11699cdc9ebf1abc2 +size 4663448 diff --git a/model/model/layers/7/self_attn/q_proj/kernel/0.2 b/model/model/layers/7/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..59630607fbdd77591509ec943e3273f3aeea9a64 --- /dev/null +++ b/model/model/layers/7/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d0b9497bcedb9a5bdecdbdd5f15556bc7d1f6c04528865914012389d4351f22 +size 4703958 diff --git a/model/model/layers/7/self_attn/q_proj/kernel/0.3 b/model/model/layers/7/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..6f13824ebd3711527af7b9b5cd04b958f3686ad1 --- /dev/null +++ b/model/model/layers/7/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:332b63d724fca932d11200e04322ec7b7c6f240fd68232b824b7a8953e973638 +size 4663428 diff --git a/model/model/layers/7/self_attn/sinks/.zarray b/model/model/layers/7/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/7/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/self_attn/sinks/0 b/model/model/layers/7/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..dc0eefb551f5e8401673597866c7dc8a6fb922d0 Binary files /dev/null and b/model/model/layers/7/self_attn/sinks/0 differ diff --git a/model/model/layers/7/self_attn/v_proj/bias/.zarray b/model/model/layers/7/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/7/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/self_attn/v_proj/bias/0 b/model/model/layers/7/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..e62ac8a83e485f75d84de997223eba04a8a84045 Binary files /dev/null and b/model/model/layers/7/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/7/self_attn/v_proj/kernel/.zarray b/model/model/layers/7/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/7/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/7/self_attn/v_proj/kernel/0.0 b/model/model/layers/7/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..a1c29a2cec4e57d6caab0ee551668e8d207c1ede --- /dev/null +++ b/model/model/layers/7/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed97ba8096a6573c6005cff0e8cabc5802f048ac444008598f1db1727e0f6f82 +size 578719 diff --git a/model/model/layers/7/self_attn/v_proj/kernel/0.1 b/model/model/layers/7/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..6f5d29240a2dd6d631f4a0cc3ef4c83b7db30cb4 --- /dev/null +++ b/model/model/layers/7/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c32a562c5e35121829d2c43d5c3e838a14cf2f82c5bd29f872cd8b1422e67bb2 +size 579360 diff --git a/model/model/layers/7/self_attn/v_proj/kernel/0.2 b/model/model/layers/7/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..970d22d2e88d755b0bd5e5a8b4cdc0395606f6d6 --- /dev/null +++ b/model/model/layers/7/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74624baad1a8738c014b94b6520a9ceb6898bf7b19171fa470cdecc0f78f20ec +size 579437 diff --git a/model/model/layers/7/self_attn/v_proj/kernel/0.3 b/model/model/layers/7/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..400a011e70eea1c24a0eea30c13fa88d71ea25bf --- /dev/null +++ b/model/model/layers/7/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f069e11a03702da9c07764ef773a53e90129db299ca04e0a5241329da87af490 +size 578423 diff --git a/model/model/layers/8/input_layernorm/kernel/.zarray b/model/model/layers/8/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/8/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/input_layernorm/kernel/0 b/model/model/layers/8/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..75ae1863dabfc3c2fcaad25fea99c621ecbb76a9 Binary files /dev/null and b/model/model/layers/8/input_layernorm/kernel/0 differ diff --git a/model/model/layers/8/mlp/experts/down_proj/bias/.zarray b/model/model/layers/8/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/8/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/mlp/experts/down_proj/bias/0.0 b/model/model/layers/8/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..3dd9934cc17db4d19eb5f7fc5119d11d216ed0f8 --- /dev/null +++ b/model/model/layers/8/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a61a0094fa1e5ed250f8d0b56f5be18fbb23b5d34552d7a2d33bc4eba214ec8 +size 145505 diff --git a/model/model/layers/8/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/8/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/8/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/8/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..5943e49b29037180190bc65889abf7afc95e3fb2 --- /dev/null +++ b/model/model/layers/8/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:168b7929555695c8a63d011c0ec37cd8407a1bdb48b705a32dda3f00ae12b7c2 +size 187420066 diff --git a/model/model/layers/8/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/8/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/8/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/8/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..554d31e4fd375a949efb1f2cfd21d12beadf33e9 --- /dev/null +++ b/model/model/layers/8/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4de180b412b7fc046c87b3e500fe0a19ade54551f2e9c72d01daec345336a63f +size 137478 diff --git a/model/model/layers/8/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/8/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/8/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/8/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..cf8f32c969176961ee1772449d02b8651291e268 --- /dev/null +++ b/model/model/layers/8/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bea9fdcc60770a3b15f402d87f93c9144fe3f802ca8c43a7a2b83984599e30f3 +size 192632880 diff --git a/model/model/layers/8/mlp/experts/up_proj/bias/.zarray b/model/model/layers/8/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/8/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/mlp/experts/up_proj/bias/0.0 b/model/model/layers/8/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..6fc74b2cbe50ab463bff0272d28fe7b495715076 --- /dev/null +++ b/model/model/layers/8/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d102ccce8238edd52a888d34df1a2fcefb661d3b07b5f38724b569b27dfc86f +size 124688 diff --git a/model/model/layers/8/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/8/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/8/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/8/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..487b5ed1499ec04735cc95a2e8729f728ee36e24 --- /dev/null +++ b/model/model/layers/8/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dab8be41c471dc021dab1175e1044df14a88807dcf0d7195a238598befca02b +size 181281617 diff --git a/model/model/layers/8/mlp/router/bias/.zarray b/model/model/layers/8/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/8/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/mlp/router/bias/0 b/model/model/layers/8/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..53dacba2479de088894b53b10873137e8e29638a Binary files /dev/null and b/model/model/layers/8/mlp/router/bias/0 differ diff --git a/model/model/layers/8/mlp/router/kernel/.zarray b/model/model/layers/8/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/8/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/mlp/router/kernel/0.0 b/model/model/layers/8/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..57c8808df88085c51e7e7b0de7ff31fbacddeaf8 --- /dev/null +++ b/model/model/layers/8/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:533ffbe5c8b2a0863970acb08c191c812a7ffd7f618a8ca9d4074e31e0ea8f74 +size 144892 diff --git a/model/model/layers/8/post_attention_layernorm/kernel/.zarray b/model/model/layers/8/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/8/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/post_attention_layernorm/kernel/0 b/model/model/layers/8/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..0eb4ee8d7fd697ad008bd27487d77fe5c369bedc Binary files /dev/null and b/model/model/layers/8/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/8/self_attn/k_proj/bias/.zarray b/model/model/layers/8/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/8/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/self_attn/k_proj/bias/0 b/model/model/layers/8/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/8/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/8/self_attn/k_proj/kernel/.zarray b/model/model/layers/8/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/8/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/self_attn/k_proj/kernel/0.0 b/model/model/layers/8/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..7c0f1283237a471633ac1bbcbe58e3cba7f693b7 --- /dev/null +++ b/model/model/layers/8/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce508d1021fde6fd4380b1c91f1bab1bb127b3adc2a7dd615a833b8efd419cf4 +size 579822 diff --git a/model/model/layers/8/self_attn/k_proj/kernel/0.1 b/model/model/layers/8/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..10399431fa19675b8469c4d6b0d16549269ad824 --- /dev/null +++ b/model/model/layers/8/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd8e524077a9728ce49c9800552735991522489e125643ec5892a7ea3173b0ad +size 582519 diff --git a/model/model/layers/8/self_attn/k_proj/kernel/0.2 b/model/model/layers/8/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..e1111ebceaa8b8199aa308c56ae3cd536d06c852 --- /dev/null +++ b/model/model/layers/8/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:263542ce4585ea82a7ff9e49c65cb18a33f5675f8179210a50350d8fb348f02d +size 579981 diff --git a/model/model/layers/8/self_attn/k_proj/kernel/0.3 b/model/model/layers/8/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..b507006bdadb0ec202e78fe0f8f9d7a92624f5d5 --- /dev/null +++ b/model/model/layers/8/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bd8350ab511d9ffd40ec1a1e6215910d6c333e55bd09fb76f7766a7d09d1eeb +size 579403 diff --git a/model/model/layers/8/self_attn/o_proj/bias/.zarray b/model/model/layers/8/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/8/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/self_attn/o_proj/bias/0 b/model/model/layers/8/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..ab5e9e98e0c687e69b0639845e083d415ed95deb Binary files /dev/null and b/model/model/layers/8/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/8/self_attn/o_proj/kernel/.zarray b/model/model/layers/8/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/8/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/self_attn/o_proj/kernel/0.0 b/model/model/layers/8/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..38f32885c7bb5a21f6ab82796d9b8350d22a8986 --- /dev/null +++ b/model/model/layers/8/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dff9221dbd50179954649734d0b6f7f3c0af3743303a40be6a75b7cbd7f4332 +size 4648303 diff --git a/model/model/layers/8/self_attn/o_proj/kernel/1.0 b/model/model/layers/8/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..ef3f12248315d339e98cf041f645b61f6464cc19 --- /dev/null +++ b/model/model/layers/8/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69b02e1508b6d63204a15e737d629a0799a77f574ba734b8d81b8cac0d4dc240 +size 4644956 diff --git a/model/model/layers/8/self_attn/o_proj/kernel/2.0 b/model/model/layers/8/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..ee0515c0bc1683d14687051e77293a326b774efd --- /dev/null +++ b/model/model/layers/8/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323c11461a96561d43bc08ee621ea8df83c57d04c2c9b9b6155a2502421563b8 +size 4641276 diff --git a/model/model/layers/8/self_attn/o_proj/kernel/3.0 b/model/model/layers/8/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..5463014a04d3dc9ad92bcddb9064e233d31ff3e0 --- /dev/null +++ b/model/model/layers/8/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfb0229d49d239810251bf1476b7cc27a5197c6bd0848e2dfc834bec07e7b556 +size 4635012 diff --git a/model/model/layers/8/self_attn/q_proj/bias/.zarray b/model/model/layers/8/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/8/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/self_attn/q_proj/bias/0 b/model/model/layers/8/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..18aabb6ab05660663cc95f44276e8d5d87d37bae Binary files /dev/null and b/model/model/layers/8/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/8/self_attn/q_proj/kernel/.zarray b/model/model/layers/8/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/8/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/self_attn/q_proj/kernel/0.0 b/model/model/layers/8/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..788a475d93a4f048202e7d300e09249739c930db --- /dev/null +++ b/model/model/layers/8/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:449f94b211ea5195e95d30412eaa8a073db09447a0cd70c2b89b54be611dd443 +size 4661360 diff --git a/model/model/layers/8/self_attn/q_proj/kernel/0.1 b/model/model/layers/8/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..6eccecfec357de644cb55733b34f3faaca081033 --- /dev/null +++ b/model/model/layers/8/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8a924b3ee2fe3de992aded01051a92b59ea6e1ade54e58134f9b64991070e5f +size 4703529 diff --git a/model/model/layers/8/self_attn/q_proj/kernel/0.2 b/model/model/layers/8/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..4739b7ff23c6de2fa3891234c3cb3efda1388383 --- /dev/null +++ b/model/model/layers/8/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e778f7de4d27a51ef7ca628b032ba67cefb8bba523685452af26dd49ef1274a +size 4646354 diff --git a/model/model/layers/8/self_attn/q_proj/kernel/0.3 b/model/model/layers/8/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..d4139a259d6c49a4de27845b746ffd3ab34651f0 --- /dev/null +++ b/model/model/layers/8/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4eaac9c8845757c72ef9133b90125a26c5c13c120232609718524464517ffc0 +size 4655511 diff --git a/model/model/layers/8/self_attn/sinks/.zarray b/model/model/layers/8/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/8/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/self_attn/sinks/0 b/model/model/layers/8/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..8b2e1e1d5efeb0406dc6054648fdd2f81e58a89e Binary files /dev/null and b/model/model/layers/8/self_attn/sinks/0 differ diff --git a/model/model/layers/8/self_attn/v_proj/bias/.zarray b/model/model/layers/8/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/8/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/self_attn/v_proj/bias/0 b/model/model/layers/8/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..090a55b185fe441b8d8c5aff3e00ab3491460232 Binary files /dev/null and b/model/model/layers/8/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/8/self_attn/v_proj/kernel/.zarray b/model/model/layers/8/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/8/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/8/self_attn/v_proj/kernel/0.0 b/model/model/layers/8/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..8cdeb2e9970c92aac26e06f5982dd587680d9724 --- /dev/null +++ b/model/model/layers/8/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d5a6c08639af8f8e804eb962e819cb1af3b4b6cd86ee9e1f5a5f9948ffe4757 +size 577313 diff --git a/model/model/layers/8/self_attn/v_proj/kernel/0.1 b/model/model/layers/8/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..e37ca74d6b70d4efebb70389477d25968843ff2c --- /dev/null +++ b/model/model/layers/8/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:121e6e19f205217b4f6a4772d7af6dbc07236b051047f14583f7120821b8cc43 +size 578774 diff --git a/model/model/layers/8/self_attn/v_proj/kernel/0.2 b/model/model/layers/8/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..1b3699242d733d5e6d9901d4e4c618b3f99c8224 --- /dev/null +++ b/model/model/layers/8/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c77cc38b64d5fbe2ca3c845703b449288bf40bcd74ce79484fbae14018a8f8f9 +size 577614 diff --git a/model/model/layers/8/self_attn/v_proj/kernel/0.3 b/model/model/layers/8/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..176d84a330e7015264d4b54beee409ed57ee139c --- /dev/null +++ b/model/model/layers/8/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22894c0f53411a37a13233c6f48473ebb8134448d06465c5fd601f3e1b5980b8 +size 578946 diff --git a/model/model/layers/9/input_layernorm/kernel/.zarray b/model/model/layers/9/input_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/9/input_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/input_layernorm/kernel/0 b/model/model/layers/9/input_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..80008ddaed621a0618c4da18b7d3a7bae5fedd10 Binary files /dev/null and b/model/model/layers/9/input_layernorm/kernel/0 differ diff --git a/model/model/layers/9/mlp/experts/down_proj/bias/.zarray b/model/model/layers/9/mlp/experts/down_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/9/mlp/experts/down_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/mlp/experts/down_proj/bias/0.0 b/model/model/layers/9/mlp/experts/down_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..3a3125962dee3a76c57b033147798c001a2a4030 --- /dev/null +++ b/model/model/layers/9/mlp/experts/down_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55d13f91458e813f0e01e9e4bf203c0d0fb3d33d3cfe300b014247e34ba624aa +size 144694 diff --git a/model/model/layers/9/mlp/experts/down_proj/kernel/.zarray b/model/model/layers/9/mlp/experts/down_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/9/mlp/experts/down_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/mlp/experts/down_proj/kernel/0.0.0 b/model/model/layers/9/mlp/experts/down_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..e761ddecf81df931433c3797f78d4b7b8e5584b9 --- /dev/null +++ b/model/model/layers/9/mlp/experts/down_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:737ac945aaf3d45af85c27251721f6818ea91480d3234697884b48c1e7d980de +size 184891007 diff --git a/model/model/layers/9/mlp/experts/gate_proj/bias/.zarray b/model/model/layers/9/mlp/experts/gate_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/9/mlp/experts/gate_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/mlp/experts/gate_proj/bias/0.0 b/model/model/layers/9/mlp/experts/gate_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..ddab3ce99da19e2c112de56009125a49153d8354 --- /dev/null +++ b/model/model/layers/9/mlp/experts/gate_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9bb89db765e64365b2f416b0120d2196962029384deca187c1ea617620c8c2e +size 138928 diff --git a/model/model/layers/9/mlp/experts/gate_proj/kernel/.zarray b/model/model/layers/9/mlp/experts/gate_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/9/mlp/experts/gate_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/mlp/experts/gate_proj/kernel/0.0.0 b/model/model/layers/9/mlp/experts/gate_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..adb8131118d951f18b35c72bc78f8d52a1b62711 --- /dev/null +++ b/model/model/layers/9/mlp/experts/gate_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d4e2d223653aa15bdbb3785a5eb45e67f142e894445dd94099fb3659176c669 +size 193814106 diff --git a/model/model/layers/9/mlp/experts/up_proj/bias/.zarray b/model/model/layers/9/mlp/experts/up_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a701bdfb4b6dba91e0301e5dadc2d03dd8dfa994 --- /dev/null +++ b/model/model/layers/9/mlp/experts/up_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/mlp/experts/up_proj/bias/0.0 b/model/model/layers/9/mlp/experts/up_proj/bias/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..713f184029587cce0717f9e11aca08f19a0e738d --- /dev/null +++ b/model/model/layers/9/mlp/experts/up_proj/bias/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8db0bd58e178404d1510c83f4b27cb04ddb63459a2e37dfa60936ee900ae3f59 +size 126231 diff --git a/model/model/layers/9/mlp/experts/up_proj/kernel/.zarray b/model/model/layers/9/mlp/experts/up_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6f440124d59d06538074f0d08099b3ef675a3e2b --- /dev/null +++ b/model/model/layers/9/mlp/experts/up_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[32,2880,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32,2880,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/mlp/experts/up_proj/kernel/0.0.0 b/model/model/layers/9/mlp/experts/up_proj/kernel/0.0.0 new file mode 100644 index 0000000000000000000000000000000000000000..fca13dfeafeca1b6560bd653576acc340444bd0a --- /dev/null +++ b/model/model/layers/9/mlp/experts/up_proj/kernel/0.0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40b2f7f773e10755ec7251875f9c94a6737a3a762fbfd187101213b339765c6b +size 182311424 diff --git a/model/model/layers/9/mlp/router/bias/.zarray b/model/model/layers/9/mlp/router/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..27b136e09a02238bcf70d174848d0e86a714bd2d --- /dev/null +++ b/model/model/layers/9/mlp/router/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/mlp/router/bias/0 b/model/model/layers/9/mlp/router/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..88d9cd2200799b1cc58afd2abf8e00842e2f8591 Binary files /dev/null and b/model/model/layers/9/mlp/router/bias/0 differ diff --git a/model/model/layers/9/mlp/router/kernel/.zarray b/model/model/layers/9/mlp/router/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..663c6e6100f77f739bf91a6b7caa8276da6ea3f4 --- /dev/null +++ b/model/model/layers/9/mlp/router/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,32],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,32],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/mlp/router/kernel/0.0 b/model/model/layers/9/mlp/router/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..f398d187e655a60ec82a339a44ad25b25f25fcff --- /dev/null +++ b/model/model/layers/9/mlp/router/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51afa72ebf606996e8b7b0f24edaffe2e4562d54ed39c65d8504307d2dff34b2 +size 144873 diff --git a/model/model/layers/9/post_attention_layernorm/kernel/.zarray b/model/model/layers/9/post_attention_layernorm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/9/post_attention_layernorm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/post_attention_layernorm/kernel/0 b/model/model/layers/9/post_attention_layernorm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..2ba4217dc6c66ce2306cc2fe0d0054d81d6cebcd Binary files /dev/null and b/model/model/layers/9/post_attention_layernorm/kernel/0 differ diff --git a/model/model/layers/9/self_attn/k_proj/bias/.zarray b/model/model/layers/9/self_attn/k_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/9/self_attn/k_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/self_attn/k_proj/bias/0 b/model/model/layers/9/self_attn/k_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..a7be141c25d5282d2d2d0c3ed8ea25371293b837 Binary files /dev/null and b/model/model/layers/9/self_attn/k_proj/bias/0 differ diff --git a/model/model/layers/9/self_attn/k_proj/kernel/.zarray b/model/model/layers/9/self_attn/k_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/9/self_attn/k_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/self_attn/k_proj/kernel/0.0 b/model/model/layers/9/self_attn/k_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..c99f8d66edb3fc24d748cce2bc0ea58b054dd930 --- /dev/null +++ b/model/model/layers/9/self_attn/k_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:417801c40a4e88d01af72a854f90db83749a31a97c626eebe5dc6c64f98030e0 +size 585716 diff --git a/model/model/layers/9/self_attn/k_proj/kernel/0.1 b/model/model/layers/9/self_attn/k_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..3c914e3b7f70c4f6301e09812e20a9055700eb38 --- /dev/null +++ b/model/model/layers/9/self_attn/k_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b2b0372e9a2636513116d32cb130efb45953a20108a369be165983a0f269eb1 +size 588055 diff --git a/model/model/layers/9/self_attn/k_proj/kernel/0.2 b/model/model/layers/9/self_attn/k_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..2a329e30cdd9eae848e168881a5b92aaad301133 --- /dev/null +++ b/model/model/layers/9/self_attn/k_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:909e719881d5af8efa2149f5ba459a6ede13b3e61b0c886c42ee3e1092b891e9 +size 587177 diff --git a/model/model/layers/9/self_attn/k_proj/kernel/0.3 b/model/model/layers/9/self_attn/k_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..b96ca646e8f782f41b64d72aa0bd910b446a9bb2 --- /dev/null +++ b/model/model/layers/9/self_attn/k_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03fa410492465c6b1d1630832c4f57b705929285d774dea6370c16c1a7e03048 +size 597285 diff --git a/model/model/layers/9/self_attn/o_proj/bias/.zarray b/model/model/layers/9/self_attn/o_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/layers/9/self_attn/o_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/self_attn/o_proj/bias/0 b/model/model/layers/9/self_attn/o_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..cd731062e6abb4b2c0b6bf7824bdab4226214113 Binary files /dev/null and b/model/model/layers/9/self_attn/o_proj/bias/0 differ diff --git a/model/model/layers/9/self_attn/o_proj/kernel/.zarray b/model/model/layers/9/self_attn/o_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..c6e983987e73251ab61b458fe6a17f30f9da0708 --- /dev/null +++ b/model/model/layers/9/self_attn/o_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[1024,2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096,2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/self_attn/o_proj/kernel/0.0 b/model/model/layers/9/self_attn/o_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..96ed238ae253593fbda850f610df39e5e2be10ae --- /dev/null +++ b/model/model/layers/9/self_attn/o_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14f5854c9fc3132223787b116d388659c3c5457ad201b53118b0a7c36920ddba +size 4640716 diff --git a/model/model/layers/9/self_attn/o_proj/kernel/1.0 b/model/model/layers/9/self_attn/o_proj/kernel/1.0 new file mode 100644 index 0000000000000000000000000000000000000000..582cb8de59699e470e50f3e660e7c4808fec5ee5 --- /dev/null +++ b/model/model/layers/9/self_attn/o_proj/kernel/1.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a24eb1bdd86526d812ede45d737f5e02866e3b695b95a6f7596b0fd726879f8 +size 4647898 diff --git a/model/model/layers/9/self_attn/o_proj/kernel/2.0 b/model/model/layers/9/self_attn/o_proj/kernel/2.0 new file mode 100644 index 0000000000000000000000000000000000000000..69500216aaf49217f0a38cb256b4e44428b50fa7 --- /dev/null +++ b/model/model/layers/9/self_attn/o_proj/kernel/2.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e45594c41b0d7e64ea791d8367346b84b73bac306f5afa2aadb8f0574da2720d +size 4642668 diff --git a/model/model/layers/9/self_attn/o_proj/kernel/3.0 b/model/model/layers/9/self_attn/o_proj/kernel/3.0 new file mode 100644 index 0000000000000000000000000000000000000000..f95dd9902c02a0cf7e6b44747a1a2950752c862e --- /dev/null +++ b/model/model/layers/9/self_attn/o_proj/kernel/3.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:677cd1f357670c27e84a4881201fa5ce788ba6b90278c314df4511fbd001ffde +size 4648376 diff --git a/model/model/layers/9/self_attn/q_proj/bias/.zarray b/model/model/layers/9/self_attn/q_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..6cb36eccfd612cd6d39e72807aaa8527aa28075d --- /dev/null +++ b/model/model/layers/9/self_attn/q_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[4096],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/self_attn/q_proj/bias/0 b/model/model/layers/9/self_attn/q_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..736097a6529a561d5cbdd535ac87a0b1495c4e98 Binary files /dev/null and b/model/model/layers/9/self_attn/q_proj/bias/0 differ diff --git a/model/model/layers/9/self_attn/q_proj/kernel/.zarray b/model/model/layers/9/self_attn/q_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..dea5cc5e2daa703e3f4feec5e6253531f3931d84 --- /dev/null +++ b/model/model/layers/9/self_attn/q_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,1024],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,4096],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/self_attn/q_proj/kernel/0.0 b/model/model/layers/9/self_attn/q_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..01d9ac327f79d95bf0677bbb51e1f88ff1f03e13 --- /dev/null +++ b/model/model/layers/9/self_attn/q_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:005fc7f6d08f54f6b37528eb825e82e70a821d46ecd2749b554f31d2d472ba71 +size 4656159 diff --git a/model/model/layers/9/self_attn/q_proj/kernel/0.1 b/model/model/layers/9/self_attn/q_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..964ef6b3702126fbe92d33e7b309890f515c36a2 --- /dev/null +++ b/model/model/layers/9/self_attn/q_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2428646ef9a3be3616d2f4281c7014502ba7b6b7b38bcdc088f4d0c6ec72ffbe +size 4651720 diff --git a/model/model/layers/9/self_attn/q_proj/kernel/0.2 b/model/model/layers/9/self_attn/q_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..e8e088b2d144e4607d1ccd3baa974bba090b365e --- /dev/null +++ b/model/model/layers/9/self_attn/q_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:539c57a2986d0a890475cdb03a9a50b43cac4dfb963e988364523ba59fabb629 +size 4677277 diff --git a/model/model/layers/9/self_attn/q_proj/kernel/0.3 b/model/model/layers/9/self_attn/q_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..b36939ad16247145d58962d24d8ed524ab7320de --- /dev/null +++ b/model/model/layers/9/self_attn/q_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e613f7cda9e486113a76feb050332509fc6f641c40a3b3489832882696f801e +size 4709790 diff --git a/model/model/layers/9/self_attn/sinks/.zarray b/model/model/layers/9/self_attn/sinks/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..75fb6ffa552a3ab35caf4dd9123b81fce2aa7eaa --- /dev/null +++ b/model/model/layers/9/self_attn/sinks/.zarray @@ -0,0 +1 @@ +{"chunks":[64],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[64],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/self_attn/sinks/0 b/model/model/layers/9/self_attn/sinks/0 new file mode 100644 index 0000000000000000000000000000000000000000..5bf13c5166d2cc0f7aaf9910d3f906d30719c193 Binary files /dev/null and b/model/model/layers/9/self_attn/sinks/0 differ diff --git a/model/model/layers/9/self_attn/v_proj/bias/.zarray b/model/model/layers/9/self_attn/v_proj/bias/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..82cda9219c678aba952afd8b130fd0430cff4770 --- /dev/null +++ b/model/model/layers/9/self_attn/v_proj/bias/.zarray @@ -0,0 +1 @@ +{"chunks":[512],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/self_attn/v_proj/bias/0 b/model/model/layers/9/self_attn/v_proj/bias/0 new file mode 100644 index 0000000000000000000000000000000000000000..73da2e410c8fc0207088409784b9f755645ddbf8 Binary files /dev/null and b/model/model/layers/9/self_attn/v_proj/bias/0 differ diff --git a/model/model/layers/9/self_attn/v_proj/kernel/.zarray b/model/model/layers/9/self_attn/v_proj/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..231cd5a292062df57f49aa96a5b9f10317e49377 --- /dev/null +++ b/model/model/layers/9/self_attn/v_proj/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880,128],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880,512],"zarr_format":2} \ No newline at end of file diff --git a/model/model/layers/9/self_attn/v_proj/kernel/0.0 b/model/model/layers/9/self_attn/v_proj/kernel/0.0 new file mode 100644 index 0000000000000000000000000000000000000000..ba1f4f3ba7f1ced88d9be3a68590153bf21936c7 --- /dev/null +++ b/model/model/layers/9/self_attn/v_proj/kernel/0.0 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb3c644c90a78cdb5e419545cb0c9541927eb34325df3ac2e4783f4b6c52b04c +size 581160 diff --git a/model/model/layers/9/self_attn/v_proj/kernel/0.1 b/model/model/layers/9/self_attn/v_proj/kernel/0.1 new file mode 100644 index 0000000000000000000000000000000000000000..834bde7e22fc01edcad4135f6ce42a7bb702ba17 --- /dev/null +++ b/model/model/layers/9/self_attn/v_proj/kernel/0.1 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b05e62485d12887bc93e4531a4153c2e18b7e70bac726ec5bc1097e0af8ae6a0 +size 579373 diff --git a/model/model/layers/9/self_attn/v_proj/kernel/0.2 b/model/model/layers/9/self_attn/v_proj/kernel/0.2 new file mode 100644 index 0000000000000000000000000000000000000000..905a32b4e62b950282d2195c382829976220533c --- /dev/null +++ b/model/model/layers/9/self_attn/v_proj/kernel/0.2 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3158d3ed98fe9b6051adb305b2b90f42f04c3aa549662771d407a235a54bbd6f +size 580961 diff --git a/model/model/layers/9/self_attn/v_proj/kernel/0.3 b/model/model/layers/9/self_attn/v_proj/kernel/0.3 new file mode 100644 index 0000000000000000000000000000000000000000..86ad3503993a8cc3382143bce6c7cf3f46018423 --- /dev/null +++ b/model/model/layers/9/self_attn/v_proj/kernel/0.3 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd877f599e437222a34d90213fe220a9348818eb51df53d618720d77a2fc6bc4 +size 585587 diff --git a/model/model/norm/kernel/.zarray b/model/model/norm/kernel/.zarray new file mode 100644 index 0000000000000000000000000000000000000000..a6b4a137bbd7791e040a35594e3226e4b578df4d --- /dev/null +++ b/model/model/norm/kernel/.zarray @@ -0,0 +1 @@ +{"chunks":[2880],"compressor":{"id":"zstd","level":1},"dimension_separator":".","dtype":"bfloat16","fill_value":null,"filters":null,"order":"C","shape":[2880],"zarr_format":2} \ No newline at end of file diff --git a/model/model/norm/kernel/0 b/model/model/norm/kernel/0 new file mode 100644 index 0000000000000000000000000000000000000000..2589fed6065537e2010d8cbbd072df6f56579c60 Binary files /dev/null and b/model/model/norm/kernel/0 differ diff --git a/model_structure.json b/model_structure.json new file mode 100644 index 0000000000000000000000000000000000000000..eb3bb1807227a6f99e76ada8e8669b1a4cc45967 --- /dev/null +++ b/model_structure.json @@ -0,0 +1,1854 @@ +{ + "format": "pytree-structure", + "version": "0.0.84", + "backend": "tensorstore", + "prefix": "model", + "treedef_b64": "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", + "leaf_keys_full": [ + "model.lm_head.kernel", + "model.model.embed_tokens.embedding", + "model.model.layers.0.input_layernorm.kernel", + "model.model.layers.0.mlp.experts.down_proj.bias", + "model.model.layers.0.mlp.experts.down_proj.kernel", + "model.model.layers.0.mlp.experts.gate_proj.bias", + "model.model.layers.0.mlp.experts.gate_proj.kernel", + "model.model.layers.0.mlp.experts.up_proj.bias", + "model.model.layers.0.mlp.experts.up_proj.kernel", + "model.model.layers.0.mlp.router.bias", + "model.model.layers.0.mlp.router.kernel", + "model.model.layers.0.post_attention_layernorm.kernel", + "model.model.layers.0.self_attn.k_proj.bias", + "model.model.layers.0.self_attn.k_proj.kernel", + "model.model.layers.0.self_attn.o_proj.bias", + "model.model.layers.0.self_attn.o_proj.kernel", + "model.model.layers.0.self_attn.q_proj.bias", + "model.model.layers.0.self_attn.q_proj.kernel", + "model.model.layers.0.self_attn.sinks", + "model.model.layers.0.self_attn.v_proj.bias", + "model.model.layers.0.self_attn.v_proj.kernel", + "model.model.layers.1.input_layernorm.kernel", + "model.model.layers.1.mlp.experts.down_proj.bias", + "model.model.layers.1.mlp.experts.down_proj.kernel", + "model.model.layers.1.mlp.experts.gate_proj.bias", + "model.model.layers.1.mlp.experts.gate_proj.kernel", + "model.model.layers.1.mlp.experts.up_proj.bias", + "model.model.layers.1.mlp.experts.up_proj.kernel", + "model.model.layers.1.mlp.router.bias", + "model.model.layers.1.mlp.router.kernel", + "model.model.layers.1.post_attention_layernorm.kernel", + "model.model.layers.1.self_attn.k_proj.bias", + "model.model.layers.1.self_attn.k_proj.kernel", + "model.model.layers.1.self_attn.o_proj.bias", + "model.model.layers.1.self_attn.o_proj.kernel", + "model.model.layers.1.self_attn.q_proj.bias", + "model.model.layers.1.self_attn.q_proj.kernel", + "model.model.layers.1.self_attn.sinks", + "model.model.layers.1.self_attn.v_proj.bias", + "model.model.layers.1.self_attn.v_proj.kernel", + "model.model.layers.2.input_layernorm.kernel", + "model.model.layers.2.mlp.experts.down_proj.bias", + "model.model.layers.2.mlp.experts.down_proj.kernel", + "model.model.layers.2.mlp.experts.gate_proj.bias", + "model.model.layers.2.mlp.experts.gate_proj.kernel", + "model.model.layers.2.mlp.experts.up_proj.bias", + "model.model.layers.2.mlp.experts.up_proj.kernel", + "model.model.layers.2.mlp.router.bias", + "model.model.layers.2.mlp.router.kernel", + "model.model.layers.2.post_attention_layernorm.kernel", + "model.model.layers.2.self_attn.k_proj.bias", + "model.model.layers.2.self_attn.k_proj.kernel", + "model.model.layers.2.self_attn.o_proj.bias", + "model.model.layers.2.self_attn.o_proj.kernel", + "model.model.layers.2.self_attn.q_proj.bias", + "model.model.layers.2.self_attn.q_proj.kernel", + "model.model.layers.2.self_attn.sinks", + "model.model.layers.2.self_attn.v_proj.bias", + "model.model.layers.2.self_attn.v_proj.kernel", + "model.model.layers.3.input_layernorm.kernel", + "model.model.layers.3.mlp.experts.down_proj.bias", + "model.model.layers.3.mlp.experts.down_proj.kernel", + "model.model.layers.3.mlp.experts.gate_proj.bias", + "model.model.layers.3.mlp.experts.gate_proj.kernel", + "model.model.layers.3.mlp.experts.up_proj.bias", + "model.model.layers.3.mlp.experts.up_proj.kernel", + "model.model.layers.3.mlp.router.bias", + "model.model.layers.3.mlp.router.kernel", + "model.model.layers.3.post_attention_layernorm.kernel", + "model.model.layers.3.self_attn.k_proj.bias", + "model.model.layers.3.self_attn.k_proj.kernel", + "model.model.layers.3.self_attn.o_proj.bias", + "model.model.layers.3.self_attn.o_proj.kernel", + "model.model.layers.3.self_attn.q_proj.bias", + "model.model.layers.3.self_attn.q_proj.kernel", + "model.model.layers.3.self_attn.sinks", + "model.model.layers.3.self_attn.v_proj.bias", + "model.model.layers.3.self_attn.v_proj.kernel", + "model.model.layers.4.input_layernorm.kernel", + "model.model.layers.4.mlp.experts.down_proj.bias", + "model.model.layers.4.mlp.experts.down_proj.kernel", + "model.model.layers.4.mlp.experts.gate_proj.bias", + "model.model.layers.4.mlp.experts.gate_proj.kernel", + "model.model.layers.4.mlp.experts.up_proj.bias", + "model.model.layers.4.mlp.experts.up_proj.kernel", + "model.model.layers.4.mlp.router.bias", + "model.model.layers.4.mlp.router.kernel", + "model.model.layers.4.post_attention_layernorm.kernel", + "model.model.layers.4.self_attn.k_proj.bias", + "model.model.layers.4.self_attn.k_proj.kernel", + "model.model.layers.4.self_attn.o_proj.bias", + "model.model.layers.4.self_attn.o_proj.kernel", + "model.model.layers.4.self_attn.q_proj.bias", + "model.model.layers.4.self_attn.q_proj.kernel", + "model.model.layers.4.self_attn.sinks", + "model.model.layers.4.self_attn.v_proj.bias", + "model.model.layers.4.self_attn.v_proj.kernel", + "model.model.layers.5.input_layernorm.kernel", + "model.model.layers.5.mlp.experts.down_proj.bias", + "model.model.layers.5.mlp.experts.down_proj.kernel", + "model.model.layers.5.mlp.experts.gate_proj.bias", + "model.model.layers.5.mlp.experts.gate_proj.kernel", + "model.model.layers.5.mlp.experts.up_proj.bias", + "model.model.layers.5.mlp.experts.up_proj.kernel", + "model.model.layers.5.mlp.router.bias", + "model.model.layers.5.mlp.router.kernel", + "model.model.layers.5.post_attention_layernorm.kernel", + "model.model.layers.5.self_attn.k_proj.bias", + "model.model.layers.5.self_attn.k_proj.kernel", + "model.model.layers.5.self_attn.o_proj.bias", + "model.model.layers.5.self_attn.o_proj.kernel", + "model.model.layers.5.self_attn.q_proj.bias", + "model.model.layers.5.self_attn.q_proj.kernel", + "model.model.layers.5.self_attn.sinks", + "model.model.layers.5.self_attn.v_proj.bias", + "model.model.layers.5.self_attn.v_proj.kernel", + "model.model.layers.6.input_layernorm.kernel", + "model.model.layers.6.mlp.experts.down_proj.bias", + "model.model.layers.6.mlp.experts.down_proj.kernel", + "model.model.layers.6.mlp.experts.gate_proj.bias", + "model.model.layers.6.mlp.experts.gate_proj.kernel", + "model.model.layers.6.mlp.experts.up_proj.bias", + "model.model.layers.6.mlp.experts.up_proj.kernel", + "model.model.layers.6.mlp.router.bias", + "model.model.layers.6.mlp.router.kernel", + "model.model.layers.6.post_attention_layernorm.kernel", + "model.model.layers.6.self_attn.k_proj.bias", + "model.model.layers.6.self_attn.k_proj.kernel", + "model.model.layers.6.self_attn.o_proj.bias", + "model.model.layers.6.self_attn.o_proj.kernel", + "model.model.layers.6.self_attn.q_proj.bias", + "model.model.layers.6.self_attn.q_proj.kernel", + "model.model.layers.6.self_attn.sinks", + "model.model.layers.6.self_attn.v_proj.bias", + "model.model.layers.6.self_attn.v_proj.kernel", + "model.model.layers.7.input_layernorm.kernel", + "model.model.layers.7.mlp.experts.down_proj.bias", + "model.model.layers.7.mlp.experts.down_proj.kernel", + "model.model.layers.7.mlp.experts.gate_proj.bias", + "model.model.layers.7.mlp.experts.gate_proj.kernel", + "model.model.layers.7.mlp.experts.up_proj.bias", + "model.model.layers.7.mlp.experts.up_proj.kernel", + "model.model.layers.7.mlp.router.bias", + "model.model.layers.7.mlp.router.kernel", + "model.model.layers.7.post_attention_layernorm.kernel", + "model.model.layers.7.self_attn.k_proj.bias", + "model.model.layers.7.self_attn.k_proj.kernel", + "model.model.layers.7.self_attn.o_proj.bias", + "model.model.layers.7.self_attn.o_proj.kernel", + "model.model.layers.7.self_attn.q_proj.bias", + "model.model.layers.7.self_attn.q_proj.kernel", + "model.model.layers.7.self_attn.sinks", + "model.model.layers.7.self_attn.v_proj.bias", + "model.model.layers.7.self_attn.v_proj.kernel", + "model.model.layers.8.input_layernorm.kernel", + "model.model.layers.8.mlp.experts.down_proj.bias", + "model.model.layers.8.mlp.experts.down_proj.kernel", + "model.model.layers.8.mlp.experts.gate_proj.bias", + "model.model.layers.8.mlp.experts.gate_proj.kernel", + "model.model.layers.8.mlp.experts.up_proj.bias", + "model.model.layers.8.mlp.experts.up_proj.kernel", + "model.model.layers.8.mlp.router.bias", + "model.model.layers.8.mlp.router.kernel", + "model.model.layers.8.post_attention_layernorm.kernel", + "model.model.layers.8.self_attn.k_proj.bias", + "model.model.layers.8.self_attn.k_proj.kernel", + "model.model.layers.8.self_attn.o_proj.bias", + "model.model.layers.8.self_attn.o_proj.kernel", + "model.model.layers.8.self_attn.q_proj.bias", + "model.model.layers.8.self_attn.q_proj.kernel", + "model.model.layers.8.self_attn.sinks", + "model.model.layers.8.self_attn.v_proj.bias", + "model.model.layers.8.self_attn.v_proj.kernel", + "model.model.layers.9.input_layernorm.kernel", + "model.model.layers.9.mlp.experts.down_proj.bias", + "model.model.layers.9.mlp.experts.down_proj.kernel", + "model.model.layers.9.mlp.experts.gate_proj.bias", + "model.model.layers.9.mlp.experts.gate_proj.kernel", + "model.model.layers.9.mlp.experts.up_proj.bias", + "model.model.layers.9.mlp.experts.up_proj.kernel", + "model.model.layers.9.mlp.router.bias", + "model.model.layers.9.mlp.router.kernel", + "model.model.layers.9.post_attention_layernorm.kernel", + "model.model.layers.9.self_attn.k_proj.bias", + "model.model.layers.9.self_attn.k_proj.kernel", + "model.model.layers.9.self_attn.o_proj.bias", + "model.model.layers.9.self_attn.o_proj.kernel", + "model.model.layers.9.self_attn.q_proj.bias", + "model.model.layers.9.self_attn.q_proj.kernel", + "model.model.layers.9.self_attn.sinks", + "model.model.layers.9.self_attn.v_proj.bias", + "model.model.layers.9.self_attn.v_proj.kernel", + "model.model.layers.10.input_layernorm.kernel", + "model.model.layers.10.mlp.experts.down_proj.bias", + "model.model.layers.10.mlp.experts.down_proj.kernel", + "model.model.layers.10.mlp.experts.gate_proj.bias", + "model.model.layers.10.mlp.experts.gate_proj.kernel", + "model.model.layers.10.mlp.experts.up_proj.bias", + "model.model.layers.10.mlp.experts.up_proj.kernel", + "model.model.layers.10.mlp.router.bias", + "model.model.layers.10.mlp.router.kernel", + "model.model.layers.10.post_attention_layernorm.kernel", + "model.model.layers.10.self_attn.k_proj.bias", + "model.model.layers.10.self_attn.k_proj.kernel", + "model.model.layers.10.self_attn.o_proj.bias", + "model.model.layers.10.self_attn.o_proj.kernel", + "model.model.layers.10.self_attn.q_proj.bias", + "model.model.layers.10.self_attn.q_proj.kernel", + "model.model.layers.10.self_attn.sinks", + "model.model.layers.10.self_attn.v_proj.bias", + "model.model.layers.10.self_attn.v_proj.kernel", + "model.model.layers.11.input_layernorm.kernel", + "model.model.layers.11.mlp.experts.down_proj.bias", + "model.model.layers.11.mlp.experts.down_proj.kernel", + "model.model.layers.11.mlp.experts.gate_proj.bias", + "model.model.layers.11.mlp.experts.gate_proj.kernel", + "model.model.layers.11.mlp.experts.up_proj.bias", + "model.model.layers.11.mlp.experts.up_proj.kernel", + "model.model.layers.11.mlp.router.bias", + "model.model.layers.11.mlp.router.kernel", + "model.model.layers.11.post_attention_layernorm.kernel", + "model.model.layers.11.self_attn.k_proj.bias", + "model.model.layers.11.self_attn.k_proj.kernel", + "model.model.layers.11.self_attn.o_proj.bias", + "model.model.layers.11.self_attn.o_proj.kernel", + "model.model.layers.11.self_attn.q_proj.bias", + "model.model.layers.11.self_attn.q_proj.kernel", + "model.model.layers.11.self_attn.sinks", + "model.model.layers.11.self_attn.v_proj.bias", + "model.model.layers.11.self_attn.v_proj.kernel", + "model.model.layers.12.input_layernorm.kernel", + "model.model.layers.12.mlp.experts.down_proj.bias", + "model.model.layers.12.mlp.experts.down_proj.kernel", + "model.model.layers.12.mlp.experts.gate_proj.bias", + "model.model.layers.12.mlp.experts.gate_proj.kernel", + "model.model.layers.12.mlp.experts.up_proj.bias", + "model.model.layers.12.mlp.experts.up_proj.kernel", + "model.model.layers.12.mlp.router.bias", + "model.model.layers.12.mlp.router.kernel", + "model.model.layers.12.post_attention_layernorm.kernel", + "model.model.layers.12.self_attn.k_proj.bias", + "model.model.layers.12.self_attn.k_proj.kernel", + "model.model.layers.12.self_attn.o_proj.bias", + "model.model.layers.12.self_attn.o_proj.kernel", + "model.model.layers.12.self_attn.q_proj.bias", + "model.model.layers.12.self_attn.q_proj.kernel", + "model.model.layers.12.self_attn.sinks", + "model.model.layers.12.self_attn.v_proj.bias", + "model.model.layers.12.self_attn.v_proj.kernel", + "model.model.layers.13.input_layernorm.kernel", + "model.model.layers.13.mlp.experts.down_proj.bias", + "model.model.layers.13.mlp.experts.down_proj.kernel", + "model.model.layers.13.mlp.experts.gate_proj.bias", + "model.model.layers.13.mlp.experts.gate_proj.kernel", + "model.model.layers.13.mlp.experts.up_proj.bias", + "model.model.layers.13.mlp.experts.up_proj.kernel", + "model.model.layers.13.mlp.router.bias", + "model.model.layers.13.mlp.router.kernel", + "model.model.layers.13.post_attention_layernorm.kernel", + "model.model.layers.13.self_attn.k_proj.bias", + "model.model.layers.13.self_attn.k_proj.kernel", + "model.model.layers.13.self_attn.o_proj.bias", + "model.model.layers.13.self_attn.o_proj.kernel", + "model.model.layers.13.self_attn.q_proj.bias", + "model.model.layers.13.self_attn.q_proj.kernel", + "model.model.layers.13.self_attn.sinks", + "model.model.layers.13.self_attn.v_proj.bias", + "model.model.layers.13.self_attn.v_proj.kernel", + "model.model.layers.14.input_layernorm.kernel", + "model.model.layers.14.mlp.experts.down_proj.bias", + "model.model.layers.14.mlp.experts.down_proj.kernel", + "model.model.layers.14.mlp.experts.gate_proj.bias", + "model.model.layers.14.mlp.experts.gate_proj.kernel", + "model.model.layers.14.mlp.experts.up_proj.bias", + "model.model.layers.14.mlp.experts.up_proj.kernel", + "model.model.layers.14.mlp.router.bias", + "model.model.layers.14.mlp.router.kernel", + "model.model.layers.14.post_attention_layernorm.kernel", + "model.model.layers.14.self_attn.k_proj.bias", + "model.model.layers.14.self_attn.k_proj.kernel", + "model.model.layers.14.self_attn.o_proj.bias", + "model.model.layers.14.self_attn.o_proj.kernel", + "model.model.layers.14.self_attn.q_proj.bias", + "model.model.layers.14.self_attn.q_proj.kernel", + "model.model.layers.14.self_attn.sinks", + "model.model.layers.14.self_attn.v_proj.bias", + "model.model.layers.14.self_attn.v_proj.kernel", + "model.model.layers.15.input_layernorm.kernel", + "model.model.layers.15.mlp.experts.down_proj.bias", + "model.model.layers.15.mlp.experts.down_proj.kernel", + "model.model.layers.15.mlp.experts.gate_proj.bias", + "model.model.layers.15.mlp.experts.gate_proj.kernel", + "model.model.layers.15.mlp.experts.up_proj.bias", + "model.model.layers.15.mlp.experts.up_proj.kernel", + "model.model.layers.15.mlp.router.bias", + "model.model.layers.15.mlp.router.kernel", + "model.model.layers.15.post_attention_layernorm.kernel", + "model.model.layers.15.self_attn.k_proj.bias", + "model.model.layers.15.self_attn.k_proj.kernel", + "model.model.layers.15.self_attn.o_proj.bias", + "model.model.layers.15.self_attn.o_proj.kernel", + "model.model.layers.15.self_attn.q_proj.bias", + "model.model.layers.15.self_attn.q_proj.kernel", + "model.model.layers.15.self_attn.sinks", + "model.model.layers.15.self_attn.v_proj.bias", + "model.model.layers.15.self_attn.v_proj.kernel", + "model.model.layers.16.input_layernorm.kernel", + "model.model.layers.16.mlp.experts.down_proj.bias", + "model.model.layers.16.mlp.experts.down_proj.kernel", + "model.model.layers.16.mlp.experts.gate_proj.bias", + "model.model.layers.16.mlp.experts.gate_proj.kernel", + "model.model.layers.16.mlp.experts.up_proj.bias", + "model.model.layers.16.mlp.experts.up_proj.kernel", + "model.model.layers.16.mlp.router.bias", + "model.model.layers.16.mlp.router.kernel", + "model.model.layers.16.post_attention_layernorm.kernel", + "model.model.layers.16.self_attn.k_proj.bias", + "model.model.layers.16.self_attn.k_proj.kernel", + "model.model.layers.16.self_attn.o_proj.bias", + "model.model.layers.16.self_attn.o_proj.kernel", + "model.model.layers.16.self_attn.q_proj.bias", + "model.model.layers.16.self_attn.q_proj.kernel", + "model.model.layers.16.self_attn.sinks", + "model.model.layers.16.self_attn.v_proj.bias", + "model.model.layers.16.self_attn.v_proj.kernel", + "model.model.layers.17.input_layernorm.kernel", + "model.model.layers.17.mlp.experts.down_proj.bias", + "model.model.layers.17.mlp.experts.down_proj.kernel", + "model.model.layers.17.mlp.experts.gate_proj.bias", + "model.model.layers.17.mlp.experts.gate_proj.kernel", + "model.model.layers.17.mlp.experts.up_proj.bias", + "model.model.layers.17.mlp.experts.up_proj.kernel", + "model.model.layers.17.mlp.router.bias", + "model.model.layers.17.mlp.router.kernel", + "model.model.layers.17.post_attention_layernorm.kernel", + "model.model.layers.17.self_attn.k_proj.bias", + "model.model.layers.17.self_attn.k_proj.kernel", + "model.model.layers.17.self_attn.o_proj.bias", + "model.model.layers.17.self_attn.o_proj.kernel", + "model.model.layers.17.self_attn.q_proj.bias", + "model.model.layers.17.self_attn.q_proj.kernel", + "model.model.layers.17.self_attn.sinks", + "model.model.layers.17.self_attn.v_proj.bias", + "model.model.layers.17.self_attn.v_proj.kernel", + "model.model.layers.18.input_layernorm.kernel", + "model.model.layers.18.mlp.experts.down_proj.bias", + "model.model.layers.18.mlp.experts.down_proj.kernel", + "model.model.layers.18.mlp.experts.gate_proj.bias", + "model.model.layers.18.mlp.experts.gate_proj.kernel", + "model.model.layers.18.mlp.experts.up_proj.bias", + "model.model.layers.18.mlp.experts.up_proj.kernel", + "model.model.layers.18.mlp.router.bias", + "model.model.layers.18.mlp.router.kernel", + "model.model.layers.18.post_attention_layernorm.kernel", + "model.model.layers.18.self_attn.k_proj.bias", + "model.model.layers.18.self_attn.k_proj.kernel", + "model.model.layers.18.self_attn.o_proj.bias", + "model.model.layers.18.self_attn.o_proj.kernel", + "model.model.layers.18.self_attn.q_proj.bias", + "model.model.layers.18.self_attn.q_proj.kernel", + "model.model.layers.18.self_attn.sinks", + "model.model.layers.18.self_attn.v_proj.bias", + "model.model.layers.18.self_attn.v_proj.kernel", + "model.model.layers.19.input_layernorm.kernel", + "model.model.layers.19.mlp.experts.down_proj.bias", + "model.model.layers.19.mlp.experts.down_proj.kernel", + "model.model.layers.19.mlp.experts.gate_proj.bias", + "model.model.layers.19.mlp.experts.gate_proj.kernel", + "model.model.layers.19.mlp.experts.up_proj.bias", + "model.model.layers.19.mlp.experts.up_proj.kernel", + "model.model.layers.19.mlp.router.bias", + "model.model.layers.19.mlp.router.kernel", + "model.model.layers.19.post_attention_layernorm.kernel", + "model.model.layers.19.self_attn.k_proj.bias", + "model.model.layers.19.self_attn.k_proj.kernel", + "model.model.layers.19.self_attn.o_proj.bias", + "model.model.layers.19.self_attn.o_proj.kernel", + "model.model.layers.19.self_attn.q_proj.bias", + "model.model.layers.19.self_attn.q_proj.kernel", + "model.model.layers.19.self_attn.sinks", + "model.model.layers.19.self_attn.v_proj.bias", + "model.model.layers.19.self_attn.v_proj.kernel", + "model.model.layers.20.input_layernorm.kernel", + "model.model.layers.20.mlp.experts.down_proj.bias", + "model.model.layers.20.mlp.experts.down_proj.kernel", + "model.model.layers.20.mlp.experts.gate_proj.bias", + "model.model.layers.20.mlp.experts.gate_proj.kernel", + "model.model.layers.20.mlp.experts.up_proj.bias", + "model.model.layers.20.mlp.experts.up_proj.kernel", + "model.model.layers.20.mlp.router.bias", + "model.model.layers.20.mlp.router.kernel", + "model.model.layers.20.post_attention_layernorm.kernel", + "model.model.layers.20.self_attn.k_proj.bias", + "model.model.layers.20.self_attn.k_proj.kernel", + "model.model.layers.20.self_attn.o_proj.bias", + "model.model.layers.20.self_attn.o_proj.kernel", + "model.model.layers.20.self_attn.q_proj.bias", + "model.model.layers.20.self_attn.q_proj.kernel", + "model.model.layers.20.self_attn.sinks", + "model.model.layers.20.self_attn.v_proj.bias", + "model.model.layers.20.self_attn.v_proj.kernel", + "model.model.layers.21.input_layernorm.kernel", + "model.model.layers.21.mlp.experts.down_proj.bias", + "model.model.layers.21.mlp.experts.down_proj.kernel", + "model.model.layers.21.mlp.experts.gate_proj.bias", + "model.model.layers.21.mlp.experts.gate_proj.kernel", + "model.model.layers.21.mlp.experts.up_proj.bias", + "model.model.layers.21.mlp.experts.up_proj.kernel", + "model.model.layers.21.mlp.router.bias", + "model.model.layers.21.mlp.router.kernel", + "model.model.layers.21.post_attention_layernorm.kernel", + "model.model.layers.21.self_attn.k_proj.bias", + "model.model.layers.21.self_attn.k_proj.kernel", + "model.model.layers.21.self_attn.o_proj.bias", + "model.model.layers.21.self_attn.o_proj.kernel", + "model.model.layers.21.self_attn.q_proj.bias", + "model.model.layers.21.self_attn.q_proj.kernel", + "model.model.layers.21.self_attn.sinks", + "model.model.layers.21.self_attn.v_proj.bias", + "model.model.layers.21.self_attn.v_proj.kernel", + "model.model.layers.22.input_layernorm.kernel", + "model.model.layers.22.mlp.experts.down_proj.bias", + "model.model.layers.22.mlp.experts.down_proj.kernel", + "model.model.layers.22.mlp.experts.gate_proj.bias", + "model.model.layers.22.mlp.experts.gate_proj.kernel", + "model.model.layers.22.mlp.experts.up_proj.bias", + "model.model.layers.22.mlp.experts.up_proj.kernel", + "model.model.layers.22.mlp.router.bias", + "model.model.layers.22.mlp.router.kernel", + "model.model.layers.22.post_attention_layernorm.kernel", + "model.model.layers.22.self_attn.k_proj.bias", + "model.model.layers.22.self_attn.k_proj.kernel", + "model.model.layers.22.self_attn.o_proj.bias", + "model.model.layers.22.self_attn.o_proj.kernel", + "model.model.layers.22.self_attn.q_proj.bias", + "model.model.layers.22.self_attn.q_proj.kernel", + "model.model.layers.22.self_attn.sinks", + "model.model.layers.22.self_attn.v_proj.bias", + "model.model.layers.22.self_attn.v_proj.kernel", + "model.model.layers.23.input_layernorm.kernel", + "model.model.layers.23.mlp.experts.down_proj.bias", + "model.model.layers.23.mlp.experts.down_proj.kernel", + "model.model.layers.23.mlp.experts.gate_proj.bias", + "model.model.layers.23.mlp.experts.gate_proj.kernel", + "model.model.layers.23.mlp.experts.up_proj.bias", + "model.model.layers.23.mlp.experts.up_proj.kernel", + "model.model.layers.23.mlp.router.bias", + "model.model.layers.23.mlp.router.kernel", + "model.model.layers.23.post_attention_layernorm.kernel", + "model.model.layers.23.self_attn.k_proj.bias", + "model.model.layers.23.self_attn.k_proj.kernel", + "model.model.layers.23.self_attn.o_proj.bias", + "model.model.layers.23.self_attn.o_proj.kernel", + "model.model.layers.23.self_attn.q_proj.bias", + "model.model.layers.23.self_attn.q_proj.kernel", + "model.model.layers.23.self_attn.sinks", + "model.model.layers.23.self_attn.v_proj.bias", + "model.model.layers.23.self_attn.v_proj.kernel", + "model.model.norm.kernel" + ], + "arr_mask": [ + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true, + true + ], + "array_keys": [ + "model.lm_head.kernel", + "model.model.embed_tokens.embedding", + "model.model.layers.0.input_layernorm.kernel", + "model.model.layers.0.mlp.experts.down_proj.bias", + "model.model.layers.0.mlp.experts.down_proj.kernel", + "model.model.layers.0.mlp.experts.gate_proj.bias", + "model.model.layers.0.mlp.experts.gate_proj.kernel", + "model.model.layers.0.mlp.experts.up_proj.bias", + "model.model.layers.0.mlp.experts.up_proj.kernel", + "model.model.layers.0.mlp.router.bias", + "model.model.layers.0.mlp.router.kernel", + "model.model.layers.0.post_attention_layernorm.kernel", + "model.model.layers.0.self_attn.k_proj.bias", + "model.model.layers.0.self_attn.k_proj.kernel", + "model.model.layers.0.self_attn.o_proj.bias", + "model.model.layers.0.self_attn.o_proj.kernel", + "model.model.layers.0.self_attn.q_proj.bias", + "model.model.layers.0.self_attn.q_proj.kernel", + "model.model.layers.0.self_attn.sinks", + "model.model.layers.0.self_attn.v_proj.bias", + "model.model.layers.0.self_attn.v_proj.kernel", + "model.model.layers.1.input_layernorm.kernel", + "model.model.layers.1.mlp.experts.down_proj.bias", + "model.model.layers.1.mlp.experts.down_proj.kernel", + "model.model.layers.1.mlp.experts.gate_proj.bias", + "model.model.layers.1.mlp.experts.gate_proj.kernel", + "model.model.layers.1.mlp.experts.up_proj.bias", + "model.model.layers.1.mlp.experts.up_proj.kernel", + "model.model.layers.1.mlp.router.bias", + "model.model.layers.1.mlp.router.kernel", + "model.model.layers.1.post_attention_layernorm.kernel", + "model.model.layers.1.self_attn.k_proj.bias", + "model.model.layers.1.self_attn.k_proj.kernel", + "model.model.layers.1.self_attn.o_proj.bias", + "model.model.layers.1.self_attn.o_proj.kernel", + "model.model.layers.1.self_attn.q_proj.bias", + "model.model.layers.1.self_attn.q_proj.kernel", + "model.model.layers.1.self_attn.sinks", + "model.model.layers.1.self_attn.v_proj.bias", + "model.model.layers.1.self_attn.v_proj.kernel", + "model.model.layers.2.input_layernorm.kernel", + "model.model.layers.2.mlp.experts.down_proj.bias", + "model.model.layers.2.mlp.experts.down_proj.kernel", + "model.model.layers.2.mlp.experts.gate_proj.bias", + "model.model.layers.2.mlp.experts.gate_proj.kernel", + "model.model.layers.2.mlp.experts.up_proj.bias", + "model.model.layers.2.mlp.experts.up_proj.kernel", + "model.model.layers.2.mlp.router.bias", + "model.model.layers.2.mlp.router.kernel", + "model.model.layers.2.post_attention_layernorm.kernel", + "model.model.layers.2.self_attn.k_proj.bias", + "model.model.layers.2.self_attn.k_proj.kernel", + "model.model.layers.2.self_attn.o_proj.bias", + "model.model.layers.2.self_attn.o_proj.kernel", + "model.model.layers.2.self_attn.q_proj.bias", + "model.model.layers.2.self_attn.q_proj.kernel", + "model.model.layers.2.self_attn.sinks", + "model.model.layers.2.self_attn.v_proj.bias", + "model.model.layers.2.self_attn.v_proj.kernel", + "model.model.layers.3.input_layernorm.kernel", + "model.model.layers.3.mlp.experts.down_proj.bias", + "model.model.layers.3.mlp.experts.down_proj.kernel", + "model.model.layers.3.mlp.experts.gate_proj.bias", + "model.model.layers.3.mlp.experts.gate_proj.kernel", + "model.model.layers.3.mlp.experts.up_proj.bias", + "model.model.layers.3.mlp.experts.up_proj.kernel", + "model.model.layers.3.mlp.router.bias", + "model.model.layers.3.mlp.router.kernel", + "model.model.layers.3.post_attention_layernorm.kernel", + "model.model.layers.3.self_attn.k_proj.bias", + "model.model.layers.3.self_attn.k_proj.kernel", + "model.model.layers.3.self_attn.o_proj.bias", + "model.model.layers.3.self_attn.o_proj.kernel", + "model.model.layers.3.self_attn.q_proj.bias", + "model.model.layers.3.self_attn.q_proj.kernel", + "model.model.layers.3.self_attn.sinks", + "model.model.layers.3.self_attn.v_proj.bias", + "model.model.layers.3.self_attn.v_proj.kernel", + "model.model.layers.4.input_layernorm.kernel", + "model.model.layers.4.mlp.experts.down_proj.bias", + "model.model.layers.4.mlp.experts.down_proj.kernel", + "model.model.layers.4.mlp.experts.gate_proj.bias", + "model.model.layers.4.mlp.experts.gate_proj.kernel", + "model.model.layers.4.mlp.experts.up_proj.bias", + "model.model.layers.4.mlp.experts.up_proj.kernel", + "model.model.layers.4.mlp.router.bias", + "model.model.layers.4.mlp.router.kernel", + "model.model.layers.4.post_attention_layernorm.kernel", + "model.model.layers.4.self_attn.k_proj.bias", + "model.model.layers.4.self_attn.k_proj.kernel", + "model.model.layers.4.self_attn.o_proj.bias", + "model.model.layers.4.self_attn.o_proj.kernel", + "model.model.layers.4.self_attn.q_proj.bias", + "model.model.layers.4.self_attn.q_proj.kernel", + "model.model.layers.4.self_attn.sinks", + "model.model.layers.4.self_attn.v_proj.bias", + "model.model.layers.4.self_attn.v_proj.kernel", + "model.model.layers.5.input_layernorm.kernel", + "model.model.layers.5.mlp.experts.down_proj.bias", + "model.model.layers.5.mlp.experts.down_proj.kernel", + "model.model.layers.5.mlp.experts.gate_proj.bias", + "model.model.layers.5.mlp.experts.gate_proj.kernel", + "model.model.layers.5.mlp.experts.up_proj.bias", + "model.model.layers.5.mlp.experts.up_proj.kernel", + "model.model.layers.5.mlp.router.bias", + "model.model.layers.5.mlp.router.kernel", + "model.model.layers.5.post_attention_layernorm.kernel", + "model.model.layers.5.self_attn.k_proj.bias", + "model.model.layers.5.self_attn.k_proj.kernel", + "model.model.layers.5.self_attn.o_proj.bias", + "model.model.layers.5.self_attn.o_proj.kernel", + "model.model.layers.5.self_attn.q_proj.bias", + "model.model.layers.5.self_attn.q_proj.kernel", + "model.model.layers.5.self_attn.sinks", + "model.model.layers.5.self_attn.v_proj.bias", + "model.model.layers.5.self_attn.v_proj.kernel", + "model.model.layers.6.input_layernorm.kernel", + "model.model.layers.6.mlp.experts.down_proj.bias", + "model.model.layers.6.mlp.experts.down_proj.kernel", + "model.model.layers.6.mlp.experts.gate_proj.bias", + "model.model.layers.6.mlp.experts.gate_proj.kernel", + "model.model.layers.6.mlp.experts.up_proj.bias", + "model.model.layers.6.mlp.experts.up_proj.kernel", + "model.model.layers.6.mlp.router.bias", + "model.model.layers.6.mlp.router.kernel", + "model.model.layers.6.post_attention_layernorm.kernel", + "model.model.layers.6.self_attn.k_proj.bias", + "model.model.layers.6.self_attn.k_proj.kernel", + "model.model.layers.6.self_attn.o_proj.bias", + "model.model.layers.6.self_attn.o_proj.kernel", + "model.model.layers.6.self_attn.q_proj.bias", + "model.model.layers.6.self_attn.q_proj.kernel", + "model.model.layers.6.self_attn.sinks", + "model.model.layers.6.self_attn.v_proj.bias", + "model.model.layers.6.self_attn.v_proj.kernel", + "model.model.layers.7.input_layernorm.kernel", + "model.model.layers.7.mlp.experts.down_proj.bias", + "model.model.layers.7.mlp.experts.down_proj.kernel", + "model.model.layers.7.mlp.experts.gate_proj.bias", + "model.model.layers.7.mlp.experts.gate_proj.kernel", + "model.model.layers.7.mlp.experts.up_proj.bias", + "model.model.layers.7.mlp.experts.up_proj.kernel", + "model.model.layers.7.mlp.router.bias", + "model.model.layers.7.mlp.router.kernel", + "model.model.layers.7.post_attention_layernorm.kernel", + "model.model.layers.7.self_attn.k_proj.bias", + "model.model.layers.7.self_attn.k_proj.kernel", + "model.model.layers.7.self_attn.o_proj.bias", + "model.model.layers.7.self_attn.o_proj.kernel", + "model.model.layers.7.self_attn.q_proj.bias", + "model.model.layers.7.self_attn.q_proj.kernel", + "model.model.layers.7.self_attn.sinks", + "model.model.layers.7.self_attn.v_proj.bias", + "model.model.layers.7.self_attn.v_proj.kernel", + "model.model.layers.8.input_layernorm.kernel", + "model.model.layers.8.mlp.experts.down_proj.bias", + "model.model.layers.8.mlp.experts.down_proj.kernel", + "model.model.layers.8.mlp.experts.gate_proj.bias", + "model.model.layers.8.mlp.experts.gate_proj.kernel", + "model.model.layers.8.mlp.experts.up_proj.bias", + "model.model.layers.8.mlp.experts.up_proj.kernel", + "model.model.layers.8.mlp.router.bias", + "model.model.layers.8.mlp.router.kernel", + "model.model.layers.8.post_attention_layernorm.kernel", + "model.model.layers.8.self_attn.k_proj.bias", + "model.model.layers.8.self_attn.k_proj.kernel", + "model.model.layers.8.self_attn.o_proj.bias", + "model.model.layers.8.self_attn.o_proj.kernel", + "model.model.layers.8.self_attn.q_proj.bias", + "model.model.layers.8.self_attn.q_proj.kernel", + "model.model.layers.8.self_attn.sinks", + "model.model.layers.8.self_attn.v_proj.bias", + "model.model.layers.8.self_attn.v_proj.kernel", + "model.model.layers.9.input_layernorm.kernel", + "model.model.layers.9.mlp.experts.down_proj.bias", + "model.model.layers.9.mlp.experts.down_proj.kernel", + "model.model.layers.9.mlp.experts.gate_proj.bias", + "model.model.layers.9.mlp.experts.gate_proj.kernel", + "model.model.layers.9.mlp.experts.up_proj.bias", + "model.model.layers.9.mlp.experts.up_proj.kernel", + "model.model.layers.9.mlp.router.bias", + "model.model.layers.9.mlp.router.kernel", + "model.model.layers.9.post_attention_layernorm.kernel", + "model.model.layers.9.self_attn.k_proj.bias", + "model.model.layers.9.self_attn.k_proj.kernel", + "model.model.layers.9.self_attn.o_proj.bias", + "model.model.layers.9.self_attn.o_proj.kernel", + "model.model.layers.9.self_attn.q_proj.bias", + "model.model.layers.9.self_attn.q_proj.kernel", + "model.model.layers.9.self_attn.sinks", + "model.model.layers.9.self_attn.v_proj.bias", + "model.model.layers.9.self_attn.v_proj.kernel", + "model.model.layers.10.input_layernorm.kernel", + "model.model.layers.10.mlp.experts.down_proj.bias", + "model.model.layers.10.mlp.experts.down_proj.kernel", + "model.model.layers.10.mlp.experts.gate_proj.bias", + "model.model.layers.10.mlp.experts.gate_proj.kernel", + "model.model.layers.10.mlp.experts.up_proj.bias", + "model.model.layers.10.mlp.experts.up_proj.kernel", + "model.model.layers.10.mlp.router.bias", + "model.model.layers.10.mlp.router.kernel", + "model.model.layers.10.post_attention_layernorm.kernel", + "model.model.layers.10.self_attn.k_proj.bias", + "model.model.layers.10.self_attn.k_proj.kernel", + "model.model.layers.10.self_attn.o_proj.bias", + "model.model.layers.10.self_attn.o_proj.kernel", + "model.model.layers.10.self_attn.q_proj.bias", + "model.model.layers.10.self_attn.q_proj.kernel", + "model.model.layers.10.self_attn.sinks", + "model.model.layers.10.self_attn.v_proj.bias", + "model.model.layers.10.self_attn.v_proj.kernel", + "model.model.layers.11.input_layernorm.kernel", + "model.model.layers.11.mlp.experts.down_proj.bias", + "model.model.layers.11.mlp.experts.down_proj.kernel", + "model.model.layers.11.mlp.experts.gate_proj.bias", + "model.model.layers.11.mlp.experts.gate_proj.kernel", + "model.model.layers.11.mlp.experts.up_proj.bias", + "model.model.layers.11.mlp.experts.up_proj.kernel", + "model.model.layers.11.mlp.router.bias", + "model.model.layers.11.mlp.router.kernel", + "model.model.layers.11.post_attention_layernorm.kernel", + "model.model.layers.11.self_attn.k_proj.bias", + "model.model.layers.11.self_attn.k_proj.kernel", + "model.model.layers.11.self_attn.o_proj.bias", + "model.model.layers.11.self_attn.o_proj.kernel", + "model.model.layers.11.self_attn.q_proj.bias", + "model.model.layers.11.self_attn.q_proj.kernel", + "model.model.layers.11.self_attn.sinks", + "model.model.layers.11.self_attn.v_proj.bias", + "model.model.layers.11.self_attn.v_proj.kernel", + "model.model.layers.12.input_layernorm.kernel", + "model.model.layers.12.mlp.experts.down_proj.bias", + "model.model.layers.12.mlp.experts.down_proj.kernel", + "model.model.layers.12.mlp.experts.gate_proj.bias", + "model.model.layers.12.mlp.experts.gate_proj.kernel", + "model.model.layers.12.mlp.experts.up_proj.bias", + "model.model.layers.12.mlp.experts.up_proj.kernel", + "model.model.layers.12.mlp.router.bias", + "model.model.layers.12.mlp.router.kernel", + "model.model.layers.12.post_attention_layernorm.kernel", + "model.model.layers.12.self_attn.k_proj.bias", + "model.model.layers.12.self_attn.k_proj.kernel", + "model.model.layers.12.self_attn.o_proj.bias", + "model.model.layers.12.self_attn.o_proj.kernel", + "model.model.layers.12.self_attn.q_proj.bias", + "model.model.layers.12.self_attn.q_proj.kernel", + "model.model.layers.12.self_attn.sinks", + "model.model.layers.12.self_attn.v_proj.bias", + "model.model.layers.12.self_attn.v_proj.kernel", + "model.model.layers.13.input_layernorm.kernel", + "model.model.layers.13.mlp.experts.down_proj.bias", + "model.model.layers.13.mlp.experts.down_proj.kernel", + "model.model.layers.13.mlp.experts.gate_proj.bias", + "model.model.layers.13.mlp.experts.gate_proj.kernel", + "model.model.layers.13.mlp.experts.up_proj.bias", + "model.model.layers.13.mlp.experts.up_proj.kernel", + "model.model.layers.13.mlp.router.bias", + "model.model.layers.13.mlp.router.kernel", + "model.model.layers.13.post_attention_layernorm.kernel", + "model.model.layers.13.self_attn.k_proj.bias", + "model.model.layers.13.self_attn.k_proj.kernel", + "model.model.layers.13.self_attn.o_proj.bias", + "model.model.layers.13.self_attn.o_proj.kernel", + "model.model.layers.13.self_attn.q_proj.bias", + "model.model.layers.13.self_attn.q_proj.kernel", + "model.model.layers.13.self_attn.sinks", + "model.model.layers.13.self_attn.v_proj.bias", + "model.model.layers.13.self_attn.v_proj.kernel", + "model.model.layers.14.input_layernorm.kernel", + "model.model.layers.14.mlp.experts.down_proj.bias", + "model.model.layers.14.mlp.experts.down_proj.kernel", + "model.model.layers.14.mlp.experts.gate_proj.bias", + "model.model.layers.14.mlp.experts.gate_proj.kernel", + "model.model.layers.14.mlp.experts.up_proj.bias", + "model.model.layers.14.mlp.experts.up_proj.kernel", + "model.model.layers.14.mlp.router.bias", + "model.model.layers.14.mlp.router.kernel", + "model.model.layers.14.post_attention_layernorm.kernel", + "model.model.layers.14.self_attn.k_proj.bias", + "model.model.layers.14.self_attn.k_proj.kernel", + "model.model.layers.14.self_attn.o_proj.bias", + "model.model.layers.14.self_attn.o_proj.kernel", + "model.model.layers.14.self_attn.q_proj.bias", + "model.model.layers.14.self_attn.q_proj.kernel", + "model.model.layers.14.self_attn.sinks", + "model.model.layers.14.self_attn.v_proj.bias", + "model.model.layers.14.self_attn.v_proj.kernel", + "model.model.layers.15.input_layernorm.kernel", + "model.model.layers.15.mlp.experts.down_proj.bias", + "model.model.layers.15.mlp.experts.down_proj.kernel", + "model.model.layers.15.mlp.experts.gate_proj.bias", + "model.model.layers.15.mlp.experts.gate_proj.kernel", + "model.model.layers.15.mlp.experts.up_proj.bias", + "model.model.layers.15.mlp.experts.up_proj.kernel", + "model.model.layers.15.mlp.router.bias", + "model.model.layers.15.mlp.router.kernel", + "model.model.layers.15.post_attention_layernorm.kernel", + "model.model.layers.15.self_attn.k_proj.bias", + "model.model.layers.15.self_attn.k_proj.kernel", + "model.model.layers.15.self_attn.o_proj.bias", + "model.model.layers.15.self_attn.o_proj.kernel", + "model.model.layers.15.self_attn.q_proj.bias", + "model.model.layers.15.self_attn.q_proj.kernel", + "model.model.layers.15.self_attn.sinks", + "model.model.layers.15.self_attn.v_proj.bias", + "model.model.layers.15.self_attn.v_proj.kernel", + "model.model.layers.16.input_layernorm.kernel", + "model.model.layers.16.mlp.experts.down_proj.bias", + "model.model.layers.16.mlp.experts.down_proj.kernel", + "model.model.layers.16.mlp.experts.gate_proj.bias", + "model.model.layers.16.mlp.experts.gate_proj.kernel", + "model.model.layers.16.mlp.experts.up_proj.bias", + "model.model.layers.16.mlp.experts.up_proj.kernel", + "model.model.layers.16.mlp.router.bias", + "model.model.layers.16.mlp.router.kernel", + "model.model.layers.16.post_attention_layernorm.kernel", + "model.model.layers.16.self_attn.k_proj.bias", + "model.model.layers.16.self_attn.k_proj.kernel", + "model.model.layers.16.self_attn.o_proj.bias", + "model.model.layers.16.self_attn.o_proj.kernel", + "model.model.layers.16.self_attn.q_proj.bias", + "model.model.layers.16.self_attn.q_proj.kernel", + "model.model.layers.16.self_attn.sinks", + "model.model.layers.16.self_attn.v_proj.bias", + "model.model.layers.16.self_attn.v_proj.kernel", + "model.model.layers.17.input_layernorm.kernel", + "model.model.layers.17.mlp.experts.down_proj.bias", + "model.model.layers.17.mlp.experts.down_proj.kernel", + "model.model.layers.17.mlp.experts.gate_proj.bias", + "model.model.layers.17.mlp.experts.gate_proj.kernel", + "model.model.layers.17.mlp.experts.up_proj.bias", + "model.model.layers.17.mlp.experts.up_proj.kernel", + "model.model.layers.17.mlp.router.bias", + "model.model.layers.17.mlp.router.kernel", + "model.model.layers.17.post_attention_layernorm.kernel", + "model.model.layers.17.self_attn.k_proj.bias", + "model.model.layers.17.self_attn.k_proj.kernel", + "model.model.layers.17.self_attn.o_proj.bias", + "model.model.layers.17.self_attn.o_proj.kernel", + "model.model.layers.17.self_attn.q_proj.bias", + "model.model.layers.17.self_attn.q_proj.kernel", + "model.model.layers.17.self_attn.sinks", + "model.model.layers.17.self_attn.v_proj.bias", + "model.model.layers.17.self_attn.v_proj.kernel", + "model.model.layers.18.input_layernorm.kernel", + "model.model.layers.18.mlp.experts.down_proj.bias", + "model.model.layers.18.mlp.experts.down_proj.kernel", + "model.model.layers.18.mlp.experts.gate_proj.bias", + "model.model.layers.18.mlp.experts.gate_proj.kernel", + "model.model.layers.18.mlp.experts.up_proj.bias", + "model.model.layers.18.mlp.experts.up_proj.kernel", + "model.model.layers.18.mlp.router.bias", + "model.model.layers.18.mlp.router.kernel", + "model.model.layers.18.post_attention_layernorm.kernel", + "model.model.layers.18.self_attn.k_proj.bias", + "model.model.layers.18.self_attn.k_proj.kernel", + "model.model.layers.18.self_attn.o_proj.bias", + "model.model.layers.18.self_attn.o_proj.kernel", + "model.model.layers.18.self_attn.q_proj.bias", + "model.model.layers.18.self_attn.q_proj.kernel", + "model.model.layers.18.self_attn.sinks", + "model.model.layers.18.self_attn.v_proj.bias", + "model.model.layers.18.self_attn.v_proj.kernel", + "model.model.layers.19.input_layernorm.kernel", + "model.model.layers.19.mlp.experts.down_proj.bias", + "model.model.layers.19.mlp.experts.down_proj.kernel", + "model.model.layers.19.mlp.experts.gate_proj.bias", + "model.model.layers.19.mlp.experts.gate_proj.kernel", + "model.model.layers.19.mlp.experts.up_proj.bias", + "model.model.layers.19.mlp.experts.up_proj.kernel", + "model.model.layers.19.mlp.router.bias", + "model.model.layers.19.mlp.router.kernel", + "model.model.layers.19.post_attention_layernorm.kernel", + "model.model.layers.19.self_attn.k_proj.bias", + "model.model.layers.19.self_attn.k_proj.kernel", + "model.model.layers.19.self_attn.o_proj.bias", + "model.model.layers.19.self_attn.o_proj.kernel", + "model.model.layers.19.self_attn.q_proj.bias", + "model.model.layers.19.self_attn.q_proj.kernel", + "model.model.layers.19.self_attn.sinks", + "model.model.layers.19.self_attn.v_proj.bias", + "model.model.layers.19.self_attn.v_proj.kernel", + "model.model.layers.20.input_layernorm.kernel", + "model.model.layers.20.mlp.experts.down_proj.bias", + "model.model.layers.20.mlp.experts.down_proj.kernel", + "model.model.layers.20.mlp.experts.gate_proj.bias", + "model.model.layers.20.mlp.experts.gate_proj.kernel", + "model.model.layers.20.mlp.experts.up_proj.bias", + "model.model.layers.20.mlp.experts.up_proj.kernel", + "model.model.layers.20.mlp.router.bias", + "model.model.layers.20.mlp.router.kernel", + "model.model.layers.20.post_attention_layernorm.kernel", + "model.model.layers.20.self_attn.k_proj.bias", + "model.model.layers.20.self_attn.k_proj.kernel", + "model.model.layers.20.self_attn.o_proj.bias", + "model.model.layers.20.self_attn.o_proj.kernel", + "model.model.layers.20.self_attn.q_proj.bias", + "model.model.layers.20.self_attn.q_proj.kernel", + "model.model.layers.20.self_attn.sinks", + "model.model.layers.20.self_attn.v_proj.bias", + "model.model.layers.20.self_attn.v_proj.kernel", + "model.model.layers.21.input_layernorm.kernel", + "model.model.layers.21.mlp.experts.down_proj.bias", + "model.model.layers.21.mlp.experts.down_proj.kernel", + "model.model.layers.21.mlp.experts.gate_proj.bias", + "model.model.layers.21.mlp.experts.gate_proj.kernel", + "model.model.layers.21.mlp.experts.up_proj.bias", + "model.model.layers.21.mlp.experts.up_proj.kernel", + "model.model.layers.21.mlp.router.bias", + "model.model.layers.21.mlp.router.kernel", + "model.model.layers.21.post_attention_layernorm.kernel", + "model.model.layers.21.self_attn.k_proj.bias", + "model.model.layers.21.self_attn.k_proj.kernel", + "model.model.layers.21.self_attn.o_proj.bias", + "model.model.layers.21.self_attn.o_proj.kernel", + "model.model.layers.21.self_attn.q_proj.bias", + "model.model.layers.21.self_attn.q_proj.kernel", + "model.model.layers.21.self_attn.sinks", + "model.model.layers.21.self_attn.v_proj.bias", + "model.model.layers.21.self_attn.v_proj.kernel", + "model.model.layers.22.input_layernorm.kernel", + "model.model.layers.22.mlp.experts.down_proj.bias", + "model.model.layers.22.mlp.experts.down_proj.kernel", + "model.model.layers.22.mlp.experts.gate_proj.bias", + "model.model.layers.22.mlp.experts.gate_proj.kernel", + "model.model.layers.22.mlp.experts.up_proj.bias", + "model.model.layers.22.mlp.experts.up_proj.kernel", + "model.model.layers.22.mlp.router.bias", + "model.model.layers.22.mlp.router.kernel", + "model.model.layers.22.post_attention_layernorm.kernel", + "model.model.layers.22.self_attn.k_proj.bias", + "model.model.layers.22.self_attn.k_proj.kernel", + "model.model.layers.22.self_attn.o_proj.bias", + "model.model.layers.22.self_attn.o_proj.kernel", + "model.model.layers.22.self_attn.q_proj.bias", + "model.model.layers.22.self_attn.q_proj.kernel", + "model.model.layers.22.self_attn.sinks", + "model.model.layers.22.self_attn.v_proj.bias", + "model.model.layers.22.self_attn.v_proj.kernel", + "model.model.layers.23.input_layernorm.kernel", + "model.model.layers.23.mlp.experts.down_proj.bias", + "model.model.layers.23.mlp.experts.down_proj.kernel", + "model.model.layers.23.mlp.experts.gate_proj.bias", + "model.model.layers.23.mlp.experts.gate_proj.kernel", + "model.model.layers.23.mlp.experts.up_proj.bias", + "model.model.layers.23.mlp.experts.up_proj.kernel", + "model.model.layers.23.mlp.router.bias", + "model.model.layers.23.mlp.router.kernel", + "model.model.layers.23.post_attention_layernorm.kernel", + "model.model.layers.23.self_attn.k_proj.bias", + "model.model.layers.23.self_attn.k_proj.kernel", + "model.model.layers.23.self_attn.o_proj.bias", + "model.model.layers.23.self_attn.o_proj.kernel", + "model.model.layers.23.self_attn.q_proj.bias", + "model.model.layers.23.self_attn.q_proj.kernel", + "model.model.layers.23.self_attn.sinks", + "model.model.layers.23.self_attn.v_proj.bias", + "model.model.layers.23.self_attn.v_proj.kernel", + "model.model.norm.kernel" + ], + "array_relpaths": [ + "model/lm_head/kernel", + "model/model/embed_tokens/embedding", + "model/model/layers/0/input_layernorm/kernel", + "model/model/layers/0/mlp/experts/down_proj/bias", + "model/model/layers/0/mlp/experts/down_proj/kernel", + "model/model/layers/0/mlp/experts/gate_proj/bias", + "model/model/layers/0/mlp/experts/gate_proj/kernel", + "model/model/layers/0/mlp/experts/up_proj/bias", + "model/model/layers/0/mlp/experts/up_proj/kernel", + "model/model/layers/0/mlp/router/bias", + "model/model/layers/0/mlp/router/kernel", + "model/model/layers/0/post_attention_layernorm/kernel", + "model/model/layers/0/self_attn/k_proj/bias", + "model/model/layers/0/self_attn/k_proj/kernel", + "model/model/layers/0/self_attn/o_proj/bias", + "model/model/layers/0/self_attn/o_proj/kernel", + "model/model/layers/0/self_attn/q_proj/bias", + "model/model/layers/0/self_attn/q_proj/kernel", + "model/model/layers/0/self_attn/sinks", + "model/model/layers/0/self_attn/v_proj/bias", + "model/model/layers/0/self_attn/v_proj/kernel", + "model/model/layers/1/input_layernorm/kernel", + "model/model/layers/1/mlp/experts/down_proj/bias", + "model/model/layers/1/mlp/experts/down_proj/kernel", + "model/model/layers/1/mlp/experts/gate_proj/bias", + "model/model/layers/1/mlp/experts/gate_proj/kernel", + "model/model/layers/1/mlp/experts/up_proj/bias", + "model/model/layers/1/mlp/experts/up_proj/kernel", + "model/model/layers/1/mlp/router/bias", + "model/model/layers/1/mlp/router/kernel", + "model/model/layers/1/post_attention_layernorm/kernel", + "model/model/layers/1/self_attn/k_proj/bias", + "model/model/layers/1/self_attn/k_proj/kernel", + "model/model/layers/1/self_attn/o_proj/bias", + "model/model/layers/1/self_attn/o_proj/kernel", + "model/model/layers/1/self_attn/q_proj/bias", + "model/model/layers/1/self_attn/q_proj/kernel", + "model/model/layers/1/self_attn/sinks", + "model/model/layers/1/self_attn/v_proj/bias", + "model/model/layers/1/self_attn/v_proj/kernel", + "model/model/layers/2/input_layernorm/kernel", + "model/model/layers/2/mlp/experts/down_proj/bias", + "model/model/layers/2/mlp/experts/down_proj/kernel", + "model/model/layers/2/mlp/experts/gate_proj/bias", + "model/model/layers/2/mlp/experts/gate_proj/kernel", + "model/model/layers/2/mlp/experts/up_proj/bias", + "model/model/layers/2/mlp/experts/up_proj/kernel", + "model/model/layers/2/mlp/router/bias", + "model/model/layers/2/mlp/router/kernel", + "model/model/layers/2/post_attention_layernorm/kernel", + "model/model/layers/2/self_attn/k_proj/bias", + "model/model/layers/2/self_attn/k_proj/kernel", + "model/model/layers/2/self_attn/o_proj/bias", + "model/model/layers/2/self_attn/o_proj/kernel", + "model/model/layers/2/self_attn/q_proj/bias", + "model/model/layers/2/self_attn/q_proj/kernel", + "model/model/layers/2/self_attn/sinks", + "model/model/layers/2/self_attn/v_proj/bias", + "model/model/layers/2/self_attn/v_proj/kernel", + "model/model/layers/3/input_layernorm/kernel", + "model/model/layers/3/mlp/experts/down_proj/bias", + "model/model/layers/3/mlp/experts/down_proj/kernel", + "model/model/layers/3/mlp/experts/gate_proj/bias", + "model/model/layers/3/mlp/experts/gate_proj/kernel", + "model/model/layers/3/mlp/experts/up_proj/bias", + "model/model/layers/3/mlp/experts/up_proj/kernel", + "model/model/layers/3/mlp/router/bias", + "model/model/layers/3/mlp/router/kernel", + "model/model/layers/3/post_attention_layernorm/kernel", + "model/model/layers/3/self_attn/k_proj/bias", + "model/model/layers/3/self_attn/k_proj/kernel", + "model/model/layers/3/self_attn/o_proj/bias", + "model/model/layers/3/self_attn/o_proj/kernel", + "model/model/layers/3/self_attn/q_proj/bias", + "model/model/layers/3/self_attn/q_proj/kernel", + "model/model/layers/3/self_attn/sinks", + "model/model/layers/3/self_attn/v_proj/bias", + "model/model/layers/3/self_attn/v_proj/kernel", + "model/model/layers/4/input_layernorm/kernel", + "model/model/layers/4/mlp/experts/down_proj/bias", + "model/model/layers/4/mlp/experts/down_proj/kernel", + "model/model/layers/4/mlp/experts/gate_proj/bias", + "model/model/layers/4/mlp/experts/gate_proj/kernel", + "model/model/layers/4/mlp/experts/up_proj/bias", + "model/model/layers/4/mlp/experts/up_proj/kernel", + "model/model/layers/4/mlp/router/bias", + "model/model/layers/4/mlp/router/kernel", + "model/model/layers/4/post_attention_layernorm/kernel", + "model/model/layers/4/self_attn/k_proj/bias", + "model/model/layers/4/self_attn/k_proj/kernel", + "model/model/layers/4/self_attn/o_proj/bias", + "model/model/layers/4/self_attn/o_proj/kernel", + "model/model/layers/4/self_attn/q_proj/bias", + "model/model/layers/4/self_attn/q_proj/kernel", + "model/model/layers/4/self_attn/sinks", + "model/model/layers/4/self_attn/v_proj/bias", + "model/model/layers/4/self_attn/v_proj/kernel", + "model/model/layers/5/input_layernorm/kernel", + "model/model/layers/5/mlp/experts/down_proj/bias", + "model/model/layers/5/mlp/experts/down_proj/kernel", + "model/model/layers/5/mlp/experts/gate_proj/bias", + "model/model/layers/5/mlp/experts/gate_proj/kernel", + "model/model/layers/5/mlp/experts/up_proj/bias", + "model/model/layers/5/mlp/experts/up_proj/kernel", + "model/model/layers/5/mlp/router/bias", + "model/model/layers/5/mlp/router/kernel", + "model/model/layers/5/post_attention_layernorm/kernel", + "model/model/layers/5/self_attn/k_proj/bias", + "model/model/layers/5/self_attn/k_proj/kernel", + "model/model/layers/5/self_attn/o_proj/bias", + "model/model/layers/5/self_attn/o_proj/kernel", + "model/model/layers/5/self_attn/q_proj/bias", + "model/model/layers/5/self_attn/q_proj/kernel", + "model/model/layers/5/self_attn/sinks", + "model/model/layers/5/self_attn/v_proj/bias", + "model/model/layers/5/self_attn/v_proj/kernel", + "model/model/layers/6/input_layernorm/kernel", + "model/model/layers/6/mlp/experts/down_proj/bias", + "model/model/layers/6/mlp/experts/down_proj/kernel", + "model/model/layers/6/mlp/experts/gate_proj/bias", + "model/model/layers/6/mlp/experts/gate_proj/kernel", + "model/model/layers/6/mlp/experts/up_proj/bias", + "model/model/layers/6/mlp/experts/up_proj/kernel", + "model/model/layers/6/mlp/router/bias", + "model/model/layers/6/mlp/router/kernel", + "model/model/layers/6/post_attention_layernorm/kernel", + "model/model/layers/6/self_attn/k_proj/bias", + "model/model/layers/6/self_attn/k_proj/kernel", + "model/model/layers/6/self_attn/o_proj/bias", + "model/model/layers/6/self_attn/o_proj/kernel", + "model/model/layers/6/self_attn/q_proj/bias", + "model/model/layers/6/self_attn/q_proj/kernel", + "model/model/layers/6/self_attn/sinks", + "model/model/layers/6/self_attn/v_proj/bias", + "model/model/layers/6/self_attn/v_proj/kernel", + "model/model/layers/7/input_layernorm/kernel", + "model/model/layers/7/mlp/experts/down_proj/bias", + "model/model/layers/7/mlp/experts/down_proj/kernel", + "model/model/layers/7/mlp/experts/gate_proj/bias", + "model/model/layers/7/mlp/experts/gate_proj/kernel", + "model/model/layers/7/mlp/experts/up_proj/bias", + "model/model/layers/7/mlp/experts/up_proj/kernel", + "model/model/layers/7/mlp/router/bias", + "model/model/layers/7/mlp/router/kernel", + "model/model/layers/7/post_attention_layernorm/kernel", + "model/model/layers/7/self_attn/k_proj/bias", + "model/model/layers/7/self_attn/k_proj/kernel", + "model/model/layers/7/self_attn/o_proj/bias", + "model/model/layers/7/self_attn/o_proj/kernel", + "model/model/layers/7/self_attn/q_proj/bias", + "model/model/layers/7/self_attn/q_proj/kernel", + "model/model/layers/7/self_attn/sinks", + "model/model/layers/7/self_attn/v_proj/bias", + "model/model/layers/7/self_attn/v_proj/kernel", + "model/model/layers/8/input_layernorm/kernel", + "model/model/layers/8/mlp/experts/down_proj/bias", + "model/model/layers/8/mlp/experts/down_proj/kernel", + "model/model/layers/8/mlp/experts/gate_proj/bias", + "model/model/layers/8/mlp/experts/gate_proj/kernel", + "model/model/layers/8/mlp/experts/up_proj/bias", + "model/model/layers/8/mlp/experts/up_proj/kernel", + "model/model/layers/8/mlp/router/bias", + "model/model/layers/8/mlp/router/kernel", + "model/model/layers/8/post_attention_layernorm/kernel", + "model/model/layers/8/self_attn/k_proj/bias", + "model/model/layers/8/self_attn/k_proj/kernel", + "model/model/layers/8/self_attn/o_proj/bias", + "model/model/layers/8/self_attn/o_proj/kernel", + "model/model/layers/8/self_attn/q_proj/bias", + "model/model/layers/8/self_attn/q_proj/kernel", + "model/model/layers/8/self_attn/sinks", + "model/model/layers/8/self_attn/v_proj/bias", + "model/model/layers/8/self_attn/v_proj/kernel", + "model/model/layers/9/input_layernorm/kernel", + "model/model/layers/9/mlp/experts/down_proj/bias", + "model/model/layers/9/mlp/experts/down_proj/kernel", + "model/model/layers/9/mlp/experts/gate_proj/bias", + "model/model/layers/9/mlp/experts/gate_proj/kernel", + "model/model/layers/9/mlp/experts/up_proj/bias", + "model/model/layers/9/mlp/experts/up_proj/kernel", + "model/model/layers/9/mlp/router/bias", + "model/model/layers/9/mlp/router/kernel", + "model/model/layers/9/post_attention_layernorm/kernel", + "model/model/layers/9/self_attn/k_proj/bias", + "model/model/layers/9/self_attn/k_proj/kernel", + "model/model/layers/9/self_attn/o_proj/bias", + "model/model/layers/9/self_attn/o_proj/kernel", + "model/model/layers/9/self_attn/q_proj/bias", + "model/model/layers/9/self_attn/q_proj/kernel", + "model/model/layers/9/self_attn/sinks", + "model/model/layers/9/self_attn/v_proj/bias", + "model/model/layers/9/self_attn/v_proj/kernel", + "model/model/layers/10/input_layernorm/kernel", + "model/model/layers/10/mlp/experts/down_proj/bias", + "model/model/layers/10/mlp/experts/down_proj/kernel", + "model/model/layers/10/mlp/experts/gate_proj/bias", + "model/model/layers/10/mlp/experts/gate_proj/kernel", + "model/model/layers/10/mlp/experts/up_proj/bias", + "model/model/layers/10/mlp/experts/up_proj/kernel", + "model/model/layers/10/mlp/router/bias", + "model/model/layers/10/mlp/router/kernel", + "model/model/layers/10/post_attention_layernorm/kernel", + "model/model/layers/10/self_attn/k_proj/bias", + "model/model/layers/10/self_attn/k_proj/kernel", + "model/model/layers/10/self_attn/o_proj/bias", + "model/model/layers/10/self_attn/o_proj/kernel", + "model/model/layers/10/self_attn/q_proj/bias", + "model/model/layers/10/self_attn/q_proj/kernel", + "model/model/layers/10/self_attn/sinks", + "model/model/layers/10/self_attn/v_proj/bias", + "model/model/layers/10/self_attn/v_proj/kernel", + "model/model/layers/11/input_layernorm/kernel", + "model/model/layers/11/mlp/experts/down_proj/bias", + "model/model/layers/11/mlp/experts/down_proj/kernel", + "model/model/layers/11/mlp/experts/gate_proj/bias", + "model/model/layers/11/mlp/experts/gate_proj/kernel", + "model/model/layers/11/mlp/experts/up_proj/bias", + "model/model/layers/11/mlp/experts/up_proj/kernel", + "model/model/layers/11/mlp/router/bias", + "model/model/layers/11/mlp/router/kernel", + "model/model/layers/11/post_attention_layernorm/kernel", + "model/model/layers/11/self_attn/k_proj/bias", + "model/model/layers/11/self_attn/k_proj/kernel", + "model/model/layers/11/self_attn/o_proj/bias", + "model/model/layers/11/self_attn/o_proj/kernel", + "model/model/layers/11/self_attn/q_proj/bias", + "model/model/layers/11/self_attn/q_proj/kernel", + "model/model/layers/11/self_attn/sinks", + "model/model/layers/11/self_attn/v_proj/bias", + "model/model/layers/11/self_attn/v_proj/kernel", + "model/model/layers/12/input_layernorm/kernel", + "model/model/layers/12/mlp/experts/down_proj/bias", + "model/model/layers/12/mlp/experts/down_proj/kernel", + "model/model/layers/12/mlp/experts/gate_proj/bias", + "model/model/layers/12/mlp/experts/gate_proj/kernel", + "model/model/layers/12/mlp/experts/up_proj/bias", + "model/model/layers/12/mlp/experts/up_proj/kernel", + "model/model/layers/12/mlp/router/bias", + "model/model/layers/12/mlp/router/kernel", + "model/model/layers/12/post_attention_layernorm/kernel", + "model/model/layers/12/self_attn/k_proj/bias", + "model/model/layers/12/self_attn/k_proj/kernel", + "model/model/layers/12/self_attn/o_proj/bias", + "model/model/layers/12/self_attn/o_proj/kernel", + "model/model/layers/12/self_attn/q_proj/bias", + "model/model/layers/12/self_attn/q_proj/kernel", + "model/model/layers/12/self_attn/sinks", + "model/model/layers/12/self_attn/v_proj/bias", + "model/model/layers/12/self_attn/v_proj/kernel", + "model/model/layers/13/input_layernorm/kernel", + "model/model/layers/13/mlp/experts/down_proj/bias", + "model/model/layers/13/mlp/experts/down_proj/kernel", + "model/model/layers/13/mlp/experts/gate_proj/bias", + "model/model/layers/13/mlp/experts/gate_proj/kernel", + "model/model/layers/13/mlp/experts/up_proj/bias", + "model/model/layers/13/mlp/experts/up_proj/kernel", + "model/model/layers/13/mlp/router/bias", + "model/model/layers/13/mlp/router/kernel", + "model/model/layers/13/post_attention_layernorm/kernel", + "model/model/layers/13/self_attn/k_proj/bias", + "model/model/layers/13/self_attn/k_proj/kernel", + "model/model/layers/13/self_attn/o_proj/bias", + "model/model/layers/13/self_attn/o_proj/kernel", + "model/model/layers/13/self_attn/q_proj/bias", + "model/model/layers/13/self_attn/q_proj/kernel", + "model/model/layers/13/self_attn/sinks", + "model/model/layers/13/self_attn/v_proj/bias", + "model/model/layers/13/self_attn/v_proj/kernel", + "model/model/layers/14/input_layernorm/kernel", + "model/model/layers/14/mlp/experts/down_proj/bias", + "model/model/layers/14/mlp/experts/down_proj/kernel", + "model/model/layers/14/mlp/experts/gate_proj/bias", + "model/model/layers/14/mlp/experts/gate_proj/kernel", + "model/model/layers/14/mlp/experts/up_proj/bias", + "model/model/layers/14/mlp/experts/up_proj/kernel", + "model/model/layers/14/mlp/router/bias", + "model/model/layers/14/mlp/router/kernel", + "model/model/layers/14/post_attention_layernorm/kernel", + "model/model/layers/14/self_attn/k_proj/bias", + "model/model/layers/14/self_attn/k_proj/kernel", + "model/model/layers/14/self_attn/o_proj/bias", + "model/model/layers/14/self_attn/o_proj/kernel", + "model/model/layers/14/self_attn/q_proj/bias", + "model/model/layers/14/self_attn/q_proj/kernel", + "model/model/layers/14/self_attn/sinks", + "model/model/layers/14/self_attn/v_proj/bias", + "model/model/layers/14/self_attn/v_proj/kernel", + "model/model/layers/15/input_layernorm/kernel", + "model/model/layers/15/mlp/experts/down_proj/bias", + "model/model/layers/15/mlp/experts/down_proj/kernel", + "model/model/layers/15/mlp/experts/gate_proj/bias", + "model/model/layers/15/mlp/experts/gate_proj/kernel", + "model/model/layers/15/mlp/experts/up_proj/bias", + "model/model/layers/15/mlp/experts/up_proj/kernel", + "model/model/layers/15/mlp/router/bias", + "model/model/layers/15/mlp/router/kernel", + "model/model/layers/15/post_attention_layernorm/kernel", + "model/model/layers/15/self_attn/k_proj/bias", + "model/model/layers/15/self_attn/k_proj/kernel", + "model/model/layers/15/self_attn/o_proj/bias", + "model/model/layers/15/self_attn/o_proj/kernel", + "model/model/layers/15/self_attn/q_proj/bias", + "model/model/layers/15/self_attn/q_proj/kernel", + "model/model/layers/15/self_attn/sinks", + "model/model/layers/15/self_attn/v_proj/bias", + "model/model/layers/15/self_attn/v_proj/kernel", + "model/model/layers/16/input_layernorm/kernel", + "model/model/layers/16/mlp/experts/down_proj/bias", + "model/model/layers/16/mlp/experts/down_proj/kernel", + "model/model/layers/16/mlp/experts/gate_proj/bias", + "model/model/layers/16/mlp/experts/gate_proj/kernel", + "model/model/layers/16/mlp/experts/up_proj/bias", + "model/model/layers/16/mlp/experts/up_proj/kernel", + "model/model/layers/16/mlp/router/bias", + "model/model/layers/16/mlp/router/kernel", + "model/model/layers/16/post_attention_layernorm/kernel", + "model/model/layers/16/self_attn/k_proj/bias", + "model/model/layers/16/self_attn/k_proj/kernel", + "model/model/layers/16/self_attn/o_proj/bias", + "model/model/layers/16/self_attn/o_proj/kernel", + "model/model/layers/16/self_attn/q_proj/bias", + "model/model/layers/16/self_attn/q_proj/kernel", + "model/model/layers/16/self_attn/sinks", + "model/model/layers/16/self_attn/v_proj/bias", + "model/model/layers/16/self_attn/v_proj/kernel", + "model/model/layers/17/input_layernorm/kernel", + "model/model/layers/17/mlp/experts/down_proj/bias", + "model/model/layers/17/mlp/experts/down_proj/kernel", + "model/model/layers/17/mlp/experts/gate_proj/bias", + "model/model/layers/17/mlp/experts/gate_proj/kernel", + "model/model/layers/17/mlp/experts/up_proj/bias", + "model/model/layers/17/mlp/experts/up_proj/kernel", + "model/model/layers/17/mlp/router/bias", + "model/model/layers/17/mlp/router/kernel", + "model/model/layers/17/post_attention_layernorm/kernel", + "model/model/layers/17/self_attn/k_proj/bias", + "model/model/layers/17/self_attn/k_proj/kernel", + "model/model/layers/17/self_attn/o_proj/bias", + "model/model/layers/17/self_attn/o_proj/kernel", + "model/model/layers/17/self_attn/q_proj/bias", + "model/model/layers/17/self_attn/q_proj/kernel", + "model/model/layers/17/self_attn/sinks", + "model/model/layers/17/self_attn/v_proj/bias", + "model/model/layers/17/self_attn/v_proj/kernel", + "model/model/layers/18/input_layernorm/kernel", + "model/model/layers/18/mlp/experts/down_proj/bias", + "model/model/layers/18/mlp/experts/down_proj/kernel", + "model/model/layers/18/mlp/experts/gate_proj/bias", + "model/model/layers/18/mlp/experts/gate_proj/kernel", + "model/model/layers/18/mlp/experts/up_proj/bias", + "model/model/layers/18/mlp/experts/up_proj/kernel", + "model/model/layers/18/mlp/router/bias", + "model/model/layers/18/mlp/router/kernel", + "model/model/layers/18/post_attention_layernorm/kernel", + "model/model/layers/18/self_attn/k_proj/bias", + "model/model/layers/18/self_attn/k_proj/kernel", + "model/model/layers/18/self_attn/o_proj/bias", + "model/model/layers/18/self_attn/o_proj/kernel", + "model/model/layers/18/self_attn/q_proj/bias", + "model/model/layers/18/self_attn/q_proj/kernel", + "model/model/layers/18/self_attn/sinks", + "model/model/layers/18/self_attn/v_proj/bias", + "model/model/layers/18/self_attn/v_proj/kernel", + "model/model/layers/19/input_layernorm/kernel", + "model/model/layers/19/mlp/experts/down_proj/bias", + "model/model/layers/19/mlp/experts/down_proj/kernel", + "model/model/layers/19/mlp/experts/gate_proj/bias", + "model/model/layers/19/mlp/experts/gate_proj/kernel", + "model/model/layers/19/mlp/experts/up_proj/bias", + "model/model/layers/19/mlp/experts/up_proj/kernel", + "model/model/layers/19/mlp/router/bias", + "model/model/layers/19/mlp/router/kernel", + "model/model/layers/19/post_attention_layernorm/kernel", + "model/model/layers/19/self_attn/k_proj/bias", + "model/model/layers/19/self_attn/k_proj/kernel", + "model/model/layers/19/self_attn/o_proj/bias", + "model/model/layers/19/self_attn/o_proj/kernel", + "model/model/layers/19/self_attn/q_proj/bias", + "model/model/layers/19/self_attn/q_proj/kernel", + "model/model/layers/19/self_attn/sinks", + "model/model/layers/19/self_attn/v_proj/bias", + "model/model/layers/19/self_attn/v_proj/kernel", + "model/model/layers/20/input_layernorm/kernel", + "model/model/layers/20/mlp/experts/down_proj/bias", + "model/model/layers/20/mlp/experts/down_proj/kernel", + "model/model/layers/20/mlp/experts/gate_proj/bias", + "model/model/layers/20/mlp/experts/gate_proj/kernel", + "model/model/layers/20/mlp/experts/up_proj/bias", + "model/model/layers/20/mlp/experts/up_proj/kernel", + "model/model/layers/20/mlp/router/bias", + "model/model/layers/20/mlp/router/kernel", + "model/model/layers/20/post_attention_layernorm/kernel", + "model/model/layers/20/self_attn/k_proj/bias", + "model/model/layers/20/self_attn/k_proj/kernel", + "model/model/layers/20/self_attn/o_proj/bias", + "model/model/layers/20/self_attn/o_proj/kernel", + "model/model/layers/20/self_attn/q_proj/bias", + "model/model/layers/20/self_attn/q_proj/kernel", + "model/model/layers/20/self_attn/sinks", + "model/model/layers/20/self_attn/v_proj/bias", + "model/model/layers/20/self_attn/v_proj/kernel", + "model/model/layers/21/input_layernorm/kernel", + "model/model/layers/21/mlp/experts/down_proj/bias", + "model/model/layers/21/mlp/experts/down_proj/kernel", + "model/model/layers/21/mlp/experts/gate_proj/bias", + "model/model/layers/21/mlp/experts/gate_proj/kernel", + "model/model/layers/21/mlp/experts/up_proj/bias", + "model/model/layers/21/mlp/experts/up_proj/kernel", + "model/model/layers/21/mlp/router/bias", + "model/model/layers/21/mlp/router/kernel", + "model/model/layers/21/post_attention_layernorm/kernel", + "model/model/layers/21/self_attn/k_proj/bias", + "model/model/layers/21/self_attn/k_proj/kernel", + "model/model/layers/21/self_attn/o_proj/bias", + "model/model/layers/21/self_attn/o_proj/kernel", + "model/model/layers/21/self_attn/q_proj/bias", + "model/model/layers/21/self_attn/q_proj/kernel", + "model/model/layers/21/self_attn/sinks", + "model/model/layers/21/self_attn/v_proj/bias", + "model/model/layers/21/self_attn/v_proj/kernel", + "model/model/layers/22/input_layernorm/kernel", + "model/model/layers/22/mlp/experts/down_proj/bias", + "model/model/layers/22/mlp/experts/down_proj/kernel", + "model/model/layers/22/mlp/experts/gate_proj/bias", + "model/model/layers/22/mlp/experts/gate_proj/kernel", + "model/model/layers/22/mlp/experts/up_proj/bias", + "model/model/layers/22/mlp/experts/up_proj/kernel", + "model/model/layers/22/mlp/router/bias", + "model/model/layers/22/mlp/router/kernel", + "model/model/layers/22/post_attention_layernorm/kernel", + "model/model/layers/22/self_attn/k_proj/bias", + "model/model/layers/22/self_attn/k_proj/kernel", + "model/model/layers/22/self_attn/o_proj/bias", + "model/model/layers/22/self_attn/o_proj/kernel", + "model/model/layers/22/self_attn/q_proj/bias", + "model/model/layers/22/self_attn/q_proj/kernel", + "model/model/layers/22/self_attn/sinks", + "model/model/layers/22/self_attn/v_proj/bias", + "model/model/layers/22/self_attn/v_proj/kernel", + "model/model/layers/23/input_layernorm/kernel", + "model/model/layers/23/mlp/experts/down_proj/bias", + "model/model/layers/23/mlp/experts/down_proj/kernel", + "model/model/layers/23/mlp/experts/gate_proj/bias", + "model/model/layers/23/mlp/experts/gate_proj/kernel", + "model/model/layers/23/mlp/experts/up_proj/bias", + "model/model/layers/23/mlp/experts/up_proj/kernel", + "model/model/layers/23/mlp/router/bias", + "model/model/layers/23/mlp/router/kernel", + "model/model/layers/23/post_attention_layernorm/kernel", + "model/model/layers/23/self_attn/k_proj/bias", + "model/model/layers/23/self_attn/k_proj/kernel", + "model/model/layers/23/self_attn/o_proj/bias", + "model/model/layers/23/self_attn/o_proj/kernel", + "model/model/layers/23/self_attn/q_proj/bias", + "model/model/layers/23/self_attn/q_proj/kernel", + "model/model/layers/23/self_attn/sinks", + "model/model/layers/23/self_attn/v_proj/bias", + "model/model/layers/23/self_attn/v_proj/kernel", + "model/model/norm/kernel" + ], + "nonarray_payload": {}, + "safetensors_file": null, + "extras": {} +} \ No newline at end of file diff --git a/tensorstore_index.json b/tensorstore_index.json new file mode 100644 index 0000000000000000000000000000000000000000..5f79adfec17de46f3f6a5ad0129c7c48b9112719 --- /dev/null +++ b/tensorstore_index.json @@ -0,0 +1,3559 @@ +{ + "format": "tensorstore", + "version": "0.0.84", + "prefixes": { + "model": [ + { + "path": "model/lm_head/kernel", + "shape": [ + 2880, + 201088 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/embed_tokens/embedding", + "shape": [ + 201088, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/0/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/1/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/2/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/3/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/4/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/5/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/6/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/7/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/8/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/9/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/10/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/11/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/12/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/13/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/14/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/15/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/16/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/17/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/18/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/19/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/20/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/21/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/22/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/input_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/mlp/experts/down_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/mlp/experts/down_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/mlp/experts/gate_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/mlp/experts/gate_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/mlp/experts/up_proj/bias", + "shape": [ + 32, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/mlp/experts/up_proj/kernel", + "shape": [ + 32, + 2880, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/mlp/router/bias", + "shape": [ + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/mlp/router/kernel", + "shape": [ + 2880, + 32 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/post_attention_layernorm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/self_attn/k_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/self_attn/k_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/self_attn/o_proj/bias", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/self_attn/o_proj/kernel", + "shape": [ + 4096, + 2880 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/self_attn/q_proj/bias", + "shape": [ + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/self_attn/q_proj/kernel", + "shape": [ + 2880, + 4096 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/self_attn/sinks", + "shape": [ + 64 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/self_attn/v_proj/bias", + "shape": [ + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/layers/23/self_attn/v_proj/kernel", + "shape": [ + 2880, + 512 + ], + "dtype": "bfloat16" + }, + { + "path": "model/model/norm/kernel", + "shape": [ + 2880 + ], + "dtype": "bfloat16" + } + ] + } +} \ No newline at end of file