Qwen3.5-27B / .gitattributes
erfanzar's picture
Upload tokenizer
e9e8f37 verified
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz 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/visual/blocks/21/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/6/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/pos_embed/embedding/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/21/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/21/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/21/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/pos_embed/embedding/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/21/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/6/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/21/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/21/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/6/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/pos_embed/embedding/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/21/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/21/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/21/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/merger/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/21/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/21/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/6/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/merger/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/merger/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/pos_embed/embedding/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/merger/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/merger/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/merger/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/merger/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/6/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/21/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/merger/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/21/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/21/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/21/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/patch_embed/proj/kernel/0.0.0.0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/8/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/0/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/2/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/3/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/5/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/4/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/6/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/7/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/9/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/10/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/11/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/12/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/13/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/14/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/15/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/16/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/17/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/18/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/19/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/20/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/21/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/22/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/30/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/31/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/32/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/lm_head/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/lm_head/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/embed_tokens/embedding/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/28/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/29/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/embed_tokens/embedding/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/embed_tokens/embedding/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/lm_head/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/42/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/lm_head/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/45/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/23/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/24/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/25/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/26/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/27/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/26/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/23/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/26/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/26/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/26/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/26/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/26/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/26/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/26/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/6/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/26/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/6/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/26/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/6/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/6/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/26/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/6/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/6/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/6/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/6/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/6/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/6/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/6/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/39/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/40/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/41/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/43/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/38/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/44/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/47/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/48/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/50/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/33/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/34/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/embed_tokens/embedding/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/36/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/37/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/35/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/9/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/10/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/10/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/8/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/10/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/9/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/9/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/8/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/10/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/9/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/10/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/9/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/9/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/9/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/16/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/10/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/10/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/10/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/10/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/10/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/8/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/10/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/9/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/16/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/16/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/16/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/16/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/16/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/16/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/10/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/9/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/16/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/16/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/16/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/16/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/16/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/10/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/10/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/3/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/16/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/16/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/3/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/16/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/3/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/3/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/3/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/3/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/3/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/49/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/46/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/18/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/10/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/18/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/16/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/3/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/3/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/3/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/3/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/3/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/3/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/18/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/3/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/18/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/18/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/18/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/18/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/18/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/18/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/18/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/3/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/18/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/3/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/18/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/11/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/11/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/17/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/17/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/17/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/17/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/17/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/17/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/18/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/18/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/17/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/18/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/17/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/17/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/11/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/11/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/18/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/17/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/17/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/22/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/13/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/22/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/22/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/12/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/22/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/22/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/13/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/22/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/22/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/13/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/20/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/22/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/22/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/22/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/13/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/20/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/22/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/20/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/20/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/20/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/22/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/20/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/20/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/22/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/20/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/20/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/20/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/20/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/22/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/22/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/20/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/15/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/20/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/22/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/20/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/20/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/15/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/15/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/20/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/15/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/15/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/15/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/15/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/15/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/5/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/5/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/5/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/7/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/7/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/7/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/5/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/7/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/5/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/7/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/7/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/7/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/8/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/8/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/7/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/8/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/7/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/5/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/7/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/8/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/7/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/8/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/7/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/5/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/9/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/9/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/7/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/8/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/8/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/9/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/9/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/9/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/8/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/8/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/9/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/9/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/8/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/8/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/8/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/10/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/8/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/17/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/17/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/11/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/11/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/12/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/17/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/17/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/11/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/11/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/11/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/11/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/12/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/11/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/11/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/12/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/12/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/17/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/11/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/12/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/12/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/11/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/11/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/12/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/12/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/11/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/12/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/12/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/12/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/12/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/12/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/12/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/13/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/12/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/13/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/13/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/13/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/13/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/13/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/13/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/13/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/13/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/13/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/13/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/13/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/52/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/51/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/54/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/59/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/53/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/56/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/61/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/57/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/2/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/2/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/2/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/2/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/2/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/2/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/2/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/2/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/2/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/2/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/2/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/2/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/2/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/2/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/0/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/0/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/0/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/0/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/0/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/0/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/0/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/0/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/4/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/4/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/0/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/0/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/0/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/4/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/4/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/0/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/24/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/19/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/14/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/19/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/19/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/25/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/19/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/19/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/19/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/25/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/25/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/25/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/25/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/25/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/19/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/19/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/25/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/25/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/19/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/25/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/25/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/25/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/23/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/25/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/23/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/23/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/23/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/23/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/25/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/25/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/25/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/23/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/23/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/23/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/23/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/26/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/23/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/26/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/26/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/23/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/26/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/23/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/26/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/23/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/23/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/23/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/4/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/4/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/4/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/0/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/4/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/4/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/0/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/4/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/1/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/4/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/0/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/0/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/4/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/1/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/1/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/1/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/4/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/4/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/1/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/1/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/1/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/1/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/1/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/1/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/5/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/1/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/1/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/1/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/5/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/4/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/5/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/1/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/1/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/1/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/5/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/5/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/4/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/5/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/5/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/7/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/5/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/7/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/7/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/5/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/55/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/58/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/62/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/60/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/2/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/layers/63/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/2/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/15/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/14/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/15/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/15/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/15/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/14/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/15/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/15/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/15/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/15/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/14/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/14/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/14/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/14/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/14/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/24/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/14/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/24/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/24/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/14/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/24/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/14/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/24/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/24/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/14/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/14/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/14/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/14/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/24/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/24/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/14/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/24/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/24/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/24/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/24/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/19/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/19/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/19/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/24/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/19/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/19/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/24/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/24/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/25/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/19/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
model/model/visual/blocks/19/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text