diff --git a/.gitattributes b/.gitattributes
index 03810bdf895f72462fa36616f5a53434226701c8..ad0eb45715faf6b662c60f55c0bd9ac3895c5104 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -39,3 +39,6 @@ llama32-1b-hf/harness_eval_8shot/__home__aiops__zhuty__nanotron__checkpoints__ll
 6000_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 6000_hf/harness_eval_8shot/__home__aiops__zhuty__nanotron__checkpoints__6000_hf/samples_gsm8k_2026-01-07T06-57-48.977156.jsonl filter=lfs diff=lfs merge=lfs -text
 6000_hf/harness_eval_0shot/__home__aiops__zhuty__nanotron__checkpoints__6000_hf/samples_hellaswag_2026-01-07T03-53-49.653886.jsonl filter=lfs diff=lfs merge=lfs -text
+9000_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+9000_hf/harness_eval_8shot/__home__aiops__zhuty__nanotron__checkpoints__9000_hf/samples_gsm8k_2026-01-07T07-00-26.302516.jsonl filter=lfs diff=lfs merge=lfs -text
+9000_hf/harness_eval_0shot/__home__aiops__zhuty__nanotron__checkpoints__9000_hf/samples_hellaswag_2026-01-07T03-49-27.696211.jsonl filter=lfs diff=lfs merge=lfs -text
diff --git a/9000_hf/harness_eval_0shot/__home__aiops__zhuty__nanotron__checkpoints__9000_hf/samples_hellaswag_2026-01-07T03-49-27.696211.jsonl b/9000_hf/harness_eval_0shot/__home__aiops__zhuty__nanotron__checkpoints__9000_hf/samples_hellaswag_2026-01-07T03-49-27.696211.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..6f9852f94db255f0304656c0d2d91acd430dbfaf
--- /dev/null
+++ b/9000_hf/harness_eval_0shot/__home__aiops__zhuty__nanotron__checkpoints__9000_hf/samples_hellaswag_2026-01-07T03-49-27.696211.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6c951352270e452953eddca955b7b91d59c444b0472e1b823783718174047f7
+size 42644980
diff --git a/9000_hf/harness_eval_8shot/__home__aiops__zhuty__nanotron__checkpoints__9000_hf/samples_gsm8k_2026-01-07T07-00-26.302516.jsonl b/9000_hf/harness_eval_8shot/__home__aiops__zhuty__nanotron__checkpoints__9000_hf/samples_gsm8k_2026-01-07T07-00-26.302516.jsonl
new file mode 100644
index 0000000000000000000000000000000000000000..b67087407c536f8e1a05c233f9b7047ca073fb2e
--- /dev/null
+++ b/9000_hf/harness_eval_8shot/__home__aiops__zhuty__nanotron__checkpoints__9000_hf/samples_gsm8k_2026-01-07T07-00-26.302516.jsonl
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e041e7a4dbb3adb96de2e754281310caaed9c4bfc59a9cfd708b88a5b9cef63
+size 16798564
diff --git a/9000_hf/model.safetensors b/9000_hf/model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..30e00bb81be2bb04a9a2914c749ed57ec5532e89
--- /dev/null
+++ b/9000_hf/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c90c55635cf0ceea9a88f2d3fed29e503b1f5641431a3b2a35a2c1b5dd3b71c
+size 2471645608
diff --git a/9000_hf/tokenizer.json b/9000_hf/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/9000_hf/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/llama32-1b-nt/model/model/decoder/0/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/0/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5d075231e1813d4986f33af95582cf14138f22d6
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/0/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcf8ec32f73c8df7edb3dd7727a9729d834dc2af9f5931b5d1b906df44c33b8d
+size 8388848
diff --git a/llama32-1b-nt/model/model/decoder/0/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/0/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c5eddf7cd47e6abea4d2f15719641f0335349c00
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/0/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01be991ceab7faf9d1a9ef49197c66cb138c5454b9ee1dcd68122fc2090fa2b3
+size 12583280
diff --git a/llama32-1b-nt/model/model/decoder/0/pp_block/input_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/0/pp_block/input_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..10cbf42d92181209848590a041fb43604291be87
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/0/pp_block/input_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7cea49eb581e94c8639be7b7241025a34e45665fc65ecd156eca82045a5381
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/0/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/0/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..85789ca495476713255b705a9c723bc31555e98c
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/0/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f8b68f6b1bbb164111f7cfe2dab91c22c523b3a085ea1130a3151357cb10529
+size 33554672
diff --git a/llama32-1b-nt/model/model/decoder/0/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/0/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3a2b168385362ca8f0e2c7127a7321c5017b6117
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/0/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01317c2dd8d23b2ae73991529701efa622052f5b799b451f8c0edbf5ee87f9dd
+size 67109176
diff --git a/llama32-1b-nt/model/model/decoder/0/pp_block/post_attention_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/0/pp_block/post_attention_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c858851804f0198d1103bad0b108d117a89e1cfb
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/0/pp_block/post_attention_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64db8ea88659d892d2fbe951e02eed87a9ab70629a5d60f0cceba4084d139e9c
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/1/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/1/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3845a951a59209eab79ba351cbf1bc647ecc035c
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/1/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f95ae205171c65231fdc326d0883bec0ed4650f1371f79e9a87200e7423cc2b
+size 8388848
diff --git a/llama32-1b-nt/model/model/decoder/1/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/1/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..783c95f1850fbf303c067e72b503707b2854c447
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/1/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aebcf09a0af1b43d7c2d085bc097c366b9f74575b6cf56d91c2d717e6787a25d
+size 12583280
diff --git a/llama32-1b-nt/model/model/decoder/1/pp_block/input_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/1/pp_block/input_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..40d6f8f7fb6bbcfd0cb44af6494ed12c4fc64bf0
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/1/pp_block/input_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2156f2df1e51d68b84ebaf5b0f12a853201adc0026642fb9b7bbef5c06a4ef7
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/1/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/1/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..ca7f2683be473cef145220111f787c65e0329d5d
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/1/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d5253ae1cd73f3308344ae2dccaadba5f59efca3deeba29073a29900d00987
+size 33554672
diff --git a/llama32-1b-nt/model/model/decoder/1/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/1/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..153f8e8ea61d0f674751ffbdf0bc910df55c1fb0
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/1/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41fb5a628feaf46caae796b955e9b508d2594a5096cf14a1f8fd4e5a4b86e3e6
+size 67109176
diff --git a/llama32-1b-nt/model/model/decoder/1/pp_block/post_attention_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/1/pp_block/post_attention_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7c742f15d10c8799b4111a25321d56210845aa2a
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/1/pp_block/post_attention_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71eb41eefe8ea9f1524dc9a8170e7d50f28deac6c5d216cf74192d125e497567
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/10/pp_block/input_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/10/pp_block/input_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d69b4caa77390e0b7ab9ce1fab6ae69ff0515607
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/10/pp_block/input_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:104343d2bf3568e998ffb42ca2146c24a82570944233c25d26c28b032ba27dae
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/10/pp_block/post_attention_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/10/pp_block/post_attention_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3a6b33f42663eace1c24d9ed36a939c0191c35ec
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/10/pp_block/post_attention_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b54bac7e7578f5ee0b3a8ba9ab9684016f538f65d2426eab2c31c0e9210abf6
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/12/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/12/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fe14b9f0795166b46343240ffd0edb3bf6bfd2fe
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/12/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29901b09c966155daa1cc1b2f0b6d4d9b51fbc8b3d96197688195ed0d7ffe27d
+size 8388848
diff --git a/llama32-1b-nt/model/model/decoder/12/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/12/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fc1a55dbbdda336891d3e2a76f4094dff95eea57
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/12/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1cf2c5ebbaf548e77e330958557e4b8df8bad02ccb59042388d48ce44302536
+size 12583280
diff --git a/llama32-1b-nt/model/model/decoder/12/pp_block/input_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/12/pp_block/input_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..482b8d55202d6037f51f443000eac19186b6461a
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/12/pp_block/input_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9468c20253d6e657931981408c6a387e3c4ffef4dd80e94b179d177c34797951
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/12/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/12/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..563ca545b3290232c7d2ad93ff05915e3cae271c
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/12/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3808ce3e24b90cedaf8e4c22991fd2070966e9303dae7fc57a1b96dfa7861833
+size 33554672
diff --git a/llama32-1b-nt/model/model/decoder/12/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/12/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..afa53c206c87a813f86d8d95ea04dd4dd6a9e7d3
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/12/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7befa5837d94145ca09d93f89430d65a827a2f409e98c523818bc3eff704c179
+size 67109176
diff --git a/llama32-1b-nt/model/model/decoder/12/pp_block/post_attention_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/12/pp_block/post_attention_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..da84470ae4680d764724f1bfa69fee5abfa362a7
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/12/pp_block/post_attention_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aa0a0483c4f9e9663792e40827ed48904751d24c9bd4a8e578d2cd11c42328b
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/13/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/13/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..70f0bb66818209d797737ff9489cc0bc0f095952
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/13/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5697969101bd979a80b7fb440385af088ae58fe5410c972ca25a1fb2e294d580
+size 8388848
diff --git a/llama32-1b-nt/model/model/decoder/13/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/13/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fbc146d0dcafa3bf980cdd613481da394ffa0f71
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/13/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c4a7a29176a102a8f9cf411a0bc042b5f2f97a1d1c236e624a9d06ef3bdd6c
+size 12583280
diff --git a/llama32-1b-nt/model/model/decoder/13/pp_block/input_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/13/pp_block/input_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4e11cffe2ff97a43f31c65f5188e25f6d9c5ca83
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/13/pp_block/input_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1587cc94039a6f2bcbf3a618b690d20e59ea52d4819fc49f900382b7f0e8b858
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/13/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/13/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..43fabfb0bd18224a53dd5a3d88d91a8151a23867
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/13/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbf8050b19aaf0c1501454fc16c44dd8c26f93d9859858915322f24ec8d88161
+size 33554672
diff --git a/llama32-1b-nt/model/model/decoder/13/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/13/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e591f8924d68207225269f7aa635dfa29f85083c
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/13/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ae1c6fdaba6f5847700be2e43055312c6ff97d54a3d599850b32cd275be8a5b
+size 67109176
diff --git a/llama32-1b-nt/model/model/decoder/13/pp_block/post_attention_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/13/pp_block/post_attention_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a8f5adc23f26b8c119d7ff2c763b8b3e1c723ff2
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/13/pp_block/post_attention_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d96a043ae27e520880693b9ae3c3fd3fe465b49b470e7565ea0176dcb5f9b03
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/15/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/15/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5f8e1f15ce6b89e491cb708d12c89be861149ef6
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/15/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6fde1b2d907fac5bc732d6f456ce1fde86df348350a1801e9572685d6d525dd
+size 8388848
diff --git a/llama32-1b-nt/model/model/decoder/15/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/15/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d15e41b71bad911fe4278683ea253112c88f08de
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/15/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf9902c1a5644e99e22a91171c2cbce04c2118d1ff556472b2dee704656b691f
+size 12583280
diff --git a/llama32-1b-nt/model/model/decoder/15/pp_block/input_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/15/pp_block/input_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..43e68dd96f2053d5fd1f3227e3425ab09f4fab4d
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/15/pp_block/input_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833077da913d352cf4f940f2ae912b3e966605aea5894397118c6b7798f83718
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/15/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/15/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0f7a37f1afa1ed7eb7fabba92b1a3d8960d9cb0a
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/15/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c26dcf52688014510235340347063d16642aa2eac1d837d3315388400137791d
+size 33554672
diff --git a/llama32-1b-nt/model/model/decoder/15/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/15/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..00e483bc4c01b28023f97c3d00e6f379277a3f81
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/15/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e774bc57792a81b328d939ceae2179458351cc36c1097bc2483786d5bc2d1c1
+size 67109176
diff --git a/llama32-1b-nt/model/model/decoder/15/pp_block/post_attention_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/15/pp_block/post_attention_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..e5e29dcb4463e09a0425c72491098d58e43b4026
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/15/pp_block/post_attention_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc313cf53ddad1eb093038d84c8c69667fb20816bb13088641e8e16bcd2f098b
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/4/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/4/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a332ac4417369acbfdadc7c4790f755776969c2b
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/4/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c122f0da7a1a04389dd9ee28927a481e3078a7d1d78e196e4a7ebe3a4ce3dea
+size 8388848
diff --git a/llama32-1b-nt/model/model/decoder/4/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/4/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1768c238873417286e764092eb6b966fcd91a9e2
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/4/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:965547dec7eba0f052e8b90170d43a813a4e60d2e9c9a585c7b79e00390112d5
+size 12583280
diff --git a/llama32-1b-nt/model/model/decoder/4/pp_block/input_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/4/pp_block/input_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f5336ec4f9d92fc3dcb8ee099e747dcacf8b7e14
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/4/pp_block/input_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:406cdadd5a55d620a9497e290330c744c8958e5c864f655cdff9574413c372ad
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/4/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/4/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7c400747ea3386ea1f98fda5f9639dda354f467c
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/4/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23b845a5002815f30a73162044270f8d4160c10f795ee4125f0a2e2bd918efac
+size 33554672
diff --git a/llama32-1b-nt/model/model/decoder/4/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/4/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9280120aebacc318d99f06e9aa921f02956519ff
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/4/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dea4deb2b747d546ca4311ca545d482b5f77a1ce7f42e594619389116b9c63f8
+size 67109176
diff --git a/llama32-1b-nt/model/model/decoder/4/pp_block/post_attention_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/4/pp_block/post_attention_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..a2e3c4db47f4b494b82bc0741d9f0d14ee21ccd5
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/4/pp_block/post_attention_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ff191398cbc507b7e1000dd81d9190fe794ed76296334212414257ed51b6efc
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/5/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/5/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..dbd5f71ed0034d988e080a8f26edcefbfcf3bfe4
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/5/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22750304d1b25c6bc07110cdd4e908b2b89315743715f6b0a5cba901fa452c81
+size 8388848
diff --git a/llama32-1b-nt/model/model/decoder/5/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/5/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5ddeb04333c02e855d9d112201b7f913c06ae91f
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/5/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:809054c9260ad3a88ef4697fbc36ece2019802c8d1733c93f4f1aef4c699c6c2
+size 12583280
diff --git a/llama32-1b-nt/model/model/decoder/5/pp_block/input_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/5/pp_block/input_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..83e7e61af89ef578a0635a2b8e9cb19b1a177068
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/5/pp_block/input_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9de58f7e0109dd72c4f3d84ff464b246607d8266965bdb883afc5f3211ed62fc
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/5/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/5/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3333656bc9880a092be3d4b3099014de63474a2c
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/5/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4a01bfdadfd9b0dc0e5abb2f4fe0b992ea163adcdb32d79defb746f61e88ce5
+size 33554672
diff --git a/llama32-1b-nt/model/model/decoder/5/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/5/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c642f23290c10d1e2f9d4809e903370f45a3b472
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/5/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a030cc63b1ca097d13c5b2eb7392eb16f9b474db4e03facd73e83c00e83226d5
+size 67109176
diff --git a/llama32-1b-nt/model/model/decoder/5/pp_block/post_attention_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/5/pp_block/post_attention_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5a572f60867b0dc7135b79e91224036e6e44d3e4
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/5/pp_block/post_attention_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4aa2cccdb5a23e5cf1f6bf1e346ee770308c6760971dcbc70b74ce8643228fe
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/7/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/7/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..34d2f3a9b932c6c8763dff09e4b56d3e99af9a2c
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/7/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ba6d5c261fd0078a04da858ad1ecbf74a06b76a6caa0fbab109b354383237ee
+size 8388848
diff --git a/llama32-1b-nt/model/model/decoder/7/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/7/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..1a0a68028751fbdf3edf58b67087835ec061a250
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/7/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0624eb8fded609fb9e66efae9546413ed3d0e168bf95cce776e3b810ec332e02
+size 12583280
diff --git a/llama32-1b-nt/model/model/decoder/7/pp_block/input_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/7/pp_block/input_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..518d356e5f328b6e8069569008a83686edfb539b
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/7/pp_block/input_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c02209b9c8085aa854ea49b839fa809cb023b4d206ac8fc5b62ceed89cba3f78
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/7/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/7/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..5c7c9c6dfa0be71963ebff500745876abe3cb318
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/7/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eba6f8454418c471307d36f3342b3d8c62f43d83621446379b43a23cbebebe7
+size 33554672
diff --git a/llama32-1b-nt/model/model/decoder/7/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/7/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..495146cc5f34cce1363de23fbdd02023b3073b28
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/7/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29863d99dd42cb9712704d45c3b7b17b4e656562dee5c6452ba3d92af91557d6
+size 67109176
diff --git a/llama32-1b-nt/model/model/decoder/7/pp_block/post_attention_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/7/pp_block/post_attention_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8439a56c2659e4d4cc2fa1eadf29df0ede446b52
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/7/pp_block/post_attention_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b47679dbd6163c91341a3c4c8e783b0c6f1fcd7320d766772990d4506f6363e9
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/9/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/9/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..84660a5d6c6534d1c4fc12f2ecd6ee393eaa8c20
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/9/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:957b1252f42e67eeebd290e90e8868b26d6aa7cd04586f65fdc1fc516e247e79
+size 8388848
diff --git a/llama32-1b-nt/model/model/decoder/9/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/9/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..425fb5870802251e0fc018a7a248ae66333a9eef
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/9/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4773e0d22333b1ac602bc9e608eca6c35f03a2121ac03cb353fbea2c3c027edf
+size 12583280
diff --git a/llama32-1b-nt/model/model/decoder/9/pp_block/input_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/9/pp_block/input_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..70ce186d9a9b2d747509844275049c3e4a8b489e
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/9/pp_block/input_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f39d56fd5cb4f70c18b32863bf30a21b7162da448487d574758b117cbe6ccb29
+size 4192
diff --git a/llama32-1b-nt/model/model/decoder/9/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/9/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..afcd907ef4324a01ba14951ca8232f3974f44211
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/9/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae3ce98cd49b54932bbb1e20e7104e1980ffedb8045545f743e82c4dbbd4bd64
+size 33554672
diff --git a/llama32-1b-nt/model/model/decoder/9/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-1b-nt/model/model/decoder/9/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3c77c6889a09e29ced6bdd311fe1fed22ec1f73f
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/9/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d519eed4981ec5eb981d0d2f079de453cf9be0caca471bd24c8c0c0c5c257d7
+size 67109176
diff --git a/llama32-1b-nt/model/model/decoder/9/pp_block/post_attention_layernorm/model_weight.safetensors b/llama32-1b-nt/model/model/decoder/9/pp_block/post_attention_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6483a8c3250acf082f7409d8a6f4b60f01470972
--- /dev/null
+++ b/llama32-1b-nt/model/model/decoder/9/pp_block/post_attention_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0243096b78faed933fadee5a31969c238cd34928ca73f9fd8259baf94232c70
+size 4192
diff --git a/llama32-3b-nt/model/model/decoder/23/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-3b-nt/model/model/decoder/23/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..7adb6251db4ae577197ca176541d99c7b21ffa9f
--- /dev/null
+++ b/llama32-3b-nt/model/model/decoder/23/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06bc3af9fae8d6ce8ebffca946cfec4ce1baa9927ed117331cb5936d09b0a538
+size 18874608
diff --git a/llama32-3b-nt/model/model/decoder/23/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-3b-nt/model/model/decoder/23/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..55193902a888812e0e583a42646e8267345633de
--- /dev/null
+++ b/llama32-3b-nt/model/model/decoder/23/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d701d0084e841f1557f7d3ac7ae9d43f4b495c9a081bd27f85d04ea4c6a10872
+size 31457648
diff --git a/llama32-3b-nt/model/model/decoder/23/pp_block/input_layernorm/model_weight.safetensors b/llama32-3b-nt/model/model/decoder/23/pp_block/input_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f67fcfc43efc4ecd2ccc7db31296cfbb519af80a
--- /dev/null
+++ b/llama32-3b-nt/model/model/decoder/23/pp_block/input_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:347df08ccd107aad9396fd8f29a7a623aed81700c461c79cb10652d28423fdf0
+size 6240
diff --git a/llama32-3b-nt/model/model/decoder/23/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-3b-nt/model/model/decoder/23/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d62463975ac4a33983d94799ebeb61c243e6b718
--- /dev/null
+++ b/llama32-3b-nt/model/model/decoder/23/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59de24bcd67d2e077995836a6cbbf672d1405188ac3c77b7ad7a4dfec23847bd
+size 50331888
diff --git a/llama32-3b-nt/model/model/decoder/23/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-3b-nt/model/model/decoder/23/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..98f8985a0bca732977bc9645606fd0fb56c1767f
--- /dev/null
+++ b/llama32-3b-nt/model/model/decoder/23/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:055e38ba29eb5e76275697f36d7f80434f932304b9d1610434f2072881183088
+size 100663608
diff --git a/llama32-3b-nt/model/model/decoder/23/pp_block/post_attention_layernorm/model_weight.safetensors b/llama32-3b-nt/model/model/decoder/23/pp_block/post_attention_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f664405ce6feb80b7d76904d0cc6130ed3b6dc2d
--- /dev/null
+++ b/llama32-3b-nt/model/model/decoder/23/pp_block/post_attention_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4347560d461d2c51b2f440941dbd7463ba55bd9f187594fb4751c38386920db
+size 6240
diff --git a/llama32-3b-nt/model/model/decoder/26/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-3b-nt/model/model/decoder/26/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..208083102df89c06902adc77db3ec0667a77e514
--- /dev/null
+++ b/llama32-3b-nt/model/model/decoder/26/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:570b0f79b7631d28a3a39e9fb292ef4936656c10ad818f8de1d6f38b898cf5cf
+size 18874608
diff --git a/llama32-3b-nt/model/model/decoder/26/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-3b-nt/model/model/decoder/26/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..fed057814e551717929725612546a2baf4b525cf
--- /dev/null
+++ b/llama32-3b-nt/model/model/decoder/26/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acfa8082320a212ed4d6a2802839cf19faf9dc214bfb4b9f014a28455fbdaeac
+size 31457648
diff --git a/llama32-3b-nt/model/model/decoder/26/pp_block/input_layernorm/model_weight.safetensors b/llama32-3b-nt/model/model/decoder/26/pp_block/input_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..71633ab2a9b9b0feec2957f5f6479ed2756023a3
--- /dev/null
+++ b/llama32-3b-nt/model/model/decoder/26/pp_block/input_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b89853355c54d7fce3b33e19b87126baf1ec028e67c06e030c23bc7a669c2a58
+size 6240
diff --git a/llama32-3b-nt/model/model/decoder/26/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-3b-nt/model/model/decoder/26/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8cc75b5d97e2fc323f7ca18ec01888f0d023735d
--- /dev/null
+++ b/llama32-3b-nt/model/model/decoder/26/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eef675dfbd7f7d14a1b0ccc129d5aa5b40f58e6eeede4a67098eb4147f5386fd
+size 50331888
diff --git a/llama32-3b-nt/model/model/decoder/26/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-3b-nt/model/model/decoder/26/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..9958a52024b6488e60c44e8163aada1e54c54dea
--- /dev/null
+++ b/llama32-3b-nt/model/model/decoder/26/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2d3ef5885d1384b27331852bef8c4979a36ba3b8e126660f71a16b6156d62ab
+size 100663608
diff --git a/llama32-3b-nt/model/model/decoder/26/pp_block/post_attention_layernorm/model_weight.safetensors b/llama32-3b-nt/model/model/decoder/26/pp_block/post_attention_layernorm/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3e4979d8d153ad15f336d8fddfa4498c0ea267bf
--- /dev/null
+++ b/llama32-3b-nt/model/model/decoder/26/pp_block/post_attention_layernorm/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a1c99bb29843d0206a12cb46540d5c5c69a428e3fd72d776ec65285f2f2b3b8
+size 6240
diff --git a/llama32-3b-nt/model/model/decoder/3/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-3b-nt/model/model/decoder/3/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..290a24c9aca076d718d316ddb638c09a80737ad8
--- /dev/null
+++ b/llama32-3b-nt/model/model/decoder/3/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b474d386732a42a424fd960dc0e442b27cbe40389f381508b90f7320de715773
+size 50331888
diff --git a/llama32-3b-nt/model/model/final_layer_norm/pp_block/model_weight.safetensors b/llama32-3b-nt/model/model/final_layer_norm/pp_block/model_weight.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..73d32fa0afa189bdb4d82d706b03fbfb704b2928
--- /dev/null
+++ b/llama32-3b-nt/model/model/final_layer_norm/pp_block/model_weight.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77bb24bab96b24334859af1c5751f264596baea8f5c08a928feb713078256953
+size 6240
diff --git a/llama32-3b-nt/model/model/token_position_embeddings/pp_block/token_embedding/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors b/llama32-3b-nt/model/model/token_position_embeddings/pp_block/token_embedding/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b521ac84d3781b9016b3c4e926775baaddb21ff3
--- /dev/null
+++ b/llama32-3b-nt/model/model/token_position_embeddings/pp_block/token_embedding/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a39abb76e8026af8150eaa95f12b3c058be5976e1b0f35a1704688637c3e54
+size 788005112