Hugging Face's logo

tyzhu
/
checkpoints

Safetensors
Model card Files
xet
 Community
tyzhu commited on
Commit
96faf34
·
verified ·
1 Parent(s): a8c5598

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +3 -0
  2. 9000_hf/harness_eval_0shot/__home__aiops__zhuty__nanotron__checkpoints__9000_hf/samples_hellaswag_2026-01-07T03-49-27.696211.jsonl +3 -0
  3. 9000_hf/harness_eval_8shot/__home__aiops__zhuty__nanotron__checkpoints__9000_hf/samples_gsm8k_2026-01-07T07-00-26.302516.jsonl +3 -0
  4. 9000_hf/model.safetensors +3 -0
  5. 9000_hf/tokenizer.json +3 -0
  6. 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 +3 -0
  7. 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 +3 -0
  8. llama32-1b-nt/model/model/decoder/0/pp_block/input_layernorm/model_weight.safetensors +3 -0
  9. 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 +3 -0
  10. 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 +3 -0
  11. llama32-1b-nt/model/model/decoder/0/pp_block/post_attention_layernorm/model_weight.safetensors +3 -0
  12. 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 +3 -0
  13. 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 +3 -0
  14. llama32-1b-nt/model/model/decoder/1/pp_block/input_layernorm/model_weight.safetensors +3 -0
  15. 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 +3 -0
  16. 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 +3 -0
  17. llama32-1b-nt/model/model/decoder/1/pp_block/post_attention_layernorm/model_weight.safetensors +3 -0
  18. llama32-1b-nt/model/model/decoder/10/pp_block/input_layernorm/model_weight.safetensors +3 -0
  19. llama32-1b-nt/model/model/decoder/10/pp_block/post_attention_layernorm/model_weight.safetensors +3 -0
  20. 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 +3 -0
  21. 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 +3 -0
  22. llama32-1b-nt/model/model/decoder/12/pp_block/input_layernorm/model_weight.safetensors +3 -0
  23. 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 +3 -0
  24. 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 +3 -0
  25. llama32-1b-nt/model/model/decoder/12/pp_block/post_attention_layernorm/model_weight.safetensors +3 -0
  26. 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 +3 -0
  27. 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 +3 -0
  28. llama32-1b-nt/model/model/decoder/13/pp_block/input_layernorm/model_weight.safetensors +3 -0
  29. 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 +3 -0
  30. 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 +3 -0
  31. llama32-1b-nt/model/model/decoder/13/pp_block/post_attention_layernorm/model_weight.safetensors +3 -0
  32. 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 +3 -0
  33. 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 +3 -0
  34. llama32-1b-nt/model/model/decoder/15/pp_block/input_layernorm/model_weight.safetensors +3 -0
  35. 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 +3 -0
  36. 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 +3 -0
  37. llama32-1b-nt/model/model/decoder/15/pp_block/post_attention_layernorm/model_weight.safetensors +3 -0
  38. 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 +3 -0
  39. 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 +3 -0
  40. llama32-1b-nt/model/model/decoder/4/pp_block/input_layernorm/model_weight.safetensors +3 -0
  41. 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 +3 -0
  42. 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 +3 -0
  43. llama32-1b-nt/model/model/decoder/4/pp_block/post_attention_layernorm/model_weight.safetensors +3 -0
  44. 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 +3 -0
  45. 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 +3 -0
  46. llama32-1b-nt/model/model/decoder/5/pp_block/input_layernorm/model_weight.safetensors +3 -0
  47. 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 +3 -0
  48. 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 +3 -0
  49. llama32-1b-nt/model/model/decoder/5/pp_block/post_attention_layernorm/model_weight.safetensors +3 -0
  50. 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 +3 -0
.gitattributes CHANGED
@@ -39,3 +39,6 @@ llama32-1b-hf/harness_eval_8shot/__home__aiops__zhuty__nanotron__checkpoints__ll
39
  6000_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  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
41
  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
 
 
 
 
39
  6000_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
40
  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
41
  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
42
+ 9000_hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
43
+ 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
44
+ 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
9000_hf/harness_eval_0shot/__home__aiops__zhuty__nanotron__checkpoints__9000_hf/samples_hellaswag_2026-01-07T03-49-27.696211.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6c951352270e452953eddca955b7b91d59c444b0472e1b823783718174047f7
3
+ size 42644980
9000_hf/harness_eval_8shot/__home__aiops__zhuty__nanotron__checkpoints__9000_hf/samples_gsm8k_2026-01-07T07-00-26.302516.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e041e7a4dbb3adb96de2e754281310caaed9c4bfc59a9cfd708b88a5b9cef63
3
+ size 16798564
9000_hf/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c90c55635cf0ceea9a88f2d3fed29e503b1f5641431a3b2a35a2c1b5dd3b71c
3
+ size 2471645608
9000_hf/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcf8ec32f73c8df7edb3dd7727a9729d834dc2af9f5931b5d1b906df44c33b8d
3
+ size 8388848
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01be991ceab7faf9d1a9ef49197c66cb138c5454b9ee1dcd68122fc2090fa2b3
3
+ size 12583280
llama32-1b-nt/model/model/decoder/0/pp_block/input_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f7cea49eb581e94c8639be7b7241025a34e45665fc65ecd156eca82045a5381
3
+ size 4192
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f8b68f6b1bbb164111f7cfe2dab91c22c523b3a085ea1130a3151357cb10529
3
+ size 33554672
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01317c2dd8d23b2ae73991529701efa622052f5b799b451f8c0edbf5ee87f9dd
3
+ size 67109176
llama32-1b-nt/model/model/decoder/0/pp_block/post_attention_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64db8ea88659d892d2fbe951e02eed87a9ab70629a5d60f0cceba4084d139e9c
3
+ size 4192
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f95ae205171c65231fdc326d0883bec0ed4650f1371f79e9a87200e7423cc2b
3
+ size 8388848
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aebcf09a0af1b43d7c2d085bc097c366b9f74575b6cf56d91c2d717e6787a25d
3
+ size 12583280
llama32-1b-nt/model/model/decoder/1/pp_block/input_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2156f2df1e51d68b84ebaf5b0f12a853201adc0026642fb9b7bbef5c06a4ef7
3
+ size 4192
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0d5253ae1cd73f3308344ae2dccaadba5f59efca3deeba29073a29900d00987
3
+ size 33554672
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41fb5a628feaf46caae796b955e9b508d2594a5096cf14a1f8fd4e5a4b86e3e6
3
+ size 67109176
llama32-1b-nt/model/model/decoder/1/pp_block/post_attention_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71eb41eefe8ea9f1524dc9a8170e7d50f28deac6c5d216cf74192d125e497567
3
+ size 4192
llama32-1b-nt/model/model/decoder/10/pp_block/input_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:104343d2bf3568e998ffb42ca2146c24a82570944233c25d26c28b032ba27dae
3
+ size 4192
llama32-1b-nt/model/model/decoder/10/pp_block/post_attention_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b54bac7e7578f5ee0b3a8ba9ab9684016f538f65d2426eab2c31c0e9210abf6
3
+ size 4192
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29901b09c966155daa1cc1b2f0b6d4d9b51fbc8b3d96197688195ed0d7ffe27d
3
+ size 8388848
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1cf2c5ebbaf548e77e330958557e4b8df8bad02ccb59042388d48ce44302536
3
+ size 12583280
llama32-1b-nt/model/model/decoder/12/pp_block/input_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9468c20253d6e657931981408c6a387e3c4ffef4dd80e94b179d177c34797951
3
+ size 4192
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3808ce3e24b90cedaf8e4c22991fd2070966e9303dae7fc57a1b96dfa7861833
3
+ size 33554672
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7befa5837d94145ca09d93f89430d65a827a2f409e98c523818bc3eff704c179
3
+ size 67109176
llama32-1b-nt/model/model/decoder/12/pp_block/post_attention_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3aa0a0483c4f9e9663792e40827ed48904751d24c9bd4a8e578d2cd11c42328b
3
+ size 4192
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5697969101bd979a80b7fb440385af088ae58fe5410c972ca25a1fb2e294d580
3
+ size 8388848
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37c4a7a29176a102a8f9cf411a0bc042b5f2f97a1d1c236e624a9d06ef3bdd6c
3
+ size 12583280
llama32-1b-nt/model/model/decoder/13/pp_block/input_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1587cc94039a6f2bcbf3a618b690d20e59ea52d4819fc49f900382b7f0e8b858
3
+ size 4192
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbf8050b19aaf0c1501454fc16c44dd8c26f93d9859858915322f24ec8d88161
3
+ size 33554672
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ae1c6fdaba6f5847700be2e43055312c6ff97d54a3d599850b32cd275be8a5b
3
+ size 67109176
llama32-1b-nt/model/model/decoder/13/pp_block/post_attention_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d96a043ae27e520880693b9ae3c3fd3fe465b49b470e7565ea0176dcb5f9b03
3
+ size 4192
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6fde1b2d907fac5bc732d6f456ce1fde86df348350a1801e9572685d6d525dd
3
+ size 8388848
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf9902c1a5644e99e22a91171c2cbce04c2118d1ff556472b2dee704656b691f
3
+ size 12583280
llama32-1b-nt/model/model/decoder/15/pp_block/input_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:833077da913d352cf4f940f2ae912b3e966605aea5894397118c6b7798f83718
3
+ size 4192
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c26dcf52688014510235340347063d16642aa2eac1d837d3315388400137791d
3
+ size 33554672
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e774bc57792a81b328d939ceae2179458351cc36c1097bc2483786d5bc2d1c1
3
+ size 67109176
llama32-1b-nt/model/model/decoder/15/pp_block/post_attention_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc313cf53ddad1eb093038d84c8c69667fb20816bb13088641e8e16bcd2f098b
3
+ size 4192
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c122f0da7a1a04389dd9ee28927a481e3078a7d1d78e196e4a7ebe3a4ce3dea
3
+ size 8388848
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:965547dec7eba0f052e8b90170d43a813a4e60d2e9c9a585c7b79e00390112d5
3
+ size 12583280
llama32-1b-nt/model/model/decoder/4/pp_block/input_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:406cdadd5a55d620a9497e290330c744c8958e5c864f655cdff9574413c372ad
3
+ size 4192
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23b845a5002815f30a73162044270f8d4160c10f795ee4125f0a2e2bd918efac
3
+ size 33554672
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dea4deb2b747d546ca4311ca545d482b5f77a1ce7f42e594619389116b9c63f8
3
+ size 67109176
llama32-1b-nt/model/model/decoder/4/pp_block/post_attention_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ff191398cbc507b7e1000dd81d9190fe794ed76296334212414257ed51b6efc
3
+ size 4192
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22750304d1b25c6bc07110cdd4e908b2b89315743715f6b0a5cba901fa452c81
3
+ size 8388848
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:809054c9260ad3a88ef4697fbc36ece2019802c8d1733c93f4f1aef4c699c6c2
3
+ size 12583280
llama32-1b-nt/model/model/decoder/5/pp_block/input_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9de58f7e0109dd72c4f3d84ff464b246607d8266965bdb883afc5f3211ed62fc
3
+ size 4192
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4a01bfdadfd9b0dc0e5abb2f4fe0b992ea163adcdb32d79defb746f61e88ce5
3
+ size 33554672
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a030cc63b1ca097d13c5b2eb7392eb16f9b474db4e03facd73e83c00e83226d5
3
+ size 67109176
llama32-1b-nt/model/model/decoder/5/pp_block/post_attention_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4aa2cccdb5a23e5cf1f6bf1e346ee770308c6760971dcbc70b74ce8643228fe
3
+ size 4192
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ba6d5c261fd0078a04da858ad1ecbf74a06b76a6caa0fbab109b354383237ee
3
+ size 8388848