Hugging Face's logo

tyzhu
/
checkpoints

Safetensors
Model card Files
xet
 Community
tyzhu commited on
Commit
a8c5598
·
verified ·
1 Parent(s): 25de0f9

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 +6 -0
  2. 6000_hf/harness_eval_0shot/__home__aiops__zhuty__nanotron__checkpoints__6000_hf/samples_hellaswag_2026-01-07T03-53-49.653886.jsonl +3 -0
  3. 6000_hf/harness_eval_8shot/__home__aiops__zhuty__nanotron__checkpoints__6000_hf/samples_gsm8k_2026-01-07T06-57-48.977156.jsonl +3 -0
  4. 6000_hf/model.safetensors +3 -0
  5. 6000_hf/tokenizer.json +3 -0
  6. llama32-1b-hf/harness_eval_8shot/__home__aiops__zhuty__nanotron__checkpoints__llama32-1b-hf/samples_gsm8k_2025-12-29T05-09-52.015180.jsonl +3 -0
  7. llama32-1b-hf/model.safetensors +3 -0
  8. llama32-1b-hf/tokenizer.json +3 -0
  9. llama32-1b-nt/model/model/decoder/10/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  10. llama32-1b-nt/model/model/decoder/10/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  11. llama32-1b-nt/model/model/decoder/10/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  12. llama32-1b-nt/model/model/decoder/10/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  13. llama32-1b-nt/model/model/decoder/11/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  14. llama32-1b-nt/model/model/decoder/11/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  15. llama32-1b-nt/model/model/decoder/11/pp_block/input_layernorm/model_weight.safetensors +3 -0
  16. llama32-1b-nt/model/model/decoder/11/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  17. llama32-1b-nt/model/model/decoder/11/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  18. llama32-1b-nt/model/model/decoder/11/pp_block/post_attention_layernorm/model_weight.safetensors +3 -0
  19. llama32-1b-nt/model/model/decoder/14/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  20. llama32-1b-nt/model/model/decoder/14/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  21. llama32-1b-nt/model/model/decoder/14/pp_block/input_layernorm/model_weight.safetensors +3 -0
  22. llama32-1b-nt/model/model/decoder/14/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  23. llama32-1b-nt/model/model/decoder/14/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  24. llama32-1b-nt/model/model/decoder/14/pp_block/post_attention_layernorm/model_weight.safetensors +3 -0
  25. llama32-1b-nt/model/model/decoder/2/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  26. llama32-1b-nt/model/model/decoder/2/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  27. llama32-1b-nt/model/model/decoder/2/pp_block/input_layernorm/model_weight.safetensors +3 -0
  28. llama32-1b-nt/model/model/decoder/2/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  29. llama32-1b-nt/model/model/decoder/2/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  30. llama32-1b-nt/model/model/decoder/2/pp_block/post_attention_layernorm/model_weight.safetensors +3 -0
  31. llama32-1b-nt/model/model/decoder/3/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  32. llama32-1b-nt/model/model/decoder/3/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  33. llama32-1b-nt/model/model/decoder/3/pp_block/input_layernorm/model_weight.safetensors +3 -0
  34. llama32-1b-nt/model/model/decoder/3/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  35. llama32-1b-nt/model/model/decoder/3/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  36. llama32-1b-nt/model/model/decoder/3/pp_block/post_attention_layernorm/model_weight.safetensors +3 -0
  37. llama32-1b-nt/model/model/decoder/6/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  38. llama32-1b-nt/model/model/decoder/6/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  39. llama32-1b-nt/model/model/decoder/6/pp_block/input_layernorm/model_weight.safetensors +3 -0
  40. llama32-1b-nt/model/model/decoder/6/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  41. llama32-1b-nt/model/model/decoder/6/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  42. llama32-1b-nt/model/model/decoder/6/pp_block/post_attention_layernorm/model_weight.safetensors +3 -0
  43. llama32-1b-nt/model/model/decoder/8/pp_block/attn/o_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  44. llama32-1b-nt/model/model/decoder/8/pp_block/attn/qkv_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  45. llama32-1b-nt/model/model/decoder/8/pp_block/input_layernorm/model_weight.safetensors +3 -0
  46. llama32-1b-nt/model/model/decoder/8/pp_block/mlp/down_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  47. llama32-1b-nt/model/model/decoder/8/pp_block/mlp/gate_up_proj/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
  48. llama32-1b-nt/model/model/decoder/8/pp_block/post_attention_layernorm/model_weight.safetensors +3 -0
  49. llama32-1b-nt/model/model/final_layer_norm/pp_block/model_weight.safetensors +3 -0
  50. llama32-1b-nt/model/model/token_position_embeddings/pp_block/token_embedding/model_weight_pp-rank-0-of-1_tp-rank-0-of-1.safetensors +3 -0
.gitattributes CHANGED
@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ performance_plot.png filter=lfs diff=lfs merge=lfs -text
37
+ llama32-1b-hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ llama32-1b-hf/harness_eval_8shot/__home__aiops__zhuty__nanotron__checkpoints__llama32-1b-hf/samples_gsm8k_2025-12-29T05-09-52.015180.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
6000_hf/harness_eval_0shot/__home__aiops__zhuty__nanotron__checkpoints__6000_hf/samples_hellaswag_2026-01-07T03-53-49.653886.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c87d614af3012456bc55d5fa3494796ef87ae4e88613eca380be3ef225f01836
3
+ size 42644354
6000_hf/harness_eval_8shot/__home__aiops__zhuty__nanotron__checkpoints__6000_hf/samples_gsm8k_2026-01-07T06-57-48.977156.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cbe7caf99c6b35e29595f9064ca49bed676523e4667c27e5b5f63987749f788
3
+ size 16787503
6000_hf/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aad16ad9e4e169e94cd7d1f89556300d5f2a656932b5c69c1b8fabd8a9a75477
3
+ size 2471645608
6000_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-hf/harness_eval_8shot/__home__aiops__zhuty__nanotron__checkpoints__llama32-1b-hf/samples_gsm8k_2025-12-29T05-09-52.015180.jsonl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f75192a00e0b1cb90d03c7ad57e4f284bffaca99894fbc40cd9bf163fd836498
3
+ size 16912314
llama32-1b-hf/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68a2e4be76fa709455a60272fba8e512c02d81c46e6c671cc9449e374fd6809a
3
+ size 2471645608
llama32-1b-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/10/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 sha256:3d0276741f3e26b94d3d4aadf34a3e5fef3aa00474baec888035a9f92022f881
3
+ size 8388848
llama32-1b-nt/model/model/decoder/10/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:b85709f23aaa73da6fcf30f4756b915d72271fc6d0129738c5974da9af23dde2
3
+ size 12583280
llama32-1b-nt/model/model/decoder/10/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 sha256:9f8a340447658116f99ec5a15aa2c53a20b8bb996ab4df8ae47cb9d882419019
3
+ size 33554672
llama32-1b-nt/model/model/decoder/10/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 sha256:1c33e2e540288c275e7d9915f1ce636797818c6fac458e6f8e150cda2db3b0d4
3
+ size 67109176
llama32-1b-nt/model/model/decoder/11/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:efc478a3d60fcac1e467a70373dd59b334bcb558e15e0215eb0d1c792b50972b
3
+ size 8388848
llama32-1b-nt/model/model/decoder/11/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:b883091770f2faa56fc0e2b09320e8175769972ead464467a7bef58e94db3eb0
3
+ size 12583280
llama32-1b-nt/model/model/decoder/11/pp_block/input_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e185d81c06bfd748aa9ad4022e23930d1924caf8690e6dcf26a42950f361b3a
3
+ size 4192
llama32-1b-nt/model/model/decoder/11/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 sha256:15488f05be50f1a666cc239bcbb5e73d57ce6d7994779fab0b7c07a4aa6b0cd9
3
+ size 33554672
llama32-1b-nt/model/model/decoder/11/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:e6875bdf65c020bb9ae736e0e56be3ffe2366503db1f80feb92fee5a80b83e97
3
+ size 67109176
llama32-1b-nt/model/model/decoder/11/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:a8897195a2355e257c436d311188af105551e6a7f7a22394d9087b73910e4b17
3
+ size 4192
llama32-1b-nt/model/model/decoder/14/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:d4a9a04f2dd01d7e2bb41bb465b9631931a731d01c0bd58eb0e161fe65cbc9e8
3
+ size 8388848
llama32-1b-nt/model/model/decoder/14/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 sha256:0f0193bb4e3d2075f27e8db32256e41ad84077a0ba6e90b3fd7713eb88b645b6
3
+ size 12583280
llama32-1b-nt/model/model/decoder/14/pp_block/input_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a2996fbd4c66b207a25eff8714789c83a0503d12e6589d8d2d49c77d6bd91af
3
+ size 4192
llama32-1b-nt/model/model/decoder/14/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 sha256:636500da5ccedc8b09aa281e05544841414ef06dc70c2b562415b8e77acdb880
3
+ size 33554672
llama32-1b-nt/model/model/decoder/14/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 sha256:6709249cd1313d73a34201c7d76f1b7bb491b0a3a0ede9532db9023b5ceba099
3
+ size 67109176
llama32-1b-nt/model/model/decoder/14/pp_block/post_attention_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3312605d121d07226257fef5622100befa51609223c091269e0ab3d6490ff18d
3
+ size 4192
llama32-1b-nt/model/model/decoder/2/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 sha256:171857c49d3140c306198ee94dea845310ab698534112725badec082f5a561b5
3
+ size 8388848
llama32-1b-nt/model/model/decoder/2/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 sha256:4c0852c03a66d037da408614141157d8badf0fd97ea6d1004f683e4cfe024ba0
3
+ size 12583280
llama32-1b-nt/model/model/decoder/2/pp_block/input_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43057a8976243fd952b5c1311112e5b925fe5554fc5ef4cc8823e6f9e3f777b2
3
+ size 4192
llama32-1b-nt/model/model/decoder/2/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:c92b38a363a5f534b727d6870cb5563defd8fd4de54aa7b1fec4c6fb8facd647
3
+ size 33554672
llama32-1b-nt/model/model/decoder/2/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:e4589939c6928c030b6f01dfe84458c237e9d185c9fd6ee2cb1cd3acc2f106e0
3
+ size 67109176
llama32-1b-nt/model/model/decoder/2/pp_block/post_attention_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:072978f2f75de4c89ec3b5953c96e06261ec69049f14e8af0c1e4b62bb9eae1d
3
+ size 4192
llama32-1b-nt/model/model/decoder/3/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 sha256:5207f7d2c950a584c8e24d60559dd5252e49df61ecefe692a72cb87c8fa43a7f
3
+ size 8388848
llama32-1b-nt/model/model/decoder/3/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 sha256:1d9df03e74515b298a1aafc56e97c834730d6858fb3840bded1b1b67272c480f
3
+ size 12583280
llama32-1b-nt/model/model/decoder/3/pp_block/input_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5769e58de93ff20eb5e96bc037539de77be4ec0ea6594e4f88edda3f58fd885f
3
+ size 4192
llama32-1b-nt/model/model/decoder/3/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:c3c9cc6ee995c91ef494b5ecd3d381c7af101aaf48ac68d27a21d13dfe446478
3
+ size 33554672
llama32-1b-nt/model/model/decoder/3/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 sha256:17b1a3cbadaf87ae16ea63b53b9b955235e18631c6cc7e78e3a3d57cd180ae85
3
+ size 67109176
llama32-1b-nt/model/model/decoder/3/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:cf50392c6293f7a006a9a04e984802988fdccbc6d5be3e2b9d3159c58608f7e1
3
+ size 4192
llama32-1b-nt/model/model/decoder/6/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:d5e328528b9b0f77f62a817e46fcf38caca64900de14497ae5b3ac780a9917a3
3
+ size 8388848
llama32-1b-nt/model/model/decoder/6/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:ca8c38229d901f63f92064308f9361a279c0ceb0d264a36195aa96ba0131e37f
3
+ size 12583280
llama32-1b-nt/model/model/decoder/6/pp_block/input_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a41f7915085e2e6ba53d4cc7f2f4ca8f16ce0f7bacd206374b8c8fdb659b5c74
3
+ size 4192
llama32-1b-nt/model/model/decoder/6/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 sha256:65e5366a16839e15b111d7f057c9665d78e4fb115f2653fbd2c974cc160e9bd9
3
+ size 33554672
llama32-1b-nt/model/model/decoder/6/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:eb74f375f385133c7181a2f179c9f6d94c0c045ed53c3d002bd618ebdd0cc5a6
3
+ size 67109176
llama32-1b-nt/model/model/decoder/6/pp_block/post_attention_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cd7bba3f6d9b1bb8411711c5e38247ad952ff395409ac998af799dff9d74be7
3
+ size 4192
llama32-1b-nt/model/model/decoder/8/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 sha256:1ae785305037ba13386d8bb00a934f49cfb6b3dbf4c4d31b2038f5b06f45431a
3
+ size 8388848
llama32-1b-nt/model/model/decoder/8/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 sha256:8302e2113e0b301d0d372bcaac546566162e6ab992284e4e2f8aa63fd525656b
3
+ size 12583280
llama32-1b-nt/model/model/decoder/8/pp_block/input_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55dd4e252b319d9ee38c014f942165ebbe45738f22660a84815a75733b55da4f
3
+ size 4192
llama32-1b-nt/model/model/decoder/8/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:debdba6aebfa8de486578d40deae3687bc3a5340c6c4d825f8024ad3ada37080
3
+ size 33554672
llama32-1b-nt/model/model/decoder/8/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:e61b0b7e1c09d6e8c7141fcc8e8dae162201c137c1fbaa1910132e2378fb4ac5
3
+ size 67109176
llama32-1b-nt/model/model/decoder/8/pp_block/post_attention_layernorm/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:993d1ca1d195240e987db38c439e4d22e350005771269be85f66b9e05d8e6def
3
+ size 4192
llama32-1b-nt/model/model/final_layer_norm/pp_block/model_weight.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0bfbd9ba193878c85f567333eb8152849ea503fde1869bd4bd41f756508c291
3
+ size 4192
llama32-1b-nt/model/model/token_position_embeddings/pp_block/token_embedding/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 sha256:96fbd336e85cf6f1cf5c09515443e251a65b10b6636f5105ba59809614a3d09f
3
+ size 525336824