Hugging Face's logo

koichi12
/
llm_tutorial

Model card Files
xet
Community
koichi12 commited on
Commit
e26479f
·
verified ·
1 Parent(s): 69a7829

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. llm_tutorial/eval/results/Qwen/Qwen2-1.5B.json +0 -0
  3. llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document.bin +3 -0
  4. llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document/cache/GPTDataset_indices/80d7dc88bf2d24bda8780c0ade9232eb-GPTDataset-description.txt +10 -0
  5. llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document/cache/GPTDataset_indices/80d7dc88bf2d24bda8780c0ade9232eb-GPTDataset-sample_index.npy +3 -0
  6. llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document/cache/GPTDataset_indices/80d7dc88bf2d24bda8780c0ade9232eb-GPTDataset-shuffle_index.npy +3 -0
  7. llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document/cache/GPTDataset_indices/853745364fb2fbc2666f7cb226ba389e-GPTDataset-description.txt +10 -0
  8. llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document/cache/GPTDataset_indices/853745364fb2fbc2666f7cb226ba389e-GPTDataset-document_index.npy +3 -0
  9. llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document/cache/GPTDataset_indices/853745364fb2fbc2666f7cb226ba389e-GPTDataset-sample_index.npy +3 -0
  10. llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document/cache/GPTDataset_indices/853745364fb2fbc2666f7cb226ba389e-GPTDataset-shuffle_index.npy +3 -0
  11. llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_processed_log.json +30 -0
  12. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document.idx +3 -0
  13. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/40b0757666be5879d4957ef001f2548f-GPTDataset-sample_index.npy +3 -0
  14. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/4c5ba66133c100eed2605c1788c35aed-GPTDataset-document_index.npy +3 -0
  15. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/74eba84f8d67c7b4de5c9dbe6e06ad05-GPTDataset-description.txt +10 -0
  16. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/83b6a7444f9036329af9611109011086-GPTDataset-description.txt +10 -0
  17. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/83b6a7444f9036329af9611109011086-GPTDataset-document_index.npy +3 -0
  18. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/90a0209287c09d4fb8c349ec9c0e0e23-GPTDataset-description.txt +10 -0
  19. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/acc018e9317275205756d04e6d7b900a-GPTDataset-document_index.npy +3 -0
  20. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/acc018e9317275205756d04e6d7b900a-GPTDataset-shuffle_index.npy +3 -0
  21. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/b7582ab95f7384b0fa67902e8323964e-GPTDataset-description.txt +10 -0
  22. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/b7582ab95f7384b0fa67902e8323964e-GPTDataset-document_index.npy +3 -0
  23. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/b7582ab95f7384b0fa67902e8323964e-GPTDataset-shuffle_index.npy +3 -0
  24. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_processed_log.json +30 -0
  25. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train/data_text_processed_log.json +30 -0
  26. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/1f75c8bdc2b9f34c2d0db923cfbe2ae8-GPTDataset-description.txt +10 -0
  27. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/3939b211f79586cf3c33deedcc9a5c78-GPTDataset-description.txt +10 -0
  28. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/6a9e50c6fa3dc30f0d28bf9ed35427a8-GPTDataset-description.txt +10 -0
  29. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/6c93d136579c889dc7737f37a743ad31-GPTDataset-description.txt +10 -0
  30. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/dfe930f22c36ea35668c4345e9143dda-GPTDataset-description.txt +10 -0
  31. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/dfe930f22c36ea35668c4345e9143dda-GPTDataset-document_index.npy +3 -0
  32. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/dfe930f22c36ea35668c4345e9143dda-GPTDataset-sample_index.npy +3 -0
  33. llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_processed_log.json +30 -0
  34. llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-instruct_3M-pairs/iter_0000698/config.json +29 -0
  35. llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-instruct_3M-pairs/iter_0000698/generation_config.json +6 -0
  36. llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-instruct_3M-pairs/iter_0000698/model.safetensors.index.json +262 -0
  37. llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-instruct_3M-pairs/iter_0000698/special_tokens_map.json +51 -0
  38. llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-instruct_3M-pairs/iter_0000698/tokenizer.json +0 -0
  39. llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-mix_6M-pairs/iter_0001397/config.json +29 -0
  40. llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-zh-mix_12M-pairs/iter_0003381/tokenizer.json +0 -0
  41. llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en-instruct_3M-pairs/iter_0000698/config.json +29 -0
  42. llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en-instruct_3M-pairs/iter_0000698/generation_config.json +6 -0
  43. llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en-instruct_3M-pairs/iter_0000698/model.safetensors.index.json +262 -0
  44. llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en-instruct_3M-pairs/iter_0000698/tokenizer.json +0 -0
  45. llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en2en-ja_3M-pairs_3.5e-5/iter_0000698/config.json +29 -0
  46. llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en2en-ja_3M-pairs_3.5e-5/iter_0000698/generation_config.json +6 -0
  47. llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en2en-ja_3M-pairs_3.5e-5/iter_0000698/model.safetensors.index.json +262 -0
  48. llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en_3M-pairs/iter_0000698/tokenizer.json +0 -0
  49. llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en_3M-pairs/iter_0000698/tokenizer_config.json +83 -0
  50. llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en_3M-pairs_3.5e-5/iter_0000698/generation_config.json +6 -0
.gitattributes CHANGED
@@ -281,3 +281,9 @@ tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/nccl/lib/l
281
  tuning-competition-baseline/.venv/lib/python3.11/site-packages/triton/third_party/cuda/bin/nvdisasm filter=lfs diff=lfs merge=lfs -text
282
  tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cufft/lib/libcufft.so.10 filter=lfs diff=lfs merge=lfs -text
283
  tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cusolver/lib/libcusolverMg.so.11 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
281
  tuning-competition-baseline/.venv/lib/python3.11/site-packages/triton/third_party/cuda/bin/nvdisasm filter=lfs diff=lfs merge=lfs -text
282
  tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cufft/lib/libcufft.so.10 filter=lfs diff=lfs merge=lfs -text
283
  tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cusolver/lib/libcusolverMg.so.11 filter=lfs diff=lfs merge=lfs -text
284
+ tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cusparse/lib/libcusparse.so.11 filter=lfs diff=lfs merge=lfs -text
285
+ tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cusolver/lib/libcusolver.so.11 filter=lfs diff=lfs merge=lfs -text
286
+ tuning-competition-baseline/.venv/lib/python3.11/site-packages/nvidia/cublas/lib/libcublasLt.so.11 filter=lfs diff=lfs merge=lfs -text
287
+ tuning-competition-baseline/.venv/lib/python3.11/site-packages/torch/lib/libtorch_cpu.so filter=lfs diff=lfs merge=lfs -text
288
+ tuning-competition-baseline/.venv/lib/python3.11/site-packages/triton/_C/libtriton.so filter=lfs diff=lfs merge=lfs -text
289
+ llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document.idx filter=lfs diff=lfs merge=lfs -text
llm_tutorial/eval/results/Qwen/Qwen2-1.5B.json ADDED
The diff for this file is too large to render. See raw diff
 
llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69102e533c8d9834fccc86c9800a276dc70bf7fae64277dd1edcc443fb8d9edf
3
+ size 4827616
llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document/cache/GPTDataset_indices/80d7dc88bf2d24bda8780c0ade9232eb-GPTDataset-description.txt ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class": "GPTDataset",
3
+ "path_prefix": "/work/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document",
4
+ "num_samples": 1492224,
5
+ "index_split": "valid",
6
+ "random_seed": 1234,
7
+ "sequence_length": 1024,
8
+ "split": null,
9
+ "split_matrix": null
10
+ }
llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document/cache/GPTDataset_indices/80d7dc88bf2d24bda8780c0ade9232eb-GPTDataset-sample_index.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:304c38c4843fa864d9ca544244424e7adb44977d413f365f7577f9457534128a
3
+ size 11946592
llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document/cache/GPTDataset_indices/80d7dc88bf2d24bda8780c0ade9232eb-GPTDataset-shuffle_index.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9301017f65cd0e6de5604fc78158233e94ea23e77d4780073e85f8a6f21d4867
3
+ size 5973356
llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document/cache/GPTDataset_indices/853745364fb2fbc2666f7cb226ba389e-GPTDataset-description.txt ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class": "GPTDataset",
3
+ "path_prefix": "/work/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document",
4
+ "num_samples": 12864,
5
+ "index_split": "test",
6
+ "random_seed": 1234,
7
+ "sequence_length": 1024,
8
+ "split": null,
9
+ "split_matrix": null
10
+ }
llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document/cache/GPTDataset_indices/853745364fb2fbc2666f7cb226ba389e-GPTDataset-document_index.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7634d28844ee195b6b26c55ddfae9bf857e33f2d41dcc90f4977511dc6a7da89
3
+ size 50024
llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document/cache/GPTDataset_indices/853745364fb2fbc2666f7cb226ba389e-GPTDataset-sample_index.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21126154c8706d05e9c5618f704fd4a4f276ebfb7779eb340026dd79ff2bd012
3
+ size 103848
llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_document/cache/GPTDataset_indices/853745364fb2fbc2666f7cb226ba389e-GPTDataset-shuffle_index.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6594b670f5a0ba3a3a686e9b55414225bd25a3eaa32ce7ff53e9b8e39264490
3
+ size 51984
llm_tutorial/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data_text_processed_log.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "total_tokens_processed": 1205770,
3
+ "total_bytes_processed": 1855632,
4
+ "total_time": 0.7141332626342773,
5
+ "input": "/share/yans/datasets/jsonl/llm-jp-corpus-v2/ja/ja_wiki/validation_0.jsonl",
6
+ "json_keys": [
7
+ "text"
8
+ ],
9
+ "split_sentences": false,
10
+ "keep_newlines": false,
11
+ "tokenizer_type": "HFPreTrainedTokenizer",
12
+ "tokenizer_model": "/share/pretrained_lm/Qwen/Qwen2-0.5B",
13
+ "vocab_file": null,
14
+ "vocab_size": 786,
15
+ "merge_file": null,
16
+ "append_eod": true,
17
+ "lang": "english",
18
+ "output_prefix": "/work/llm_recipes/datasets/bin/baseline/llm_jp_corpus_v2_ja_wiki_validation_0/data",
19
+ "workers": 32,
20
+ "partitions": 1,
21
+ "log_interval": 1000,
22
+ "keep_sequential_samples": false,
23
+ "remove_bos": false,
24
+ "keep_empty": false,
25
+ "rank": 1,
26
+ "make_vocab_size_divisible_by": 128,
27
+ "tensor_model_parallel_size": 1,
28
+ "vocab_extra_ids": 0,
29
+ "padded_vocab_size": 151680
30
+ }
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document.idx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f73ce5c1b7f7b75e8e37ee307bb61f7b6dd9cc548d15296d07b7ebaca37a7ed5
3
+ size 1998422
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/40b0757666be5879d4957ef001f2548f-GPTDataset-sample_index.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edec88e339afb4aaf4e01300d28918478ca76927690113e752634049106ed7ee
3
+ size 4056992
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/4c5ba66133c100eed2605c1788c35aed-GPTDataset-document_index.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70a8d99360f7723446eae4162864f05f3468d34db72ccdccabc9e94bb1eda03d
3
+ size 10391704
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/74eba84f8d67c7b4de5c9dbe6e06ad05-GPTDataset-description.txt ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class": "GPTDataset",
3
+ "path_prefix": "/work/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document",
4
+ "num_samples": 6432000,
5
+ "index_split": "train",
6
+ "random_seed": 1234,
7
+ "sequence_length": 4096,
8
+ "split": null,
9
+ "split_matrix": null
10
+ }
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/83b6a7444f9036329af9611109011086-GPTDataset-description.txt ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class": "GPTDataset",
3
+ "path_prefix": "/work/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document",
4
+ "num_samples": 6432000,
5
+ "index_split": "train",
6
+ "random_seed": 1234,
7
+ "sequence_length": 1021,
8
+ "split": null,
9
+ "split_matrix": null
10
+ }
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/83b6a7444f9036329af9611109011086-GPTDataset-document_index.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21f84f66187d39a65fec831dde79a77c75c63d183d836856de8e8a9c6eecba69
3
+ size 5195916
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/90a0209287c09d4fb8c349ec9c0e0e23-GPTDataset-description.txt ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class": "GPTDataset",
3
+ "path_prefix": "/work/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document",
4
+ "num_samples": 21441072,
5
+ "index_split": "valid",
6
+ "random_seed": 1234,
7
+ "sequence_length": 1021,
8
+ "split": null,
9
+ "split_matrix": null
10
+ }
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/acc018e9317275205756d04e6d7b900a-GPTDataset-document_index.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7fc1d73923c13646b18c5decd55d1d7d72ec84a3aa3a25df89efa03d428034e
3
+ size 2398184
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/acc018e9317275205756d04e6d7b900a-GPTDataset-shuffle_index.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96aac536c96b97af562469ef1fe5fcacba49c35ca2886528ed7c51bfbe0586f7
3
+ size 1379360
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/b7582ab95f7384b0fa67902e8323964e-GPTDataset-description.txt ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class": "GPTDataset",
3
+ "path_prefix": "/work/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document",
4
+ "num_samples": 3216,
5
+ "index_split": "test",
6
+ "random_seed": 1234,
7
+ "sequence_length": 4096,
8
+ "split": null,
9
+ "split_matrix": null
10
+ }
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/b7582ab95f7384b0fa67902e8323964e-GPTDataset-document_index.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e2ef80697a5421569a560b9c7919ca8edb555db0bb6f2dfb121e628ae3602b5
3
+ size 399804
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/b7582ab95f7384b0fa67902e8323964e-GPTDataset-shuffle_index.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49c67d2d3944607faa2d374e8ca45a8df4a97f109243c452a076689f0c876c53
3
+ size 230000
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data_text_processed_log.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "total_tokens_processed": 519177757,
3
+ "total_bytes_processed": 389971607,
4
+ "total_time": 43.02607178688049,
5
+ "input": "/share/yans/datasets/jsonl/llm-jp-corpus-v1/ja/ja_wiki/train_0.jsonl",
6
+ "json_keys": [
7
+ "text"
8
+ ],
9
+ "split_sentences": false,
10
+ "keep_newlines": false,
11
+ "tokenizer_type": "HFPreTrainedTokenizer",
12
+ "tokenizer_model": "/share/pretrained_lm/Phi/Phi-2",
13
+ "vocab_file": null,
14
+ "vocab_size": 786,
15
+ "merge_file": null,
16
+ "append_eod": true,
17
+ "lang": "english",
18
+ "output_prefix": "/work/llm_recipes/datasets/bin/sample/llm_jp_corpus_v1_ja_wiki_train_0/data",
19
+ "workers": 32,
20
+ "partitions": 1,
21
+ "log_interval": 1000,
22
+ "keep_sequential_samples": false,
23
+ "remove_bos": false,
24
+ "keep_empty": false,
25
+ "rank": 1,
26
+ "make_vocab_size_divisible_by": 128,
27
+ "tensor_model_parallel_size": 1,
28
+ "vocab_extra_ids": 0,
29
+ "padded_vocab_size": 50304
30
+ }
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train/data_text_processed_log.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "total_tokens_processed": 1754785366,
3
+ "total_bytes_processed": 2626031426,
4
+ "total_time": 253.11910605430603,
5
+ "input": "/share/yans/datasets/jsonl/llm-jp-corpus-v2/ja/ja_wiki/ja_wiki_train.jsonl",
6
+ "json_keys": [
7
+ "text"
8
+ ],
9
+ "split_sentences": false,
10
+ "keep_newlines": false,
11
+ "tokenizer_type": "HFPreTrainedTokenizer",
12
+ "tokenizer_model": "/share/pretrained_lm/Qwen/Qwen2-1.5B",
13
+ "vocab_file": null,
14
+ "vocab_size": 786,
15
+ "merge_file": null,
16
+ "append_eod": true,
17
+ "lang": "english",
18
+ "output_prefix": "/work/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train/data",
19
+ "workers": 32,
20
+ "partitions": 1,
21
+ "log_interval": 1000,
22
+ "keep_sequential_samples": false,
23
+ "remove_bos": false,
24
+ "keep_empty": false,
25
+ "rank": 1,
26
+ "make_vocab_size_divisible_by": 128,
27
+ "tensor_model_parallel_size": 1,
28
+ "vocab_extra_ids": 0,
29
+ "padded_vocab_size": 151680
30
+ }
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/1f75c8bdc2b9f34c2d0db923cfbe2ae8-GPTDataset-description.txt ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class": "GPTDataset",
3
+ "path_prefix": "/work/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document",
4
+ "num_samples": 6432000,
5
+ "index_split": "train",
6
+ "random_seed": 1234,
7
+ "sequence_length": 4096,
8
+ "split": null,
9
+ "split_matrix": null
10
+ }
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/3939b211f79586cf3c33deedcc9a5c78-GPTDataset-description.txt ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class": "GPTDataset",
3
+ "path_prefix": "/work/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document",
4
+ "num_samples": 324816,
5
+ "index_split": "valid",
6
+ "random_seed": 1234,
7
+ "sequence_length": 4096,
8
+ "split": null,
9
+ "split_matrix": null
10
+ }
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/6a9e50c6fa3dc30f0d28bf9ed35427a8-GPTDataset-description.txt ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class": "GPTDataset",
3
+ "path_prefix": "/work/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document",
4
+ "num_samples": 12867216,
5
+ "index_split": "valid",
6
+ "random_seed": 1234,
7
+ "sequence_length": 4096,
8
+ "split": null,
9
+ "split_matrix": null
10
+ }
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/6c93d136579c889dc7737f37a743ad31-GPTDataset-description.txt ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class": "GPTDataset",
3
+ "path_prefix": "/work/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document",
4
+ "num_samples": 6435216,
5
+ "index_split": "valid",
6
+ "random_seed": 1234,
7
+ "sequence_length": 4096,
8
+ "split": null,
9
+ "split_matrix": null
10
+ }
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/dfe930f22c36ea35668c4345e9143dda-GPTDataset-description.txt ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "class": "GPTDataset",
3
+ "path_prefix": "/work/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document",
4
+ "num_samples": 3216,
5
+ "index_split": "test",
6
+ "random_seed": 1234,
7
+ "sequence_length": 4096,
8
+ "split": null,
9
+ "split_matrix": null
10
+ }
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/dfe930f22c36ea35668c4345e9143dda-GPTDataset-document_index.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e31cf4d94d1aaf20c794ccac2c6a5b04f9279e5dd1958708e06dce51e4df656
3
+ size 399808
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_document/cache/GPTDataset_indices/dfe930f22c36ea35668c4345e9143dda-GPTDataset-sample_index.npy ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9c3166a937ba93ceec7a261cf07ed225f436e4c6edf3f82d10b4f2531d40bb5
3
+ size 595584
llm_tutorial/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data_text_processed_log.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "total_tokens_processed": 304771887,
3
+ "total_bytes_processed": 423297509,
4
+ "total_time": 41.864734411239624,
5
+ "input": "/share/yans/datasets/jsonl/llm-jp-corpus-v2/ja/ja_wiki/train_0.jsonl",
6
+ "json_keys": [
7
+ "text"
8
+ ],
9
+ "split_sentences": false,
10
+ "keep_newlines": false,
11
+ "tokenizer_type": "HFPreTrainedTokenizer",
12
+ "tokenizer_model": "/share/pretrained_lm/Qwen/Qwen2-0.5B",
13
+ "vocab_file": null,
14
+ "vocab_size": 786,
15
+ "merge_file": null,
16
+ "append_eod": true,
17
+ "lang": "english",
18
+ "output_prefix": "/work/llm_recipes/datasets/bin/sample/llm_jp_corpus_v2_ja_wiki_train_0/data",
19
+ "workers": 32,
20
+ "partitions": 1,
21
+ "log_interval": 1000,
22
+ "keep_sequential_samples": false,
23
+ "remove_bos": false,
24
+ "keep_empty": false,
25
+ "rank": 1,
26
+ "make_vocab_size_divisible_by": 128,
27
+ "tensor_model_parallel_size": 1,
28
+ "vocab_extra_ids": 0,
29
+ "padded_vocab_size": 151680
30
+ }
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-instruct_3M-pairs/iter_0000698/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/share/pretrained_lm/llm-jp/llm-jp-v3-3.7b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 3072,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "max_position_embeddings": 4096,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 24,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 24,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.43.3",
27
+ "use_cache": true,
28
+ "vocab_size": 99584
29
+ }
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-instruct_3M-pairs/iter_0000698/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.43.3"
6
+ }
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-instruct_3M-pairs/iter_0000698/model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15131652096
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
198
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
199
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
200
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
201
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
202
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
203
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
204
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
205
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
206
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
207
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
208
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
209
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
210
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
211
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
212
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
213
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
214
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
215
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
225
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
226
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
227
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
228
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
229
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
230
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
231
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
232
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
233
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
234
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
235
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
236
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
237
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
238
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
239
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
240
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
241
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
242
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
243
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
244
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
245
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
246
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
247
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
252
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
253
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
254
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
255
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
256
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
257
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
258
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
259
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
260
+ "model.norm.weight": "model-00003-of-00004.safetensors"
261
+ }
262
+ }
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-instruct_3M-pairs/iter_0000698/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<CLS|LLM-jp>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<MASK|LLM-jp>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<PAD|LLM-jp>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "<SEP|LLM-jp>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-instruct_3M-pairs/iter_0000698/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-mix_6M-pairs/iter_0001397/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/share/pretrained_lm/llm-jp/llm-jp-v3-3.7b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 3072,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "max_position_embeddings": 4096,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 24,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 24,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.43.3",
27
+ "use_cache": true,
28
+ "vocab_size": 99584
29
+ }
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_en-ja-zh-mix_12M-pairs/iter_0003381/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en-instruct_3M-pairs/iter_0000698/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/share/pretrained_lm/llm-jp/llm-jp-v3-3.7b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 3072,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "max_position_embeddings": 4096,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 24,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 24,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.43.3",
27
+ "use_cache": true,
28
+ "vocab_size": 99584
29
+ }
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en-instruct_3M-pairs/iter_0000698/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.43.3"
6
+ }
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en-instruct_3M-pairs/iter_0000698/model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15131652096
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
198
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
199
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
200
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
201
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
202
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
203
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
204
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
205
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
206
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
207
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
208
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
209
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
210
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
211
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
212
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
213
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
214
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
215
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
225
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
226
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
227
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
228
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
229
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
230
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
231
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
232
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
233
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
234
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
235
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
236
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
237
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
238
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
239
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
240
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
241
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
242
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
243
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
244
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
245
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
246
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
247
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
252
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
253
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
254
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
255
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
256
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
257
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
258
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
259
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
260
+ "model.norm.weight": "model-00003-of-00004.safetensors"
261
+ }
262
+ }
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en-instruct_3M-pairs/iter_0000698/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en2en-ja_3M-pairs_3.5e-5/iter_0000698/config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/share/pretrained_lm/llm-jp/llm-jp-v3-3.7b",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 3072,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "max_position_embeddings": 4096,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 24,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 24,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.43.3",
27
+ "use_cache": true,
28
+ "vocab_size": 99584
29
+ }
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en2en-ja_3M-pairs_3.5e-5/iter_0000698/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.43.3"
6
+ }
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en2en-ja_3M-pairs_3.5e-5/iter_0000698/model.safetensors.index.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 15131652096
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
198
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
199
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
200
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
201
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
202
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
203
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
204
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
205
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
206
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
207
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
208
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
209
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
210
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
211
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
212
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
213
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
214
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
215
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
225
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
226
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
227
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
228
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
229
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
230
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
231
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
232
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
233
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
234
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
235
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
236
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
237
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
238
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
239
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
240
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
241
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
242
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
243
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
244
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
245
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
246
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
247
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
252
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
253
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
254
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
255
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
256
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
257
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
258
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
259
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
260
+ "model.norm.weight": "model-00003-of-00004.safetensors"
261
+ }
262
+ }
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en_3M-pairs/iter_0000698/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en_3M-pairs/iter_0000698/tokenizer_config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<MASK|LLM-jp>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<PAD|LLM-jp>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "5": {
46
+ "content": "<CLS|LLM-jp>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "6": {
54
+ "content": "<SEP|LLM-jp>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "7": {
62
+ "content": "<EOD|LLM-jp>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ }
69
+ },
70
+ "bos_token": "<s>",
71
+ "clean_up_tokenization_spaces": false,
72
+ "cls_token": "<CLS|LLM-jp>",
73
+ "eod_token": "</s>",
74
+ "eos_token": "</s>",
75
+ "extra_ids": 0,
76
+ "mask_token": "<MASK|LLM-jp>",
77
+ "model_max_length": 1000000000000000019884624838656,
78
+ "pad_token": "<PAD|LLM-jp>",
79
+ "sep_token": "<SEP|LLM-jp>",
80
+ "sp_model_kwargs": {},
81
+ "tokenizer_class": "PreTrainedTokenizerFast",
82
+ "unk_token": "<unk>"
83
+ }
llm_tutorial/llm_recipes/models/hf-model-eval/llm-jp-v3-3.7b_ja-en_3M-pairs_3.5e-5/iter_0000698/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.43.3"
6
+ }