ZwwWayne commited on
Commit
2481a80
1 Parent(s): 19833d4

update model weights

Browse files
Files changed (47) hide show
  1. .gitattributes +21 -0
  2. config.json +4 -6
  3. generation_config.json +1 -1
  4. pytorch_model-00001-of-00021.bin → model-00001-of-00021.safetensors +2 -2
  5. pytorch_model-00002-of-00021.bin → model-00002-of-00021.safetensors +2 -2
  6. pytorch_model-00003-of-00021.bin → model-00003-of-00021.safetensors +2 -2
  7. pytorch_model-00004-of-00021.bin → model-00004-of-00021.safetensors +2 -2
  8. model-00005-of-00021.safetensors +3 -0
  9. model-00006-of-00021.safetensors +3 -0
  10. model-00007-of-00021.safetensors +3 -0
  11. model-00008-of-00021.safetensors +3 -0
  12. model-00009-of-00021.safetensors +3 -0
  13. model-00010-of-00021.safetensors +3 -0
  14. model-00011-of-00021.safetensors +3 -0
  15. model-00012-of-00021.safetensors +3 -0
  16. model-00013-of-00021.safetensors +3 -0
  17. model-00014-of-00021.safetensors +3 -0
  18. model-00015-of-00021.safetensors +3 -0
  19. model-00016-of-00021.safetensors +3 -0
  20. model-00017-of-00021.safetensors +3 -0
  21. model-00018-of-00021.safetensors +3 -0
  22. model-00019-of-00021.safetensors +3 -0
  23. model-00020-of-00021.safetensors +3 -0
  24. model-00021-of-00021.safetensors +3 -0
  25. model.safetensors.index.json +346 -0
  26. pytorch_model-00005-of-00021.bin +0 -3
  27. pytorch_model-00006-of-00021.bin +0 -3
  28. pytorch_model-00007-of-00021.bin +0 -3
  29. pytorch_model-00008-of-00021.bin +0 -3
  30. pytorch_model-00009-of-00021.bin +0 -3
  31. pytorch_model-00010-of-00021.bin +0 -3
  32. pytorch_model-00011-of-00021.bin +0 -3
  33. pytorch_model-00012-of-00021.bin +0 -3
  34. pytorch_model-00013-of-00021.bin +0 -3
  35. pytorch_model-00014-of-00021.bin +0 -3
  36. pytorch_model-00015-of-00021.bin +0 -3
  37. pytorch_model-00016-of-00021.bin +0 -3
  38. pytorch_model-00017-of-00021.bin +0 -3
  39. pytorch_model-00018-of-00021.bin +0 -3
  40. pytorch_model-00019-of-00021.bin +0 -3
  41. pytorch_model-00020-of-00021.bin +0 -3
  42. pytorch_model-00021-of-00021.bin +0 -3
  43. pytorch_model.bin.index.json +0 -3
  44. special_tokens_map.json +28 -4
  45. syncRecord.txt +0 -0
  46. tokenization_internlm2_fast.py +8 -8
  47. tokenizer_config.json +31 -27
.gitattributes CHANGED
@@ -56,3 +56,24 @@ pytorch_model-00004-of-00021.bin filter=lfs diff=lfs merge=lfs -text
56
  pytorch_model-00005-of-00021.bin filter=lfs diff=lfs merge=lfs -text
57
  pytorch_model-00009-of-00021.bin filter=lfs diff=lfs merge=lfs -text
58
  pytorch_model-00012-of-00021.bin filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
56
  pytorch_model-00005-of-00021.bin filter=lfs diff=lfs merge=lfs -text
57
  pytorch_model-00009-of-00021.bin filter=lfs diff=lfs merge=lfs -text
58
  pytorch_model-00012-of-00021.bin filter=lfs diff=lfs merge=lfs -text
59
+ model-00001-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
60
+ model-00002-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
61
+ model-00018-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
62
+ model-00020-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
63
+ model-00021-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
64
+ model-00005-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
65
+ model-00007-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
66
+ model-00009-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
67
+ model-00010-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
68
+ model-00012-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
69
+ model-00016-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
70
+ model-00008-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
71
+ model-00013-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
72
+ model-00014-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
73
+ model-00015-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
74
+ model-00003-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
75
+ model-00004-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
76
+ model-00006-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
77
+ model-00011-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
78
+ model-00017-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
79
+ model-00019-of-00021.safetensors filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -2,6 +2,7 @@
2
  "architectures": [
3
  "InternLM2ForCausalLM"
4
  ],
 
5
  "auto_map": {
6
  "AutoConfig": "configuration_internlm2.InternLM2Config",
7
  "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",
@@ -21,14 +22,11 @@
21
  "num_key_value_heads": 8,
22
  "pad_token_id": 2,
23
  "rms_norm_eps": 1e-05,
24
- "rope_scaling": {
25
- "factor": 3.0,
26
- "type": "dynamic"
27
- },
28
  "rope_theta": 1000000,
29
  "tie_word_embeddings": false,
30
- "torch_dtype": "float16",
31
- "transformers_version": "4.33.2",
32
  "use_cache": true,
33
  "vocab_size": 92544
34
  }
 
2
  "architectures": [
3
  "InternLM2ForCausalLM"
4
  ],
5
+ "attn_implementation": "eager",
6
  "auto_map": {
7
  "AutoConfig": "configuration_internlm2.InternLM2Config",
8
  "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM",
 
22
  "num_key_value_heads": 8,
23
  "pad_token_id": 2,
24
  "rms_norm_eps": 1e-05,
25
+ "rope_scaling": null,
 
 
 
26
  "rope_theta": 1000000,
27
  "tie_word_embeddings": false,
28
+ "torch_dtype": "bfloat16",
29
+ "transformers_version": "4.37.1",
30
  "use_cache": true,
31
  "vocab_size": 92544
32
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 2,
6
- "transformers_version": "4.33.2"
7
  }
 
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
  "pad_token_id": 2,
6
+ "transformers_version": "4.37.1"
7
  }
pytorch_model-00001-of-00021.bin → model-00001-of-00021.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:722819f7b217898ee32c8c65421006303081106b7af8048378774423de824f26
3
- size 1917348897
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71c97753e79aca0ec02fce767a8eb577a22a8d71f85f67ad1a0d27ad180de9b9
3
+ size 1917346712
pytorch_model-00002-of-00021.bin → model-00002-of-00021.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d4ee6af265497cbd169c7163f0e9ac97c56e389c7a89f825713894ff3120fee
3
- size 1937823489
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d7d3e8a363a51541d73fc3aa4d09f5101ec2112ea1f606b3d299e60d786fa65
3
+ size 1937819544
pytorch_model-00003-of-00021.bin → model-00003-of-00021.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc0d11d9813cea7bba73cfbcc0e212fff344e7282adb370fdfb20adfda9f164a
3
- size 1963014163
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c42aeb776313b0457193e34cf67449635e16d58fd458a33ea7de8f9ca4a6c2f7
3
+ size 1963010040
pytorch_model-00004-of-00021.bin → model-00004-of-00021.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa74f5be136e888c2a7c43032bd97dca226d8644ec06ec6cef986a3f5be375be
3
- size 1937823489
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f150d613778a94eecd9767d22481f885c5ea7cc6930447571419b636531fe458
3
+ size 1937819544
model-00005-of-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7ae67ff1640d2240ee39e4ad8afd6434f65dfea8edcda3e5a65228b56681c40
3
+ size 1963010056
model-00006-of-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:458d174c5f58e614eb9a4866e640658eb3fa3d693c82c121cf81305a4c7524d5
3
+ size 1937819560
model-00007-of-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e26ee729dd0f56ce9a7b9ee7cb76a0db088652d8f2e6bc804fd90ac33516124c
3
+ size 1963010064
model-00008-of-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36a950b8704d16a20578a7c81dc8839277567287a588beb813e6d11a615b7709
3
+ size 1937819560
model-00009-of-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b698ce7143053027afcd9ffb111a02ea11ffe63ec8ee7e9173632ada39352a13
3
+ size 1963010064
model-00010-of-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad08486a3e53b09f31d59d583e5101742bebcfe9f16a6197cd904fb915e62ad
3
+ size 1937819560
model-00011-of-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14726e3d81b00c9529cd10ac5715fca78d33d73dda86dae0486907d6b2d43586
3
+ size 1963010064
model-00012-of-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2f9422d667749b9c111eca0e0267c38595fb5187502cc6ed59ed3759cd578ff
3
+ size 1937819560
model-00013-of-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c762ae1adefb90c623ec485eef484c2c530d5de4b9b450e58b5c01fac5f8141
3
+ size 1963010064
model-00014-of-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26a58657add48c89e0c685a4c33d202bd390d3f891cf1b0c540845ac743e8783
3
+ size 1937819560
model-00015-of-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c843c57fb031e3307915b59f659d5f3ca7065167a5aee6a9898ecbd982a8b169
3
+ size 1963010064
model-00016-of-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c9b9280c441514ad0ef3f4c0f4771f220b1453728a142bc03d6130705d554f2
3
+ size 1937819560
model-00017-of-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81d01c0d63e0ba5178c138258d2492c2767d5af52ee66657e8efcb9fef221e37
3
+ size 1963010064
model-00018-of-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71b4ffe7d27ebda067452ad0ece09b134132097cfcea3c147860086705e2737b
3
+ size 1937819560
model-00019-of-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4970740b6cf6d32721167a8ceb7503ee162c0e9ebbcaabf60339cb07799bc95
3
+ size 1963010064
model-00020-of-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11549f6e010488fd2c9f3e7e4f83b4a27d52b30b878de2287753c5d2c199ab1f
3
+ size 1560344232
model-00021-of-00021.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dc8dffc3abaed006d85b1ac1f3d9eb1f5d32c3cfb105525111af0c559dd9e78
3
+ size 1137180800
model.safetensors.index.json ADDED
@@ -0,0 +1,346 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 39722299392
4
+ },
5
+ "weight_map": {
6
+ "model.layers.0.attention.wo.weight": "model-00001-of-00021.safetensors",
7
+ "model.layers.0.attention.wqkv.weight": "model-00001-of-00021.safetensors",
8
+ "model.layers.0.attention_norm.weight": "model-00001-of-00021.safetensors",
9
+ "model.layers.0.feed_forward.w1.weight": "model-00001-of-00021.safetensors",
10
+ "model.layers.0.feed_forward.w2.weight": "model-00001-of-00021.safetensors",
11
+ "model.layers.0.feed_forward.w3.weight": "model-00001-of-00021.safetensors",
12
+ "model.layers.0.ffn_norm.weight": "model-00001-of-00021.safetensors",
13
+ "model.layers.1.attention.wo.weight": "model-00002-of-00021.safetensors",
14
+ "model.layers.1.attention.wqkv.weight": "model-00002-of-00021.safetensors",
15
+ "model.layers.1.attention_norm.weight": "model-00002-of-00021.safetensors",
16
+ "model.layers.1.feed_forward.w1.weight": "model-00002-of-00021.safetensors",
17
+ "model.layers.1.feed_forward.w2.weight": "model-00002-of-00021.safetensors",
18
+ "model.layers.1.feed_forward.w3.weight": "model-00002-of-00021.safetensors",
19
+ "model.layers.1.ffn_norm.weight": "model-00002-of-00021.safetensors",
20
+ "model.layers.10.attention.wo.weight": "model-00005-of-00021.safetensors",
21
+ "model.layers.10.attention.wqkv.weight": "model-00005-of-00021.safetensors",
22
+ "model.layers.10.attention_norm.weight": "model-00005-of-00021.safetensors",
23
+ "model.layers.10.feed_forward.w1.weight": "model-00005-of-00021.safetensors",
24
+ "model.layers.10.feed_forward.w2.weight": "model-00005-of-00021.safetensors",
25
+ "model.layers.10.feed_forward.w3.weight": "model-00005-of-00021.safetensors",
26
+ "model.layers.10.ffn_norm.weight": "model-00005-of-00021.safetensors",
27
+ "model.layers.11.attention.wo.weight": "model-00006-of-00021.safetensors",
28
+ "model.layers.11.attention.wqkv.weight": "model-00006-of-00021.safetensors",
29
+ "model.layers.11.attention_norm.weight": "model-00006-of-00021.safetensors",
30
+ "model.layers.11.feed_forward.w1.weight": "model-00006-of-00021.safetensors",
31
+ "model.layers.11.feed_forward.w2.weight": "model-00006-of-00021.safetensors",
32
+ "model.layers.11.feed_forward.w3.weight": "model-00006-of-00021.safetensors",
33
+ "model.layers.11.ffn_norm.weight": "model-00006-of-00021.safetensors",
34
+ "model.layers.12.attention.wo.weight": "model-00006-of-00021.safetensors",
35
+ "model.layers.12.attention.wqkv.weight": "model-00006-of-00021.safetensors",
36
+ "model.layers.12.attention_norm.weight": "model-00006-of-00021.safetensors",
37
+ "model.layers.12.feed_forward.w1.weight": "model-00006-of-00021.safetensors",
38
+ "model.layers.12.feed_forward.w2.weight": "model-00006-of-00021.safetensors",
39
+ "model.layers.12.feed_forward.w3.weight": "model-00006-of-00021.safetensors",
40
+ "model.layers.12.ffn_norm.weight": "model-00006-of-00021.safetensors",
41
+ "model.layers.13.attention.wo.weight": "model-00006-of-00021.safetensors",
42
+ "model.layers.13.attention.wqkv.weight": "model-00006-of-00021.safetensors",
43
+ "model.layers.13.attention_norm.weight": "model-00007-of-00021.safetensors",
44
+ "model.layers.13.feed_forward.w1.weight": "model-00006-of-00021.safetensors",
45
+ "model.layers.13.feed_forward.w2.weight": "model-00007-of-00021.safetensors",
46
+ "model.layers.13.feed_forward.w3.weight": "model-00007-of-00021.safetensors",
47
+ "model.layers.13.ffn_norm.weight": "model-00007-of-00021.safetensors",
48
+ "model.layers.14.attention.wo.weight": "model-00007-of-00021.safetensors",
49
+ "model.layers.14.attention.wqkv.weight": "model-00007-of-00021.safetensors",
50
+ "model.layers.14.attention_norm.weight": "model-00007-of-00021.safetensors",
51
+ "model.layers.14.feed_forward.w1.weight": "model-00007-of-00021.safetensors",
52
+ "model.layers.14.feed_forward.w2.weight": "model-00007-of-00021.safetensors",
53
+ "model.layers.14.feed_forward.w3.weight": "model-00007-of-00021.safetensors",
54
+ "model.layers.14.ffn_norm.weight": "model-00007-of-00021.safetensors",
55
+ "model.layers.15.attention.wo.weight": "model-00007-of-00021.safetensors",
56
+ "model.layers.15.attention.wqkv.weight": "model-00007-of-00021.safetensors",
57
+ "model.layers.15.attention_norm.weight": "model-00007-of-00021.safetensors",
58
+ "model.layers.15.feed_forward.w1.weight": "model-00007-of-00021.safetensors",
59
+ "model.layers.15.feed_forward.w2.weight": "model-00007-of-00021.safetensors",
60
+ "model.layers.15.feed_forward.w3.weight": "model-00007-of-00021.safetensors",
61
+ "model.layers.15.ffn_norm.weight": "model-00007-of-00021.safetensors",
62
+ "model.layers.16.attention.wo.weight": "model-00008-of-00021.safetensors",
63
+ "model.layers.16.attention.wqkv.weight": "model-00008-of-00021.safetensors",
64
+ "model.layers.16.attention_norm.weight": "model-00008-of-00021.safetensors",
65
+ "model.layers.16.feed_forward.w1.weight": "model-00008-of-00021.safetensors",
66
+ "model.layers.16.feed_forward.w2.weight": "model-00008-of-00021.safetensors",
67
+ "model.layers.16.feed_forward.w3.weight": "model-00008-of-00021.safetensors",
68
+ "model.layers.16.ffn_norm.weight": "model-00008-of-00021.safetensors",
69
+ "model.layers.17.attention.wo.weight": "model-00008-of-00021.safetensors",
70
+ "model.layers.17.attention.wqkv.weight": "model-00008-of-00021.safetensors",
71
+ "model.layers.17.attention_norm.weight": "model-00008-of-00021.safetensors",
72
+ "model.layers.17.feed_forward.w1.weight": "model-00008-of-00021.safetensors",
73
+ "model.layers.17.feed_forward.w2.weight": "model-00008-of-00021.safetensors",
74
+ "model.layers.17.feed_forward.w3.weight": "model-00008-of-00021.safetensors",
75
+ "model.layers.17.ffn_norm.weight": "model-00008-of-00021.safetensors",
76
+ "model.layers.18.attention.wo.weight": "model-00008-of-00021.safetensors",
77
+ "model.layers.18.attention.wqkv.weight": "model-00008-of-00021.safetensors",
78
+ "model.layers.18.attention_norm.weight": "model-00009-of-00021.safetensors",
79
+ "model.layers.18.feed_forward.w1.weight": "model-00008-of-00021.safetensors",
80
+ "model.layers.18.feed_forward.w2.weight": "model-00009-of-00021.safetensors",
81
+ "model.layers.18.feed_forward.w3.weight": "model-00009-of-00021.safetensors",
82
+ "model.layers.18.ffn_norm.weight": "model-00009-of-00021.safetensors",
83
+ "model.layers.19.attention.wo.weight": "model-00009-of-00021.safetensors",
84
+ "model.layers.19.attention.wqkv.weight": "model-00009-of-00021.safetensors",
85
+ "model.layers.19.attention_norm.weight": "model-00009-of-00021.safetensors",
86
+ "model.layers.19.feed_forward.w1.weight": "model-00009-of-00021.safetensors",
87
+ "model.layers.19.feed_forward.w2.weight": "model-00009-of-00021.safetensors",
88
+ "model.layers.19.feed_forward.w3.weight": "model-00009-of-00021.safetensors",
89
+ "model.layers.19.ffn_norm.weight": "model-00009-of-00021.safetensors",
90
+ "model.layers.2.attention.wo.weight": "model-00002-of-00021.safetensors",
91
+ "model.layers.2.attention.wqkv.weight": "model-00002-of-00021.safetensors",
92
+ "model.layers.2.attention_norm.weight": "model-00002-of-00021.safetensors",
93
+ "model.layers.2.feed_forward.w1.weight": "model-00002-of-00021.safetensors",
94
+ "model.layers.2.feed_forward.w2.weight": "model-00002-of-00021.safetensors",
95
+ "model.layers.2.feed_forward.w3.weight": "model-00002-of-00021.safetensors",
96
+ "model.layers.2.ffn_norm.weight": "model-00002-of-00021.safetensors",
97
+ "model.layers.20.attention.wo.weight": "model-00009-of-00021.safetensors",
98
+ "model.layers.20.attention.wqkv.weight": "model-00009-of-00021.safetensors",
99
+ "model.layers.20.attention_norm.weight": "model-00009-of-00021.safetensors",
100
+ "model.layers.20.feed_forward.w1.weight": "model-00009-of-00021.safetensors",
101
+ "model.layers.20.feed_forward.w2.weight": "model-00009-of-00021.safetensors",
102
+ "model.layers.20.feed_forward.w3.weight": "model-00009-of-00021.safetensors",
103
+ "model.layers.20.ffn_norm.weight": "model-00009-of-00021.safetensors",
104
+ "model.layers.21.attention.wo.weight": "model-00010-of-00021.safetensors",
105
+ "model.layers.21.attention.wqkv.weight": "model-00010-of-00021.safetensors",
106
+ "model.layers.21.attention_norm.weight": "model-00010-of-00021.safetensors",
107
+ "model.layers.21.feed_forward.w1.weight": "model-00010-of-00021.safetensors",
108
+ "model.layers.21.feed_forward.w2.weight": "model-00010-of-00021.safetensors",
109
+ "model.layers.21.feed_forward.w3.weight": "model-00010-of-00021.safetensors",
110
+ "model.layers.21.ffn_norm.weight": "model-00010-of-00021.safetensors",
111
+ "model.layers.22.attention.wo.weight": "model-00010-of-00021.safetensors",
112
+ "model.layers.22.attention.wqkv.weight": "model-00010-of-00021.safetensors",
113
+ "model.layers.22.attention_norm.weight": "model-00010-of-00021.safetensors",
114
+ "model.layers.22.feed_forward.w1.weight": "model-00010-of-00021.safetensors",
115
+ "model.layers.22.feed_forward.w2.weight": "model-00010-of-00021.safetensors",
116
+ "model.layers.22.feed_forward.w3.weight": "model-00010-of-00021.safetensors",
117
+ "model.layers.22.ffn_norm.weight": "model-00010-of-00021.safetensors",
118
+ "model.layers.23.attention.wo.weight": "model-00010-of-00021.safetensors",
119
+ "model.layers.23.attention.wqkv.weight": "model-00010-of-00021.safetensors",
120
+ "model.layers.23.attention_norm.weight": "model-00011-of-00021.safetensors",
121
+ "model.layers.23.feed_forward.w1.weight": "model-00010-of-00021.safetensors",
122
+ "model.layers.23.feed_forward.w2.weight": "model-00011-of-00021.safetensors",
123
+ "model.layers.23.feed_forward.w3.weight": "model-00011-of-00021.safetensors",
124
+ "model.layers.23.ffn_norm.weight": "model-00011-of-00021.safetensors",
125
+ "model.layers.24.attention.wo.weight": "model-00011-of-00021.safetensors",
126
+ "model.layers.24.attention.wqkv.weight": "model-00011-of-00021.safetensors",
127
+ "model.layers.24.attention_norm.weight": "model-00011-of-00021.safetensors",
128
+ "model.layers.24.feed_forward.w1.weight": "model-00011-of-00021.safetensors",
129
+ "model.layers.24.feed_forward.w2.weight": "model-00011-of-00021.safetensors",
130
+ "model.layers.24.feed_forward.w3.weight": "model-00011-of-00021.safetensors",
131
+ "model.layers.24.ffn_norm.weight": "model-00011-of-00021.safetensors",
132
+ "model.layers.25.attention.wo.weight": "model-00011-of-00021.safetensors",
133
+ "model.layers.25.attention.wqkv.weight": "model-00011-of-00021.safetensors",
134
+ "model.layers.25.attention_norm.weight": "model-00011-of-00021.safetensors",
135
+ "model.layers.25.feed_forward.w1.weight": "model-00011-of-00021.safetensors",
136
+ "model.layers.25.feed_forward.w2.weight": "model-00011-of-00021.safetensors",
137
+ "model.layers.25.feed_forward.w3.weight": "model-00011-of-00021.safetensors",
138
+ "model.layers.25.ffn_norm.weight": "model-00011-of-00021.safetensors",
139
+ "model.layers.26.attention.wo.weight": "model-00012-of-00021.safetensors",
140
+ "model.layers.26.attention.wqkv.weight": "model-00012-of-00021.safetensors",
141
+ "model.layers.26.attention_norm.weight": "model-00012-of-00021.safetensors",
142
+ "model.layers.26.feed_forward.w1.weight": "model-00012-of-00021.safetensors",
143
+ "model.layers.26.feed_forward.w2.weight": "model-00012-of-00021.safetensors",
144
+ "model.layers.26.feed_forward.w3.weight": "model-00012-of-00021.safetensors",
145
+ "model.layers.26.ffn_norm.weight": "model-00012-of-00021.safetensors",
146
+ "model.layers.27.attention.wo.weight": "model-00012-of-00021.safetensors",
147
+ "model.layers.27.attention.wqkv.weight": "model-00012-of-00021.safetensors",
148
+ "model.layers.27.attention_norm.weight": "model-00012-of-00021.safetensors",
149
+ "model.layers.27.feed_forward.w1.weight": "model-00012-of-00021.safetensors",
150
+ "model.layers.27.feed_forward.w2.weight": "model-00012-of-00021.safetensors",
151
+ "model.layers.27.feed_forward.w3.weight": "model-00012-of-00021.safetensors",
152
+ "model.layers.27.ffn_norm.weight": "model-00012-of-00021.safetensors",
153
+ "model.layers.28.attention.wo.weight": "model-00012-of-00021.safetensors",
154
+ "model.layers.28.attention.wqkv.weight": "model-00012-of-00021.safetensors",
155
+ "model.layers.28.attention_norm.weight": "model-00013-of-00021.safetensors",
156
+ "model.layers.28.feed_forward.w1.weight": "model-00012-of-00021.safetensors",
157
+ "model.layers.28.feed_forward.w2.weight": "model-00013-of-00021.safetensors",
158
+ "model.layers.28.feed_forward.w3.weight": "model-00013-of-00021.safetensors",
159
+ "model.layers.28.ffn_norm.weight": "model-00013-of-00021.safetensors",
160
+ "model.layers.29.attention.wo.weight": "model-00013-of-00021.safetensors",
161
+ "model.layers.29.attention.wqkv.weight": "model-00013-of-00021.safetensors",
162
+ "model.layers.29.attention_norm.weight": "model-00013-of-00021.safetensors",
163
+ "model.layers.29.feed_forward.w1.weight": "model-00013-of-00021.safetensors",
164
+ "model.layers.29.feed_forward.w2.weight": "model-00013-of-00021.safetensors",
165
+ "model.layers.29.feed_forward.w3.weight": "model-00013-of-00021.safetensors",
166
+ "model.layers.29.ffn_norm.weight": "model-00013-of-00021.safetensors",
167
+ "model.layers.3.attention.wo.weight": "model-00002-of-00021.safetensors",
168
+ "model.layers.3.attention.wqkv.weight": "model-00002-of-00021.safetensors",
169
+ "model.layers.3.attention_norm.weight": "model-00003-of-00021.safetensors",
170
+ "model.layers.3.feed_forward.w1.weight": "model-00002-of-00021.safetensors",
171
+ "model.layers.3.feed_forward.w2.weight": "model-00003-of-00021.safetensors",
172
+ "model.layers.3.feed_forward.w3.weight": "model-00003-of-00021.safetensors",
173
+ "model.layers.3.ffn_norm.weight": "model-00003-of-00021.safetensors",
174
+ "model.layers.30.attention.wo.weight": "model-00013-of-00021.safetensors",
175
+ "model.layers.30.attention.wqkv.weight": "model-00013-of-00021.safetensors",
176
+ "model.layers.30.attention_norm.weight": "model-00013-of-00021.safetensors",
177
+ "model.layers.30.feed_forward.w1.weight": "model-00013-of-00021.safetensors",
178
+ "model.layers.30.feed_forward.w2.weight": "model-00013-of-00021.safetensors",
179
+ "model.layers.30.feed_forward.w3.weight": "model-00013-of-00021.safetensors",
180
+ "model.layers.30.ffn_norm.weight": "model-00013-of-00021.safetensors",
181
+ "model.layers.31.attention.wo.weight": "model-00014-of-00021.safetensors",
182
+ "model.layers.31.attention.wqkv.weight": "model-00014-of-00021.safetensors",
183
+ "model.layers.31.attention_norm.weight": "model-00014-of-00021.safetensors",
184
+ "model.layers.31.feed_forward.w1.weight": "model-00014-of-00021.safetensors",
185
+ "model.layers.31.feed_forward.w2.weight": "model-00014-of-00021.safetensors",
186
+ "model.layers.31.feed_forward.w3.weight": "model-00014-of-00021.safetensors",
187
+ "model.layers.31.ffn_norm.weight": "model-00014-of-00021.safetensors",
188
+ "model.layers.32.attention.wo.weight": "model-00014-of-00021.safetensors",
189
+ "model.layers.32.attention.wqkv.weight": "model-00014-of-00021.safetensors",
190
+ "model.layers.32.attention_norm.weight": "model-00014-of-00021.safetensors",
191
+ "model.layers.32.feed_forward.w1.weight": "model-00014-of-00021.safetensors",
192
+ "model.layers.32.feed_forward.w2.weight": "model-00014-of-00021.safetensors",
193
+ "model.layers.32.feed_forward.w3.weight": "model-00014-of-00021.safetensors",
194
+ "model.layers.32.ffn_norm.weight": "model-00014-of-00021.safetensors",
195
+ "model.layers.33.attention.wo.weight": "model-00014-of-00021.safetensors",
196
+ "model.layers.33.attention.wqkv.weight": "model-00014-of-00021.safetensors",
197
+ "model.layers.33.attention_norm.weight": "model-00015-of-00021.safetensors",
198
+ "model.layers.33.feed_forward.w1.weight": "model-00014-of-00021.safetensors",
199
+ "model.layers.33.feed_forward.w2.weight": "model-00015-of-00021.safetensors",
200
+ "model.layers.33.feed_forward.w3.weight": "model-00015-of-00021.safetensors",
201
+ "model.layers.33.ffn_norm.weight": "model-00015-of-00021.safetensors",
202
+ "model.layers.34.attention.wo.weight": "model-00015-of-00021.safetensors",
203
+ "model.layers.34.attention.wqkv.weight": "model-00015-of-00021.safetensors",
204
+ "model.layers.34.attention_norm.weight": "model-00015-of-00021.safetensors",
205
+ "model.layers.34.feed_forward.w1.weight": "model-00015-of-00021.safetensors",
206
+ "model.layers.34.feed_forward.w2.weight": "model-00015-of-00021.safetensors",
207
+ "model.layers.34.feed_forward.w3.weight": "model-00015-of-00021.safetensors",
208
+ "model.layers.34.ffn_norm.weight": "model-00015-of-00021.safetensors",
209
+ "model.layers.35.attention.wo.weight": "model-00015-of-00021.safetensors",
210
+ "model.layers.35.attention.wqkv.weight": "model-00015-of-00021.safetensors",
211
+ "model.layers.35.attention_norm.weight": "model-00015-of-00021.safetensors",
212
+ "model.layers.35.feed_forward.w1.weight": "model-00015-of-00021.safetensors",
213
+ "model.layers.35.feed_forward.w2.weight": "model-00015-of-00021.safetensors",
214
+ "model.layers.35.feed_forward.w3.weight": "model-00015-of-00021.safetensors",
215
+ "model.layers.35.ffn_norm.weight": "model-00015-of-00021.safetensors",
216
+ "model.layers.36.attention.wo.weight": "model-00016-of-00021.safetensors",
217
+ "model.layers.36.attention.wqkv.weight": "model-00016-of-00021.safetensors",
218
+ "model.layers.36.attention_norm.weight": "model-00016-of-00021.safetensors",
219
+ "model.layers.36.feed_forward.w1.weight": "model-00016-of-00021.safetensors",
220
+ "model.layers.36.feed_forward.w2.weight": "model-00016-of-00021.safetensors",
221
+ "model.layers.36.feed_forward.w3.weight": "model-00016-of-00021.safetensors",
222
+ "model.layers.36.ffn_norm.weight": "model-00016-of-00021.safetensors",
223
+ "model.layers.37.attention.wo.weight": "model-00016-of-00021.safetensors",
224
+ "model.layers.37.attention.wqkv.weight": "model-00016-of-00021.safetensors",
225
+ "model.layers.37.attention_norm.weight": "model-00016-of-00021.safetensors",
226
+ "model.layers.37.feed_forward.w1.weight": "model-00016-of-00021.safetensors",
227
+ "model.layers.37.feed_forward.w2.weight": "model-00016-of-00021.safetensors",
228
+ "model.layers.37.feed_forward.w3.weight": "model-00016-of-00021.safetensors",
229
+ "model.layers.37.ffn_norm.weight": "model-00016-of-00021.safetensors",
230
+ "model.layers.38.attention.wo.weight": "model-00016-of-00021.safetensors",
231
+ "model.layers.38.attention.wqkv.weight": "model-00016-of-00021.safetensors",
232
+ "model.layers.38.attention_norm.weight": "model-00017-of-00021.safetensors",
233
+ "model.layers.38.feed_forward.w1.weight": "model-00016-of-00021.safetensors",
234
+ "model.layers.38.feed_forward.w2.weight": "model-00017-of-00021.safetensors",
235
+ "model.layers.38.feed_forward.w3.weight": "model-00017-of-00021.safetensors",
236
+ "model.layers.38.ffn_norm.weight": "model-00017-of-00021.safetensors",
237
+ "model.layers.39.attention.wo.weight": "model-00017-of-00021.safetensors",
238
+ "model.layers.39.attention.wqkv.weight": "model-00017-of-00021.safetensors",
239
+ "model.layers.39.attention_norm.weight": "model-00017-of-00021.safetensors",
240
+ "model.layers.39.feed_forward.w1.weight": "model-00017-of-00021.safetensors",
241
+ "model.layers.39.feed_forward.w2.weight": "model-00017-of-00021.safetensors",
242
+ "model.layers.39.feed_forward.w3.weight": "model-00017-of-00021.safetensors",
243
+ "model.layers.39.ffn_norm.weight": "model-00017-of-00021.safetensors",
244
+ "model.layers.4.attention.wo.weight": "model-00003-of-00021.safetensors",
245
+ "model.layers.4.attention.wqkv.weight": "model-00003-of-00021.safetensors",
246
+ "model.layers.4.attention_norm.weight": "model-00003-of-00021.safetensors",
247
+ "model.layers.4.feed_forward.w1.weight": "model-00003-of-00021.safetensors",
248
+ "model.layers.4.feed_forward.w2.weight": "model-00003-of-00021.safetensors",
249
+ "model.layers.4.feed_forward.w3.weight": "model-00003-of-00021.safetensors",
250
+ "model.layers.4.ffn_norm.weight": "model-00003-of-00021.safetensors",
251
+ "model.layers.40.attention.wo.weight": "model-00017-of-00021.safetensors",
252
+ "model.layers.40.attention.wqkv.weight": "model-00017-of-00021.safetensors",
253
+ "model.layers.40.attention_norm.weight": "model-00017-of-00021.safetensors",
254
+ "model.layers.40.feed_forward.w1.weight": "model-00017-of-00021.safetensors",
255
+ "model.layers.40.feed_forward.w2.weight": "model-00017-of-00021.safetensors",
256
+ "model.layers.40.feed_forward.w3.weight": "model-00017-of-00021.safetensors",
257
+ "model.layers.40.ffn_norm.weight": "model-00017-of-00021.safetensors",
258
+ "model.layers.41.attention.wo.weight": "model-00018-of-00021.safetensors",
259
+ "model.layers.41.attention.wqkv.weight": "model-00018-of-00021.safetensors",
260
+ "model.layers.41.attention_norm.weight": "model-00018-of-00021.safetensors",
261
+ "model.layers.41.feed_forward.w1.weight": "model-00018-of-00021.safetensors",
262
+ "model.layers.41.feed_forward.w2.weight": "model-00018-of-00021.safetensors",
263
+ "model.layers.41.feed_forward.w3.weight": "model-00018-of-00021.safetensors",
264
+ "model.layers.41.ffn_norm.weight": "model-00018-of-00021.safetensors",
265
+ "model.layers.42.attention.wo.weight": "model-00018-of-00021.safetensors",
266
+ "model.layers.42.attention.wqkv.weight": "model-00018-of-00021.safetensors",
267
+ "model.layers.42.attention_norm.weight": "model-00018-of-00021.safetensors",
268
+ "model.layers.42.feed_forward.w1.weight": "model-00018-of-00021.safetensors",
269
+ "model.layers.42.feed_forward.w2.weight": "model-00018-of-00021.safetensors",
270
+ "model.layers.42.feed_forward.w3.weight": "model-00018-of-00021.safetensors",
271
+ "model.layers.42.ffn_norm.weight": "model-00018-of-00021.safetensors",
272
+ "model.layers.43.attention.wo.weight": "model-00018-of-00021.safetensors",
273
+ "model.layers.43.attention.wqkv.weight": "model-00018-of-00021.safetensors",
274
+ "model.layers.43.attention_norm.weight": "model-00019-of-00021.safetensors",
275
+ "model.layers.43.feed_forward.w1.weight": "model-00018-of-00021.safetensors",
276
+ "model.layers.43.feed_forward.w2.weight": "model-00019-of-00021.safetensors",
277
+ "model.layers.43.feed_forward.w3.weight": "model-00019-of-00021.safetensors",
278
+ "model.layers.43.ffn_norm.weight": "model-00019-of-00021.safetensors",
279
+ "model.layers.44.attention.wo.weight": "model-00019-of-00021.safetensors",
280
+ "model.layers.44.attention.wqkv.weight": "model-00019-of-00021.safetensors",
281
+ "model.layers.44.attention_norm.weight": "model-00019-of-00021.safetensors",
282
+ "model.layers.44.feed_forward.w1.weight": "model-00019-of-00021.safetensors",
283
+ "model.layers.44.feed_forward.w2.weight": "model-00019-of-00021.safetensors",
284
+ "model.layers.44.feed_forward.w3.weight": "model-00019-of-00021.safetensors",
285
+ "model.layers.44.ffn_norm.weight": "model-00019-of-00021.safetensors",
286
+ "model.layers.45.attention.wo.weight": "model-00019-of-00021.safetensors",
287
+ "model.layers.45.attention.wqkv.weight": "model-00019-of-00021.safetensors",
288
+ "model.layers.45.attention_norm.weight": "model-00019-of-00021.safetensors",
289
+ "model.layers.45.feed_forward.w1.weight": "model-00019-of-00021.safetensors",
290
+ "model.layers.45.feed_forward.w2.weight": "model-00019-of-00021.safetensors",
291
+ "model.layers.45.feed_forward.w3.weight": "model-00019-of-00021.safetensors",
292
+ "model.layers.45.ffn_norm.weight": "model-00019-of-00021.safetensors",
293
+ "model.layers.46.attention.wo.weight": "model-00020-of-00021.safetensors",
294
+ "model.layers.46.attention.wqkv.weight": "model-00020-of-00021.safetensors",
295
+ "model.layers.46.attention_norm.weight": "model-00020-of-00021.safetensors",
296
+ "model.layers.46.feed_forward.w1.weight": "model-00020-of-00021.safetensors",
297
+ "model.layers.46.feed_forward.w2.weight": "model-00020-of-00021.safetensors",
298
+ "model.layers.46.feed_forward.w3.weight": "model-00020-of-00021.safetensors",
299
+ "model.layers.46.ffn_norm.weight": "model-00020-of-00021.safetensors",
300
+ "model.layers.47.attention.wo.weight": "model-00020-of-00021.safetensors",
301
+ "model.layers.47.attention.wqkv.weight": "model-00020-of-00021.safetensors",
302
+ "model.layers.47.attention_norm.weight": "model-00020-of-00021.safetensors",
303
+ "model.layers.47.feed_forward.w1.weight": "model-00020-of-00021.safetensors",
304
+ "model.layers.47.feed_forward.w2.weight": "model-00020-of-00021.safetensors",
305
+ "model.layers.47.feed_forward.w3.weight": "model-00020-of-00021.safetensors",
306
+ "model.layers.47.ffn_norm.weight": "model-00020-of-00021.safetensors",
307
+ "model.layers.5.attention.wo.weight": "model-00003-of-00021.safetensors",
308
+ "model.layers.5.attention.wqkv.weight": "model-00003-of-00021.safetensors",
309
+ "model.layers.5.attention_norm.weight": "model-00003-of-00021.safetensors",
310
+ "model.layers.5.feed_forward.w1.weight": "model-00003-of-00021.safetensors",
311
+ "model.layers.5.feed_forward.w2.weight": "model-00003-of-00021.safetensors",
312
+ "model.layers.5.feed_forward.w3.weight": "model-00003-of-00021.safetensors",
313
+ "model.layers.5.ffn_norm.weight": "model-00003-of-00021.safetensors",
314
+ "model.layers.6.attention.wo.weight": "model-00004-of-00021.safetensors",
315
+ "model.layers.6.attention.wqkv.weight": "model-00004-of-00021.safetensors",
316
+ "model.layers.6.attention_norm.weight": "model-00004-of-00021.safetensors",
317
+ "model.layers.6.feed_forward.w1.weight": "model-00004-of-00021.safetensors",
318
+ "model.layers.6.feed_forward.w2.weight": "model-00004-of-00021.safetensors",
319
+ "model.layers.6.feed_forward.w3.weight": "model-00004-of-00021.safetensors",
320
+ "model.layers.6.ffn_norm.weight": "model-00004-of-00021.safetensors",
321
+ "model.layers.7.attention.wo.weight": "model-00004-of-00021.safetensors",
322
+ "model.layers.7.attention.wqkv.weight": "model-00004-of-00021.safetensors",
323
+ "model.layers.7.attention_norm.weight": "model-00004-of-00021.safetensors",
324
+ "model.layers.7.feed_forward.w1.weight": "model-00004-of-00021.safetensors",
325
+ "model.layers.7.feed_forward.w2.weight": "model-00004-of-00021.safetensors",
326
+ "model.layers.7.feed_forward.w3.weight": "model-00004-of-00021.safetensors",
327
+ "model.layers.7.ffn_norm.weight": "model-00004-of-00021.safetensors",
328
+ "model.layers.8.attention.wo.weight": "model-00004-of-00021.safetensors",
329
+ "model.layers.8.attention.wqkv.weight": "model-00004-of-00021.safetensors",
330
+ "model.layers.8.attention_norm.weight": "model-00005-of-00021.safetensors",
331
+ "model.layers.8.feed_forward.w1.weight": "model-00004-of-00021.safetensors",
332
+ "model.layers.8.feed_forward.w2.weight": "model-00005-of-00021.safetensors",
333
+ "model.layers.8.feed_forward.w3.weight": "model-00005-of-00021.safetensors",
334
+ "model.layers.8.ffn_norm.weight": "model-00005-of-00021.safetensors",
335
+ "model.layers.9.attention.wo.weight": "model-00005-of-00021.safetensors",
336
+ "model.layers.9.attention.wqkv.weight": "model-00005-of-00021.safetensors",
337
+ "model.layers.9.attention_norm.weight": "model-00005-of-00021.safetensors",
338
+ "model.layers.9.feed_forward.w1.weight": "model-00005-of-00021.safetensors",
339
+ "model.layers.9.feed_forward.w2.weight": "model-00005-of-00021.safetensors",
340
+ "model.layers.9.feed_forward.w3.weight": "model-00005-of-00021.safetensors",
341
+ "model.layers.9.ffn_norm.weight": "model-00005-of-00021.safetensors",
342
+ "model.norm.weight": "model-00020-of-00021.safetensors",
343
+ "model.tok_embeddings.weight": "model-00001-of-00021.safetensors",
344
+ "output.weight": "model-00021-of-00021.safetensors"
345
+ }
346
+ }
pytorch_model-00005-of-00021.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3b295c170c33adf209f507609fbec201a3534edd0ca2530d6524cc3dc63b989
3
- size 1963014163
 
 
 
 
pytorch_model-00006-of-00021.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb3d4c2c9b32ac6e07eb649294497621e5511c244ba780b8476e3fa22b71ea6a
3
- size 1937823489
 
 
 
 
pytorch_model-00007-of-00021.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:02c8539dc2ee3003f392001d61cd67a924fd6a4abdb6fddd70b366b703a8141c
3
- size 1963014227
 
 
 
 
pytorch_model-00008-of-00021.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7fe91599763599e612ff79bca50d1be9dd7cb9030d1e6dbacdb51dc45e22afa
3
- size 1937823489
 
 
 
 
pytorch_model-00009-of-00021.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:df8dae357eb00345ef42506045de1723869dabe8cf89fa192e06137cf3cd395d
3
- size 1963014227
 
 
 
 
pytorch_model-00010-of-00021.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8add13dc25f54db6df0a8b5e8135a63f670ac7bcbcb5706b541daa96bdfdd6c
3
- size 1937823489
 
 
 
 
pytorch_model-00011-of-00021.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:32af852ccb9936da7d332e22beda929de7fcb1f96c39262b836bca387fe0161d
3
- size 1963014227
 
 
 
 
pytorch_model-00012-of-00021.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff97793ae1fe4d27af4f9209fbf2e532cd4fb1ccc39e399aa2f58bddb765f186
3
- size 1937823489
 
 
 
 
pytorch_model-00013-of-00021.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d0c08ce8a307fa5fa3caebff931e1bf540e861e2fa38b1bfa4bcf91f7277e10
3
- size 1963014227
 
 
 
 
pytorch_model-00014-of-00021.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:15ebf9dcba9bd6b42c165736792b2ebdc33840bffc65c4314a0c704e34917d9e
3
- size 1937823489
 
 
 
 
pytorch_model-00015-of-00021.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e353fef3f3a242e8e5af05afca8e5113582d7ea3225fbe1ce111e32816e48a2c
3
- size 1963014227
 
 
 
 
pytorch_model-00016-of-00021.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ade1ad7844c0523e10e50cf541e20becd8d0a011305a0b5d49becc94cdf6692a
3
- size 1937823489
 
 
 
 
pytorch_model-00017-of-00021.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d969e5162667a98b6ed514bbf8a92f611994673ff47155a526b0092863ebc6e9
3
- size 1963014227
 
 
 
 
pytorch_model-00018-of-00021.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a8721d0d742ce15ae0f3081249b7cd7bb907701ee543101979d297cd9d6120f
3
- size 1937823489
 
 
 
 
pytorch_model-00019-of-00021.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:15b81635b5847683c9c943f8d819c29934a01e5a9e00a99464d8c5c3564d2938
3
- size 1963014227
 
 
 
 
pytorch_model-00020-of-00021.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d0dc96e4be3de25d042446799c96aa3bfb5204132cfe1d48db6f456aaf79bb1
3
- size 1560347805
 
 
 
 
pytorch_model-00021-of-00021.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1783c28825d2881dd23254e19422472464fdcd28416c9d9ae79b4fb46911ca1b
3
- size 1137181610
 
 
 
 
pytorch_model.bin.index.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e110c305db80b79307dbccd08c7e923304c1deff95dc6460ea62b7fa74716f46
3
- size 27171
 
 
 
 
special_tokens_map.json CHANGED
@@ -7,8 +7,32 @@
7
  "<|interpreter|>",
8
  "<|plugin|>"
9
  ],
10
- "bos_token": "<s>",
11
- "eos_token": "</s>",
12
- "pad_token": "</s>",
13
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  }
 
7
  "<|interpreter|>",
8
  "<|plugin|>"
9
  ],
10
+ "bos_token": {
11
+ "content": "<s>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "eos_token": {
18
+ "content": "</s>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "</s>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "unk_token": {
32
+ "content": "<unk>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ }
38
  }
syncRecord.txt ADDED
File without changes
tokenization_internlm2_fast.py CHANGED
@@ -56,14 +56,14 @@ class InternLM2Converter(SpmConverter):
56
  return unk_id
57
 
58
  def decoder(self, replacement, add_prefix_space):
59
- decoders_sequence = [
60
- decoders.Replace("▁", " "),
61
- decoders.ByteFallback(),
62
- decoders.Fuse(),
63
- ]
64
- if self.proto.normalizer_spec.add_dummy_prefix:
65
- decoders_sequence.append(decoders.Strip(content=" ", left=1))
66
- return decoders.Sequence(decoders_sequence)
67
 
68
  def tokenizer(self, proto):
69
  model_type = proto.trainer_spec.model_type
 
56
  return unk_id
57
 
58
  def decoder(self, replacement, add_prefix_space):
59
+ return decoders.Sequence(
60
+ [
61
+ decoders.Replace("▁", " "),
62
+ decoders.ByteFallback(),
63
+ decoders.Fuse(),
64
+ decoders.Strip(content=" ", left=1),
65
+ ]
66
+ )
67
 
68
  def tokenizer(self, proto):
69
  model_type = proto.trainer_spec.model_type
tokenizer_config.json CHANGED
@@ -1,17 +1,6 @@
1
  {
2
- "auto_map": {
3
- "AutoTokenizer": [
4
- "tokenization_internlm2.InternLM2Tokenizer",
5
- "tokenization_internlm2_fast.InternLM2TokenizerFast"
6
- ]
7
- },
8
- "bos_token": "<s>",
9
- "clean_up_tokenization_spaces": false,
10
- "eos_token": "</s>",
11
- "model_max_length": 1000000000000000019884624838656,
12
- "pad_token": "</s>",
13
- "tokenizer_class": "InternLM2Tokenizer",
14
- "unk_token": "<unk>",
15
  "added_tokens_decoder": {
16
  "0": {
17
  "content": "<unk>",
@@ -37,48 +26,48 @@
37
  "single_word": false,
38
  "special": true
39
  },
40
- "92543": {
41
- "content": "<|im_start|>",
42
  "lstrip": false,
43
  "normalized": false,
44
  "rstrip": false,
45
  "single_word": false,
46
  "special": true
47
  },
48
- "92542": {
49
- "content": "<|im_end|>",
50
  "lstrip": false,
51
  "normalized": false,
52
  "rstrip": false,
53
  "single_word": false,
54
  "special": true
55
  },
56
- "92541": {
57
- "content": "<|action_start|>",
58
  "lstrip": false,
59
  "normalized": false,
60
  "rstrip": false,
61
  "single_word": false,
62
  "special": true
63
  },
64
- "92540": {
65
- "content": "<|action_end|>",
66
  "lstrip": false,
67
  "normalized": false,
68
  "rstrip": false,
69
  "single_word": false,
70
  "special": true
71
  },
72
- "92539": {
73
- "content": "<|interpreter|>",
74
  "lstrip": false,
75
  "normalized": false,
76
  "rstrip": false,
77
  "single_word": false,
78
  "special": true
79
  },
80
- "92538": {
81
- "content": "<|plugin|>",
82
  "lstrip": false,
83
  "normalized": false,
84
  "rstrip": false,
@@ -94,5 +83,20 @@
94
  "<|interpreter|>",
95
  "<|plugin|>"
96
  ],
97
- "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
98
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
 
 
 
 
 
 
 
 
 
 
 
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "<unk>",
 
26
  "single_word": false,
27
  "special": true
28
  },
29
+ "92538": {
30
+ "content": "<|plugin|>",
31
  "lstrip": false,
32
  "normalized": false,
33
  "rstrip": false,
34
  "single_word": false,
35
  "special": true
36
  },
37
+ "92539": {
38
+ "content": "<|interpreter|>",
39
  "lstrip": false,
40
  "normalized": false,
41
  "rstrip": false,
42
  "single_word": false,
43
  "special": true
44
  },
45
+ "92540": {
46
+ "content": "<|action_end|>",
47
  "lstrip": false,
48
  "normalized": false,
49
  "rstrip": false,
50
  "single_word": false,
51
  "special": true
52
  },
53
+ "92541": {
54
+ "content": "<|action_start|>",
55
  "lstrip": false,
56
  "normalized": false,
57
  "rstrip": false,
58
  "single_word": false,
59
  "special": true
60
  },
61
+ "92542": {
62
+ "content": "<|im_end|>",
63
  "lstrip": false,
64
  "normalized": false,
65
  "rstrip": false,
66
  "single_word": false,
67
  "special": true
68
  },
69
+ "92543": {
70
+ "content": "<|im_start|>",
71
  "lstrip": false,
72
  "normalized": false,
73
  "rstrip": false,
 
83
  "<|interpreter|>",
84
  "<|plugin|>"
85
  ],
86
+ "auto_map": {
87
+ "AutoTokenizer": [
88
+ "tokenization_internlm2.InternLM2Tokenizer",
89
+ "tokenization_internlm2_fast.InternLM2TokenizerFast"
90
+ ]
91
+ },
92
+ "bos_token": "<s>",
93
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
94
+ "clean_up_tokenization_spaces": false,
95
+ "decode_with_prefix_space": false,
96
+ "eos_token": "</s>",
97
+ "model_max_length": 1000000000000000019884624838656,
98
+ "pad_token": "</s>",
99
+ "sp_model_kwargs": null,
100
+ "tokenizer_class": "InternLM2Tokenizer",
101
+ "unk_token": "<unk>"
102
+ }