prince-canuma commited on
Commit
20def17
·
verified ·
1 Parent(s): 9f7ec98

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 +1 -0
  2. README.md +70 -0
  3. config.json +38 -0
  4. model-00001-of-00045.safetensors +3 -0
  5. model-00002-of-00045.safetensors +3 -0
  6. model-00003-of-00045.safetensors +3 -0
  7. model-00004-of-00045.safetensors +3 -0
  8. model-00005-of-00045.safetensors +3 -0
  9. model-00006-of-00045.safetensors +3 -0
  10. model-00007-of-00045.safetensors +3 -0
  11. model-00008-of-00045.safetensors +3 -0
  12. model-00009-of-00045.safetensors +3 -0
  13. model-00010-of-00045.safetensors +3 -0
  14. model-00011-of-00045.safetensors +3 -0
  15. model-00012-of-00045.safetensors +3 -0
  16. model-00013-of-00045.safetensors +3 -0
  17. model-00014-of-00045.safetensors +3 -0
  18. model-00015-of-00045.safetensors +3 -0
  19. model-00016-of-00045.safetensors +3 -0
  20. model-00017-of-00045.safetensors +3 -0
  21. model-00018-of-00045.safetensors +3 -0
  22. model-00019-of-00045.safetensors +3 -0
  23. model-00020-of-00045.safetensors +3 -0
  24. model-00021-of-00045.safetensors +3 -0
  25. model-00022-of-00045.safetensors +3 -0
  26. model-00023-of-00045.safetensors +3 -0
  27. model-00024-of-00045.safetensors +3 -0
  28. model-00025-of-00045.safetensors +3 -0
  29. model-00026-of-00045.safetensors +3 -0
  30. model-00027-of-00045.safetensors +3 -0
  31. model-00028-of-00045.safetensors +3 -0
  32. model-00029-of-00045.safetensors +3 -0
  33. model-00030-of-00045.safetensors +3 -0
  34. model-00031-of-00045.safetensors +3 -0
  35. model-00032-of-00045.safetensors +3 -0
  36. model-00033-of-00045.safetensors +3 -0
  37. model-00034-of-00045.safetensors +3 -0
  38. model-00035-of-00045.safetensors +3 -0
  39. model-00036-of-00045.safetensors +3 -0
  40. model-00037-of-00045.safetensors +3 -0
  41. model-00038-of-00045.safetensors +3 -0
  42. model-00039-of-00045.safetensors +3 -0
  43. model-00040-of-00045.safetensors +3 -0
  44. model-00041-of-00045.safetensors +3 -0
  45. model-00042-of-00045.safetensors +3 -0
  46. model-00043-of-00045.safetensors +3 -0
  47. model-00044-of-00045.safetensors +3 -0
  48. model-00045-of-00045.safetensors +3 -0
  49. model.safetensors.index.json +521 -0
  50. special_tokens_map.json +30 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ inference: false
3
+ library_name: transformers
4
+ language:
5
+ - en
6
+ - fr
7
+ - de
8
+ - es
9
+ - it
10
+ - pt
11
+ - ja
12
+ - ko
13
+ - zh
14
+ - ar
15
+ - el
16
+ - fa
17
+ - pl
18
+ - id
19
+ - cs
20
+ - he
21
+ - hi
22
+ - nl
23
+ - ro
24
+ - ru
25
+ - tr
26
+ - uk
27
+ - vi
28
+ license: cc-by-nc-4.0
29
+ extra_gated_prompt: By submitting this form, you agree to the [License Agreement](https://cohere.com/c4ai-cc-by-nc-license) and
30
+ acknowledge that the information you provide will be collected, used, and shared
31
+ in accordance with Cohere’s [Privacy Policy]( https://cohere.com/privacy). You’ll
32
+ receive email updates about C4AI and Cohere research, events, products and services.
33
+ You can unsubscribe at any time.
34
+ extra_gated_fields:
35
+ Name: text
36
+ Affiliation: text
37
+ Country: country
38
+ I agree to use this model for non-commercial use ONLY: checkbox
39
+ base_model: CohereForAI/c4ai-command-a-03-2025
40
+ tags:
41
+ - mlx
42
+ ---
43
+
44
+ # mlx-community/c4ai-command-a-03-2025-bf16
45
+
46
+ The Model [mlx-community/c4ai-command-a-03-2025-bf16](https://huggingface.co/mlx-community/c4ai-command-a-03-2025-bf16) was
47
+ converted to MLX format from [CohereForAI/c4ai-command-a-03-2025](https://huggingface.co/CohereForAI/c4ai-command-a-03-2025)
48
+ using mlx-lm version **0.21.5**.
49
+
50
+ ## Use with mlx
51
+
52
+ ```bash
53
+ pip install mlx-lm
54
+ ```
55
+
56
+ ```python
57
+ from mlx_lm import load, generate
58
+
59
+ model, tokenizer = load("mlx-community/c4ai-command-a-03-2025-bf16")
60
+
61
+ prompt = "hello"
62
+
63
+ if tokenizer.chat_template is not None:
64
+ messages = [{"role": "user", "content": prompt}]
65
+ prompt = tokenizer.apply_chat_template(
66
+ messages, add_generation_prompt=True
67
+ )
68
+
69
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
70
+ ```
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Cohere2ForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 5,
8
+ "cache_implementation": "hybrid",
9
+ "eos_token_id": 255001,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 12288,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 36864,
15
+ "layer_norm_eps": 1e-05,
16
+ "logit_scale": 0.25,
17
+ "max_position_embeddings": 131072,
18
+ "model_type": "cohere2",
19
+ "num_attention_heads": 96,
20
+ "num_hidden_layers": 64,
21
+ "num_key_value_heads": 8,
22
+ "order_of_interleaved_layers": "local_attn_first",
23
+ "pad_token_id": 0,
24
+ "position_embedding_type": "rope_gptj",
25
+ "rope_scaling": null,
26
+ "rope_theta": 50000,
27
+ "rotary_pct": 1.0,
28
+ "sliding_window": 4096,
29
+ "sliding_window_pattern": 4,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers_version": "4.48.0.dev0",
32
+ "use_cache": true,
33
+ "use_embedding_sharing": true,
34
+ "use_gated_activation": true,
35
+ "use_parallel_block": true,
36
+ "use_parallel_embedding": true,
37
+ "vocab_size": 256000
38
+ }
model-00001-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba4bb3ae3285d9746901116181c9bff31695e084001a2a77b3c49cddb35eb832
3
+ size 41
model-00002-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96655dce2b5247af01f09110b5f6e6c07de7de29715299e1c44106dbee35b83f
3
+ size 6291456139
model-00003-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb061cc1d525e3aed1cc680d0a7aa925a52117b0d78e01120cb455e78206b340
3
+ size 4932527628
model-00004-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bd3c721a4623e750f7f238672a2749c11f2288a98b38c879e49d9b814de8f88
3
+ size 5184210190
model-00005-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e19b53ced034326972affb200a656d2d100a76a5c966471af1087085bc85f43
3
+ size 4932527628
model-00006-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0d7f6fb59c9a31d0f7e02471de0ef7f5ede5b848d128cbbc1eddb85332bee3d
3
+ size 5184210190
model-00007-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:993fe978fd7c4223269bcb1479dba0f5ae643cd765299701610217bba869c4de
3
+ size 4932527622
model-00008-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd6bdc569aaec31d82e5044a270f3e9a1a39682f363b76a1241235fdbc021149
3
+ size 5184210200
model-00009-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5b38bcb13398d5af862c0f144f91d328eda18a934d5308f9d0cfcaf5aa7e8e9
3
+ size 4932527637
model-00010-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eadd179eca62933a7ebab88f00e61dd65604c0fe89f8f8d8810be31886ba8e0b
3
+ size 5184210211
model-00011-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:199d63f8976dccdbd0c925935affe6ce7ddec0e8b52c2364c90fafada154cec4
3
+ size 4932527637
model-00012-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e416df764dfc178339746518faf801e566b97f9bcc4685bac717cb84e9917901
3
+ size 5184210201
model-00013-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4783856e4e6db9e8ae7d15d6d2affeeacd0ff8726f07ed3903218bd847a5da3
3
+ size 4932527641
model-00014-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95d5a90a28a4b48c0d9b49cbfaa319ffc528b8abf7d2685e4fb3acb2f1f8f7aa
3
+ size 5184210201
model-00015-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:634e829dcbca0e1a6a4ae260245365d269fc0b043ddc3d44a8629acddf6abd81
3
+ size 4932527639
model-00016-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f1d4e26239ca034dd2c5b85299ab34c73b91143b5b98f6d5073b72ea0c07b96
3
+ size 5184210201
model-00017-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d54c4b470d955016f39b30e91d6e1ca8498ee552eebd4df311b4c93e968c3c5b
3
+ size 4932527645
model-00018-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:127367ed6b1cd099e72a0f5f7aff21899eea94e4bdaa454ef895dc8aa60c301c
3
+ size 5184210201
model-00019-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cecd9c0e48e01be5e655be460d7e5af504319aca28668607eec2086a87ec38f
3
+ size 4932527641
model-00020-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75199f48461c4a0681ca4fa5cd8f4fbc4551871b009c79476f4f460d9a036a8a
3
+ size 5184210195
model-00021-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:593657a2591fbc709db7701fbc7296d09658ca3229e5797c37a430c80711c7ec
3
+ size 4932527641
model-00022-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb030212a1b77e5bca48e8ad8377a154c9724b6e3e6d9d690802715fc712e2a0
3
+ size 5184210211
model-00023-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:243f4099fd209fe5c52ef3e5be044055e2ff9c9e89eb53f5fc13cb3848ec605c
3
+ size 4932527643
model-00024-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76561c38d14541959ccfa5b29dd4900f05e86d464c09358c19a2ee75cccd8ae8
3
+ size 5184210205
model-00025-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eb7ea010970ddc135dba09f91d1dd5d272477d436e4d0b91299f8da282d10c9
3
+ size 4932527645
model-00026-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:428a3fa37878f1ca3a5a0cc0d668e98a78995100c4db7f38ea164c7679fd61d0
3
+ size 5184210201
model-00027-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0954adba8ab065e95db6a2938f1416429bad3c7f2b2f14d642f681fa20d05d9d
3
+ size 4932527637
model-00028-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8046a4c9de404cfb4491ccf0f19f32cce21507c802e9e76a862f87d76d80918e
3
+ size 5184210201
model-00029-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fcb944ef9d9e3c172dbda412495cf035ce22032d9d755f7b8ea1b410cfe0313
3
+ size 4932527641
model-00030-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2b78bfbbad8b788bca65462e11ae64dba6b9df38d4da79016ffb6f338440099
3
+ size 5184210211
model-00031-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:feae89e2e53d772cbdbeeb788eb6d1405dc6db57ef3674c251f35af12fa9626c
3
+ size 4932527645
model-00032-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aab3b015e23a09914ec6be826f2c19b34b063ddfc72c5278fd245962b2c559b2
3
+ size 5184210201
model-00033-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b916e38eb84c5055f10e675dd78a762ef066904c1d58bce1de109e29751e293d
3
+ size 4932527643
model-00034-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:880b1b4a62ef62794e934b1c361b068205670ed38089f72fddb936c56b4281c3
3
+ size 5184210211
model-00035-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a6ab0c1e25280944858df35f398564cdad3b8d020c51a0c8eafd9847469d1c9
3
+ size 4932527637
model-00036-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:261318b87e0811dc4c8867bab435dabc561a3994c89e6a8f3907bdcbb0d5bd7f
3
+ size 5184210211
model-00037-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d8680efee89532c12b302cef76f6005c5e7cc96e09feb0130879ae211b23c6f
3
+ size 4932527637
model-00038-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c3a42b087c4fe819d92dbcfa4e45adf0aeb4673180e854bbb2f1bff3dc93aa6
3
+ size 5184210209
model-00039-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:357c41ed2b19f09090e9522f3178a7b9b4b971408993bb66cf9f8abb92a82277
3
+ size 4932527635
model-00040-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d0fea112eb44ee8b6665d39c07e80734f3f4079d9e35dd759692a1b0520991e
3
+ size 5184210211
model-00041-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61452699141f6e0e9a96dc8f3641b8ab88377fb8b795524163fc0884dfa70791
3
+ size 4932527641
model-00042-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f00fb6d877e3bfdf3b88789b7740596e8c28358c8fbece0dc3c970acf7d36c6f
3
+ size 5184210211
model-00043-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d1f219afb2032b8750932f09a47d313e5d2ba1e9b73ccc9ad53b0b00ba0947a
3
+ size 4932527645
model-00044-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fe8536bdc34cb5a928e4dc89d8533f179afebde54e08db884014cdac3e21e0d
3
+ size 5184210211
model-00045-of-00045.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0df4cfba517b4dff837ae8bbde420df8894b375f9b79ebbd514f9accbd9cd9d
3
+ size 3372270610
model.safetensors.index.json ADDED
@@ -0,0 +1,521 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 222115160064
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00002-of-00045.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model-00003-of-00045.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model-00003-of-00045.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00045.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model-00003-of-00045.safetensors",
11
+ "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00045.safetensors",
12
+ "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00045.safetensors",
13
+ "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00045.safetensors",
14
+ "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00045.safetensors",
15
+ "model.layers.1.input_layernorm.weight": "model-00004-of-00045.safetensors",
16
+ "model.layers.1.mlp.down_proj.weight": "model-00004-of-00045.safetensors",
17
+ "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00045.safetensors",
18
+ "model.layers.1.mlp.up_proj.weight": "model-00004-of-00045.safetensors",
19
+ "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00045.safetensors",
20
+ "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00045.safetensors",
21
+ "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00045.safetensors",
22
+ "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00045.safetensors",
23
+ "model.layers.10.input_layernorm.weight": "model-00010-of-00045.safetensors",
24
+ "model.layers.10.mlp.down_proj.weight": "model-00010-of-00045.safetensors",
25
+ "model.layers.10.mlp.gate_proj.weight": "model-00009-of-00045.safetensors",
26
+ "model.layers.10.mlp.up_proj.weight": "model-00010-of-00045.safetensors",
27
+ "model.layers.10.self_attn.k_proj.weight": "model-00009-of-00045.safetensors",
28
+ "model.layers.10.self_attn.o_proj.weight": "model-00009-of-00045.safetensors",
29
+ "model.layers.10.self_attn.q_proj.weight": "model-00009-of-00045.safetensors",
30
+ "model.layers.10.self_attn.v_proj.weight": "model-00009-of-00045.safetensors",
31
+ "model.layers.11.input_layernorm.weight": "model-00010-of-00045.safetensors",
32
+ "model.layers.11.mlp.down_proj.weight": "model-00010-of-00045.safetensors",
33
+ "model.layers.11.mlp.gate_proj.weight": "model-00010-of-00045.safetensors",
34
+ "model.layers.11.mlp.up_proj.weight": "model-00010-of-00045.safetensors",
35
+ "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00045.safetensors",
36
+ "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00045.safetensors",
37
+ "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00045.safetensors",
38
+ "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00045.safetensors",
39
+ "model.layers.12.input_layernorm.weight": "model-00011-of-00045.safetensors",
40
+ "model.layers.12.mlp.down_proj.weight": "model-00011-of-00045.safetensors",
41
+ "model.layers.12.mlp.gate_proj.weight": "model-00011-of-00045.safetensors",
42
+ "model.layers.12.mlp.up_proj.weight": "model-00011-of-00045.safetensors",
43
+ "model.layers.12.self_attn.k_proj.weight": "model-00011-of-00045.safetensors",
44
+ "model.layers.12.self_attn.o_proj.weight": "model-00011-of-00045.safetensors",
45
+ "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00045.safetensors",
46
+ "model.layers.12.self_attn.v_proj.weight": "model-00011-of-00045.safetensors",
47
+ "model.layers.13.input_layernorm.weight": "model-00012-of-00045.safetensors",
48
+ "model.layers.13.mlp.down_proj.weight": "model-00012-of-00045.safetensors",
49
+ "model.layers.13.mlp.gate_proj.weight": "model-00011-of-00045.safetensors",
50
+ "model.layers.13.mlp.up_proj.weight": "model-00012-of-00045.safetensors",
51
+ "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00045.safetensors",
52
+ "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00045.safetensors",
53
+ "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00045.safetensors",
54
+ "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00045.safetensors",
55
+ "model.layers.14.input_layernorm.weight": "model-00012-of-00045.safetensors",
56
+ "model.layers.14.mlp.down_proj.weight": "model-00012-of-00045.safetensors",
57
+ "model.layers.14.mlp.gate_proj.weight": "model-00012-of-00045.safetensors",
58
+ "model.layers.14.mlp.up_proj.weight": "model-00012-of-00045.safetensors",
59
+ "model.layers.14.self_attn.k_proj.weight": "model-00012-of-00045.safetensors",
60
+ "model.layers.14.self_attn.o_proj.weight": "model-00012-of-00045.safetensors",
61
+ "model.layers.14.self_attn.q_proj.weight": "model-00012-of-00045.safetensors",
62
+ "model.layers.14.self_attn.v_proj.weight": "model-00012-of-00045.safetensors",
63
+ "model.layers.15.input_layernorm.weight": "model-00013-of-00045.safetensors",
64
+ "model.layers.15.mlp.down_proj.weight": "model-00013-of-00045.safetensors",
65
+ "model.layers.15.mlp.gate_proj.weight": "model-00013-of-00045.safetensors",
66
+ "model.layers.15.mlp.up_proj.weight": "model-00013-of-00045.safetensors",
67
+ "model.layers.15.self_attn.k_proj.weight": "model-00013-of-00045.safetensors",
68
+ "model.layers.15.self_attn.o_proj.weight": "model-00013-of-00045.safetensors",
69
+ "model.layers.15.self_attn.q_proj.weight": "model-00013-of-00045.safetensors",
70
+ "model.layers.15.self_attn.v_proj.weight": "model-00013-of-00045.safetensors",
71
+ "model.layers.16.input_layernorm.weight": "model-00014-of-00045.safetensors",
72
+ "model.layers.16.mlp.down_proj.weight": "model-00014-of-00045.safetensors",
73
+ "model.layers.16.mlp.gate_proj.weight": "model-00013-of-00045.safetensors",
74
+ "model.layers.16.mlp.up_proj.weight": "model-00014-of-00045.safetensors",
75
+ "model.layers.16.self_attn.k_proj.weight": "model-00013-of-00045.safetensors",
76
+ "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00045.safetensors",
77
+ "model.layers.16.self_attn.q_proj.weight": "model-00013-of-00045.safetensors",
78
+ "model.layers.16.self_attn.v_proj.weight": "model-00013-of-00045.safetensors",
79
+ "model.layers.17.input_layernorm.weight": "model-00014-of-00045.safetensors",
80
+ "model.layers.17.mlp.down_proj.weight": "model-00014-of-00045.safetensors",
81
+ "model.layers.17.mlp.gate_proj.weight": "model-00014-of-00045.safetensors",
82
+ "model.layers.17.mlp.up_proj.weight": "model-00014-of-00045.safetensors",
83
+ "model.layers.17.self_attn.k_proj.weight": "model-00014-of-00045.safetensors",
84
+ "model.layers.17.self_attn.o_proj.weight": "model-00014-of-00045.safetensors",
85
+ "model.layers.17.self_attn.q_proj.weight": "model-00014-of-00045.safetensors",
86
+ "model.layers.17.self_attn.v_proj.weight": "model-00014-of-00045.safetensors",
87
+ "model.layers.18.input_layernorm.weight": "model-00015-of-00045.safetensors",
88
+ "model.layers.18.mlp.down_proj.weight": "model-00015-of-00045.safetensors",
89
+ "model.layers.18.mlp.gate_proj.weight": "model-00015-of-00045.safetensors",
90
+ "model.layers.18.mlp.up_proj.weight": "model-00015-of-00045.safetensors",
91
+ "model.layers.18.self_attn.k_proj.weight": "model-00015-of-00045.safetensors",
92
+ "model.layers.18.self_attn.o_proj.weight": "model-00015-of-00045.safetensors",
93
+ "model.layers.18.self_attn.q_proj.weight": "model-00015-of-00045.safetensors",
94
+ "model.layers.18.self_attn.v_proj.weight": "model-00015-of-00045.safetensors",
95
+ "model.layers.19.input_layernorm.weight": "model-00016-of-00045.safetensors",
96
+ "model.layers.19.mlp.down_proj.weight": "model-00016-of-00045.safetensors",
97
+ "model.layers.19.mlp.gate_proj.weight": "model-00015-of-00045.safetensors",
98
+ "model.layers.19.mlp.up_proj.weight": "model-00016-of-00045.safetensors",
99
+ "model.layers.19.self_attn.k_proj.weight": "model-00015-of-00045.safetensors",
100
+ "model.layers.19.self_attn.o_proj.weight": "model-00015-of-00045.safetensors",
101
+ "model.layers.19.self_attn.q_proj.weight": "model-00015-of-00045.safetensors",
102
+ "model.layers.19.self_attn.v_proj.weight": "model-00015-of-00045.safetensors",
103
+ "model.layers.2.input_layernorm.weight": "model-00004-of-00045.safetensors",
104
+ "model.layers.2.mlp.down_proj.weight": "model-00004-of-00045.safetensors",
105
+ "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00045.safetensors",
106
+ "model.layers.2.mlp.up_proj.weight": "model-00004-of-00045.safetensors",
107
+ "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00045.safetensors",
108
+ "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00045.safetensors",
109
+ "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00045.safetensors",
110
+ "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00045.safetensors",
111
+ "model.layers.20.input_layernorm.weight": "model-00016-of-00045.safetensors",
112
+ "model.layers.20.mlp.down_proj.weight": "model-00016-of-00045.safetensors",
113
+ "model.layers.20.mlp.gate_proj.weight": "model-00016-of-00045.safetensors",
114
+ "model.layers.20.mlp.up_proj.weight": "model-00016-of-00045.safetensors",
115
+ "model.layers.20.self_attn.k_proj.weight": "model-00016-of-00045.safetensors",
116
+ "model.layers.20.self_attn.o_proj.weight": "model-00016-of-00045.safetensors",
117
+ "model.layers.20.self_attn.q_proj.weight": "model-00016-of-00045.safetensors",
118
+ "model.layers.20.self_attn.v_proj.weight": "model-00016-of-00045.safetensors",
119
+ "model.layers.21.input_layernorm.weight": "model-00017-of-00045.safetensors",
120
+ "model.layers.21.mlp.down_proj.weight": "model-00017-of-00045.safetensors",
121
+ "model.layers.21.mlp.gate_proj.weight": "model-00017-of-00045.safetensors",
122
+ "model.layers.21.mlp.up_proj.weight": "model-00017-of-00045.safetensors",
123
+ "model.layers.21.self_attn.k_proj.weight": "model-00017-of-00045.safetensors",
124
+ "model.layers.21.self_attn.o_proj.weight": "model-00017-of-00045.safetensors",
125
+ "model.layers.21.self_attn.q_proj.weight": "model-00017-of-00045.safetensors",
126
+ "model.layers.21.self_attn.v_proj.weight": "model-00017-of-00045.safetensors",
127
+ "model.layers.22.input_layernorm.weight": "model-00018-of-00045.safetensors",
128
+ "model.layers.22.mlp.down_proj.weight": "model-00018-of-00045.safetensors",
129
+ "model.layers.22.mlp.gate_proj.weight": "model-00017-of-00045.safetensors",
130
+ "model.layers.22.mlp.up_proj.weight": "model-00018-of-00045.safetensors",
131
+ "model.layers.22.self_attn.k_proj.weight": "model-00017-of-00045.safetensors",
132
+ "model.layers.22.self_attn.o_proj.weight": "model-00017-of-00045.safetensors",
133
+ "model.layers.22.self_attn.q_proj.weight": "model-00017-of-00045.safetensors",
134
+ "model.layers.22.self_attn.v_proj.weight": "model-00017-of-00045.safetensors",
135
+ "model.layers.23.input_layernorm.weight": "model-00018-of-00045.safetensors",
136
+ "model.layers.23.mlp.down_proj.weight": "model-00018-of-00045.safetensors",
137
+ "model.layers.23.mlp.gate_proj.weight": "model-00018-of-00045.safetensors",
138
+ "model.layers.23.mlp.up_proj.weight": "model-00018-of-00045.safetensors",
139
+ "model.layers.23.self_attn.k_proj.weight": "model-00018-of-00045.safetensors",
140
+ "model.layers.23.self_attn.o_proj.weight": "model-00018-of-00045.safetensors",
141
+ "model.layers.23.self_attn.q_proj.weight": "model-00018-of-00045.safetensors",
142
+ "model.layers.23.self_attn.v_proj.weight": "model-00018-of-00045.safetensors",
143
+ "model.layers.24.input_layernorm.weight": "model-00019-of-00045.safetensors",
144
+ "model.layers.24.mlp.down_proj.weight": "model-00019-of-00045.safetensors",
145
+ "model.layers.24.mlp.gate_proj.weight": "model-00019-of-00045.safetensors",
146
+ "model.layers.24.mlp.up_proj.weight": "model-00019-of-00045.safetensors",
147
+ "model.layers.24.self_attn.k_proj.weight": "model-00019-of-00045.safetensors",
148
+ "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00045.safetensors",
149
+ "model.layers.24.self_attn.q_proj.weight": "model-00019-of-00045.safetensors",
150
+ "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00045.safetensors",
151
+ "model.layers.25.input_layernorm.weight": "model-00020-of-00045.safetensors",
152
+ "model.layers.25.mlp.down_proj.weight": "model-00020-of-00045.safetensors",
153
+ "model.layers.25.mlp.gate_proj.weight": "model-00019-of-00045.safetensors",
154
+ "model.layers.25.mlp.up_proj.weight": "model-00020-of-00045.safetensors",
155
+ "model.layers.25.self_attn.k_proj.weight": "model-00019-of-00045.safetensors",
156
+ "model.layers.25.self_attn.o_proj.weight": "model-00019-of-00045.safetensors",
157
+ "model.layers.25.self_attn.q_proj.weight": "model-00019-of-00045.safetensors",
158
+ "model.layers.25.self_attn.v_proj.weight": "model-00019-of-00045.safetensors",
159
+ "model.layers.26.input_layernorm.weight": "model-00020-of-00045.safetensors",
160
+ "model.layers.26.mlp.down_proj.weight": "model-00020-of-00045.safetensors",
161
+ "model.layers.26.mlp.gate_proj.weight": "model-00020-of-00045.safetensors",
162
+ "model.layers.26.mlp.up_proj.weight": "model-00020-of-00045.safetensors",
163
+ "model.layers.26.self_attn.k_proj.weight": "model-00020-of-00045.safetensors",
164
+ "model.layers.26.self_attn.o_proj.weight": "model-00020-of-00045.safetensors",
165
+ "model.layers.26.self_attn.q_proj.weight": "model-00020-of-00045.safetensors",
166
+ "model.layers.26.self_attn.v_proj.weight": "model-00020-of-00045.safetensors",
167
+ "model.layers.27.input_layernorm.weight": "model-00021-of-00045.safetensors",
168
+ "model.layers.27.mlp.down_proj.weight": "model-00021-of-00045.safetensors",
169
+ "model.layers.27.mlp.gate_proj.weight": "model-00021-of-00045.safetensors",
170
+ "model.layers.27.mlp.up_proj.weight": "model-00021-of-00045.safetensors",
171
+ "model.layers.27.self_attn.k_proj.weight": "model-00021-of-00045.safetensors",
172
+ "model.layers.27.self_attn.o_proj.weight": "model-00021-of-00045.safetensors",
173
+ "model.layers.27.self_attn.q_proj.weight": "model-00021-of-00045.safetensors",
174
+ "model.layers.27.self_attn.v_proj.weight": "model-00021-of-00045.safetensors",
175
+ "model.layers.28.input_layernorm.weight": "model-00022-of-00045.safetensors",
176
+ "model.layers.28.mlp.down_proj.weight": "model-00022-of-00045.safetensors",
177
+ "model.layers.28.mlp.gate_proj.weight": "model-00021-of-00045.safetensors",
178
+ "model.layers.28.mlp.up_proj.weight": "model-00022-of-00045.safetensors",
179
+ "model.layers.28.self_attn.k_proj.weight": "model-00021-of-00045.safetensors",
180
+ "model.layers.28.self_attn.o_proj.weight": "model-00021-of-00045.safetensors",
181
+ "model.layers.28.self_attn.q_proj.weight": "model-00021-of-00045.safetensors",
182
+ "model.layers.28.self_attn.v_proj.weight": "model-00021-of-00045.safetensors",
183
+ "model.layers.29.input_layernorm.weight": "model-00022-of-00045.safetensors",
184
+ "model.layers.29.mlp.down_proj.weight": "model-00022-of-00045.safetensors",
185
+ "model.layers.29.mlp.gate_proj.weight": "model-00022-of-00045.safetensors",
186
+ "model.layers.29.mlp.up_proj.weight": "model-00022-of-00045.safetensors",
187
+ "model.layers.29.self_attn.k_proj.weight": "model-00022-of-00045.safetensors",
188
+ "model.layers.29.self_attn.o_proj.weight": "model-00022-of-00045.safetensors",
189
+ "model.layers.29.self_attn.q_proj.weight": "model-00022-of-00045.safetensors",
190
+ "model.layers.29.self_attn.v_proj.weight": "model-00022-of-00045.safetensors",
191
+ "model.layers.3.input_layernorm.weight": "model-00005-of-00045.safetensors",
192
+ "model.layers.3.mlp.down_proj.weight": "model-00005-of-00045.safetensors",
193
+ "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00045.safetensors",
194
+ "model.layers.3.mlp.up_proj.weight": "model-00005-of-00045.safetensors",
195
+ "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00045.safetensors",
196
+ "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00045.safetensors",
197
+ "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00045.safetensors",
198
+ "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00045.safetensors",
199
+ "model.layers.30.input_layernorm.weight": "model-00023-of-00045.safetensors",
200
+ "model.layers.30.mlp.down_proj.weight": "model-00023-of-00045.safetensors",
201
+ "model.layers.30.mlp.gate_proj.weight": "model-00023-of-00045.safetensors",
202
+ "model.layers.30.mlp.up_proj.weight": "model-00023-of-00045.safetensors",
203
+ "model.layers.30.self_attn.k_proj.weight": "model-00023-of-00045.safetensors",
204
+ "model.layers.30.self_attn.o_proj.weight": "model-00023-of-00045.safetensors",
205
+ "model.layers.30.self_attn.q_proj.weight": "model-00023-of-00045.safetensors",
206
+ "model.layers.30.self_attn.v_proj.weight": "model-00023-of-00045.safetensors",
207
+ "model.layers.31.input_layernorm.weight": "model-00024-of-00045.safetensors",
208
+ "model.layers.31.mlp.down_proj.weight": "model-00024-of-00045.safetensors",
209
+ "model.layers.31.mlp.gate_proj.weight": "model-00023-of-00045.safetensors",
210
+ "model.layers.31.mlp.up_proj.weight": "model-00024-of-00045.safetensors",
211
+ "model.layers.31.self_attn.k_proj.weight": "model-00023-of-00045.safetensors",
212
+ "model.layers.31.self_attn.o_proj.weight": "model-00023-of-00045.safetensors",
213
+ "model.layers.31.self_attn.q_proj.weight": "model-00023-of-00045.safetensors",
214
+ "model.layers.31.self_attn.v_proj.weight": "model-00023-of-00045.safetensors",
215
+ "model.layers.32.input_layernorm.weight": "model-00024-of-00045.safetensors",
216
+ "model.layers.32.mlp.down_proj.weight": "model-00024-of-00045.safetensors",
217
+ "model.layers.32.mlp.gate_proj.weight": "model-00024-of-00045.safetensors",
218
+ "model.layers.32.mlp.up_proj.weight": "model-00024-of-00045.safetensors",
219
+ "model.layers.32.self_attn.k_proj.weight": "model-00024-of-00045.safetensors",
220
+ "model.layers.32.self_attn.o_proj.weight": "model-00024-of-00045.safetensors",
221
+ "model.layers.32.self_attn.q_proj.weight": "model-00024-of-00045.safetensors",
222
+ "model.layers.32.self_attn.v_proj.weight": "model-00024-of-00045.safetensors",
223
+ "model.layers.33.input_layernorm.weight": "model-00025-of-00045.safetensors",
224
+ "model.layers.33.mlp.down_proj.weight": "model-00025-of-00045.safetensors",
225
+ "model.layers.33.mlp.gate_proj.weight": "model-00025-of-00045.safetensors",
226
+ "model.layers.33.mlp.up_proj.weight": "model-00025-of-00045.safetensors",
227
+ "model.layers.33.self_attn.k_proj.weight": "model-00025-of-00045.safetensors",
228
+ "model.layers.33.self_attn.o_proj.weight": "model-00025-of-00045.safetensors",
229
+ "model.layers.33.self_attn.q_proj.weight": "model-00025-of-00045.safetensors",
230
+ "model.layers.33.self_attn.v_proj.weight": "model-00025-of-00045.safetensors",
231
+ "model.layers.34.input_layernorm.weight": "model-00026-of-00045.safetensors",
232
+ "model.layers.34.mlp.down_proj.weight": "model-00026-of-00045.safetensors",
233
+ "model.layers.34.mlp.gate_proj.weight": "model-00025-of-00045.safetensors",
234
+ "model.layers.34.mlp.up_proj.weight": "model-00026-of-00045.safetensors",
235
+ "model.layers.34.self_attn.k_proj.weight": "model-00025-of-00045.safetensors",
236
+ "model.layers.34.self_attn.o_proj.weight": "model-00025-of-00045.safetensors",
237
+ "model.layers.34.self_attn.q_proj.weight": "model-00025-of-00045.safetensors",
238
+ "model.layers.34.self_attn.v_proj.weight": "model-00025-of-00045.safetensors",
239
+ "model.layers.35.input_layernorm.weight": "model-00026-of-00045.safetensors",
240
+ "model.layers.35.mlp.down_proj.weight": "model-00026-of-00045.safetensors",
241
+ "model.layers.35.mlp.gate_proj.weight": "model-00026-of-00045.safetensors",
242
+ "model.layers.35.mlp.up_proj.weight": "model-00026-of-00045.safetensors",
243
+ "model.layers.35.self_attn.k_proj.weight": "model-00026-of-00045.safetensors",
244
+ "model.layers.35.self_attn.o_proj.weight": "model-00026-of-00045.safetensors",
245
+ "model.layers.35.self_attn.q_proj.weight": "model-00026-of-00045.safetensors",
246
+ "model.layers.35.self_attn.v_proj.weight": "model-00026-of-00045.safetensors",
247
+ "model.layers.36.input_layernorm.weight": "model-00027-of-00045.safetensors",
248
+ "model.layers.36.mlp.down_proj.weight": "model-00027-of-00045.safetensors",
249
+ "model.layers.36.mlp.gate_proj.weight": "model-00027-of-00045.safetensors",
250
+ "model.layers.36.mlp.up_proj.weight": "model-00027-of-00045.safetensors",
251
+ "model.layers.36.self_attn.k_proj.weight": "model-00027-of-00045.safetensors",
252
+ "model.layers.36.self_attn.o_proj.weight": "model-00027-of-00045.safetensors",
253
+ "model.layers.36.self_attn.q_proj.weight": "model-00027-of-00045.safetensors",
254
+ "model.layers.36.self_attn.v_proj.weight": "model-00027-of-00045.safetensors",
255
+ "model.layers.37.input_layernorm.weight": "model-00028-of-00045.safetensors",
256
+ "model.layers.37.mlp.down_proj.weight": "model-00028-of-00045.safetensors",
257
+ "model.layers.37.mlp.gate_proj.weight": "model-00027-of-00045.safetensors",
258
+ "model.layers.37.mlp.up_proj.weight": "model-00028-of-00045.safetensors",
259
+ "model.layers.37.self_attn.k_proj.weight": "model-00027-of-00045.safetensors",
260
+ "model.layers.37.self_attn.o_proj.weight": "model-00027-of-00045.safetensors",
261
+ "model.layers.37.self_attn.q_proj.weight": "model-00027-of-00045.safetensors",
262
+ "model.layers.37.self_attn.v_proj.weight": "model-00027-of-00045.safetensors",
263
+ "model.layers.38.input_layernorm.weight": "model-00028-of-00045.safetensors",
264
+ "model.layers.38.mlp.down_proj.weight": "model-00028-of-00045.safetensors",
265
+ "model.layers.38.mlp.gate_proj.weight": "model-00028-of-00045.safetensors",
266
+ "model.layers.38.mlp.up_proj.weight": "model-00028-of-00045.safetensors",
267
+ "model.layers.38.self_attn.k_proj.weight": "model-00028-of-00045.safetensors",
268
+ "model.layers.38.self_attn.o_proj.weight": "model-00028-of-00045.safetensors",
269
+ "model.layers.38.self_attn.q_proj.weight": "model-00028-of-00045.safetensors",
270
+ "model.layers.38.self_attn.v_proj.weight": "model-00028-of-00045.safetensors",
271
+ "model.layers.39.input_layernorm.weight": "model-00029-of-00045.safetensors",
272
+ "model.layers.39.mlp.down_proj.weight": "model-00029-of-00045.safetensors",
273
+ "model.layers.39.mlp.gate_proj.weight": "model-00029-of-00045.safetensors",
274
+ "model.layers.39.mlp.up_proj.weight": "model-00029-of-00045.safetensors",
275
+ "model.layers.39.self_attn.k_proj.weight": "model-00029-of-00045.safetensors",
276
+ "model.layers.39.self_attn.o_proj.weight": "model-00029-of-00045.safetensors",
277
+ "model.layers.39.self_attn.q_proj.weight": "model-00029-of-00045.safetensors",
278
+ "model.layers.39.self_attn.v_proj.weight": "model-00029-of-00045.safetensors",
279
+ "model.layers.4.input_layernorm.weight": "model-00006-of-00045.safetensors",
280
+ "model.layers.4.mlp.down_proj.weight": "model-00006-of-00045.safetensors",
281
+ "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00045.safetensors",
282
+ "model.layers.4.mlp.up_proj.weight": "model-00006-of-00045.safetensors",
283
+ "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00045.safetensors",
284
+ "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00045.safetensors",
285
+ "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00045.safetensors",
286
+ "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00045.safetensors",
287
+ "model.layers.40.input_layernorm.weight": "model-00030-of-00045.safetensors",
288
+ "model.layers.40.mlp.down_proj.weight": "model-00030-of-00045.safetensors",
289
+ "model.layers.40.mlp.gate_proj.weight": "model-00029-of-00045.safetensors",
290
+ "model.layers.40.mlp.up_proj.weight": "model-00030-of-00045.safetensors",
291
+ "model.layers.40.self_attn.k_proj.weight": "model-00029-of-00045.safetensors",
292
+ "model.layers.40.self_attn.o_proj.weight": "model-00029-of-00045.safetensors",
293
+ "model.layers.40.self_attn.q_proj.weight": "model-00029-of-00045.safetensors",
294
+ "model.layers.40.self_attn.v_proj.weight": "model-00029-of-00045.safetensors",
295
+ "model.layers.41.input_layernorm.weight": "model-00030-of-00045.safetensors",
296
+ "model.layers.41.mlp.down_proj.weight": "model-00030-of-00045.safetensors",
297
+ "model.layers.41.mlp.gate_proj.weight": "model-00030-of-00045.safetensors",
298
+ "model.layers.41.mlp.up_proj.weight": "model-00030-of-00045.safetensors",
299
+ "model.layers.41.self_attn.k_proj.weight": "model-00030-of-00045.safetensors",
300
+ "model.layers.41.self_attn.o_proj.weight": "model-00030-of-00045.safetensors",
301
+ "model.layers.41.self_attn.q_proj.weight": "model-00030-of-00045.safetensors",
302
+ "model.layers.41.self_attn.v_proj.weight": "model-00030-of-00045.safetensors",
303
+ "model.layers.42.input_layernorm.weight": "model-00031-of-00045.safetensors",
304
+ "model.layers.42.mlp.down_proj.weight": "model-00031-of-00045.safetensors",
305
+ "model.layers.42.mlp.gate_proj.weight": "model-00031-of-00045.safetensors",
306
+ "model.layers.42.mlp.up_proj.weight": "model-00031-of-00045.safetensors",
307
+ "model.layers.42.self_attn.k_proj.weight": "model-00031-of-00045.safetensors",
308
+ "model.layers.42.self_attn.o_proj.weight": "model-00031-of-00045.safetensors",
309
+ "model.layers.42.self_attn.q_proj.weight": "model-00031-of-00045.safetensors",
310
+ "model.layers.42.self_attn.v_proj.weight": "model-00031-of-00045.safetensors",
311
+ "model.layers.43.input_layernorm.weight": "model-00032-of-00045.safetensors",
312
+ "model.layers.43.mlp.down_proj.weight": "model-00032-of-00045.safetensors",
313
+ "model.layers.43.mlp.gate_proj.weight": "model-00031-of-00045.safetensors",
314
+ "model.layers.43.mlp.up_proj.weight": "model-00032-of-00045.safetensors",
315
+ "model.layers.43.self_attn.k_proj.weight": "model-00031-of-00045.safetensors",
316
+ "model.layers.43.self_attn.o_proj.weight": "model-00031-of-00045.safetensors",
317
+ "model.layers.43.self_attn.q_proj.weight": "model-00031-of-00045.safetensors",
318
+ "model.layers.43.self_attn.v_proj.weight": "model-00031-of-00045.safetensors",
319
+ "model.layers.44.input_layernorm.weight": "model-00032-of-00045.safetensors",
320
+ "model.layers.44.mlp.down_proj.weight": "model-00032-of-00045.safetensors",
321
+ "model.layers.44.mlp.gate_proj.weight": "model-00032-of-00045.safetensors",
322
+ "model.layers.44.mlp.up_proj.weight": "model-00032-of-00045.safetensors",
323
+ "model.layers.44.self_attn.k_proj.weight": "model-00032-of-00045.safetensors",
324
+ "model.layers.44.self_attn.o_proj.weight": "model-00032-of-00045.safetensors",
325
+ "model.layers.44.self_attn.q_proj.weight": "model-00032-of-00045.safetensors",
326
+ "model.layers.44.self_attn.v_proj.weight": "model-00032-of-00045.safetensors",
327
+ "model.layers.45.input_layernorm.weight": "model-00033-of-00045.safetensors",
328
+ "model.layers.45.mlp.down_proj.weight": "model-00033-of-00045.safetensors",
329
+ "model.layers.45.mlp.gate_proj.weight": "model-00033-of-00045.safetensors",
330
+ "model.layers.45.mlp.up_proj.weight": "model-00033-of-00045.safetensors",
331
+ "model.layers.45.self_attn.k_proj.weight": "model-00033-of-00045.safetensors",
332
+ "model.layers.45.self_attn.o_proj.weight": "model-00033-of-00045.safetensors",
333
+ "model.layers.45.self_attn.q_proj.weight": "model-00033-of-00045.safetensors",
334
+ "model.layers.45.self_attn.v_proj.weight": "model-00033-of-00045.safetensors",
335
+ "model.layers.46.input_layernorm.weight": "model-00034-of-00045.safetensors",
336
+ "model.layers.46.mlp.down_proj.weight": "model-00034-of-00045.safetensors",
337
+ "model.layers.46.mlp.gate_proj.weight": "model-00033-of-00045.safetensors",
338
+ "model.layers.46.mlp.up_proj.weight": "model-00034-of-00045.safetensors",
339
+ "model.layers.46.self_attn.k_proj.weight": "model-00033-of-00045.safetensors",
340
+ "model.layers.46.self_attn.o_proj.weight": "model-00033-of-00045.safetensors",
341
+ "model.layers.46.self_attn.q_proj.weight": "model-00033-of-00045.safetensors",
342
+ "model.layers.46.self_attn.v_proj.weight": "model-00033-of-00045.safetensors",
343
+ "model.layers.47.input_layernorm.weight": "model-00034-of-00045.safetensors",
344
+ "model.layers.47.mlp.down_proj.weight": "model-00034-of-00045.safetensors",
345
+ "model.layers.47.mlp.gate_proj.weight": "model-00034-of-00045.safetensors",
346
+ "model.layers.47.mlp.up_proj.weight": "model-00034-of-00045.safetensors",
347
+ "model.layers.47.self_attn.k_proj.weight": "model-00034-of-00045.safetensors",
348
+ "model.layers.47.self_attn.o_proj.weight": "model-00034-of-00045.safetensors",
349
+ "model.layers.47.self_attn.q_proj.weight": "model-00034-of-00045.safetensors",
350
+ "model.layers.47.self_attn.v_proj.weight": "model-00034-of-00045.safetensors",
351
+ "model.layers.48.input_layernorm.weight": "model-00035-of-00045.safetensors",
352
+ "model.layers.48.mlp.down_proj.weight": "model-00035-of-00045.safetensors",
353
+ "model.layers.48.mlp.gate_proj.weight": "model-00035-of-00045.safetensors",
354
+ "model.layers.48.mlp.up_proj.weight": "model-00035-of-00045.safetensors",
355
+ "model.layers.48.self_attn.k_proj.weight": "model-00035-of-00045.safetensors",
356
+ "model.layers.48.self_attn.o_proj.weight": "model-00035-of-00045.safetensors",
357
+ "model.layers.48.self_attn.q_proj.weight": "model-00035-of-00045.safetensors",
358
+ "model.layers.48.self_attn.v_proj.weight": "model-00035-of-00045.safetensors",
359
+ "model.layers.49.input_layernorm.weight": "model-00036-of-00045.safetensors",
360
+ "model.layers.49.mlp.down_proj.weight": "model-00036-of-00045.safetensors",
361
+ "model.layers.49.mlp.gate_proj.weight": "model-00035-of-00045.safetensors",
362
+ "model.layers.49.mlp.up_proj.weight": "model-00036-of-00045.safetensors",
363
+ "model.layers.49.self_attn.k_proj.weight": "model-00035-of-00045.safetensors",
364
+ "model.layers.49.self_attn.o_proj.weight": "model-00035-of-00045.safetensors",
365
+ "model.layers.49.self_attn.q_proj.weight": "model-00035-of-00045.safetensors",
366
+ "model.layers.49.self_attn.v_proj.weight": "model-00035-of-00045.safetensors",
367
+ "model.layers.5.input_layernorm.weight": "model-00006-of-00045.safetensors",
368
+ "model.layers.5.mlp.down_proj.weight": "model-00006-of-00045.safetensors",
369
+ "model.layers.5.mlp.gate_proj.weight": "model-00006-of-00045.safetensors",
370
+ "model.layers.5.mlp.up_proj.weight": "model-00006-of-00045.safetensors",
371
+ "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00045.safetensors",
372
+ "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00045.safetensors",
373
+ "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00045.safetensors",
374
+ "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00045.safetensors",
375
+ "model.layers.50.input_layernorm.weight": "model-00036-of-00045.safetensors",
376
+ "model.layers.50.mlp.down_proj.weight": "model-00036-of-00045.safetensors",
377
+ "model.layers.50.mlp.gate_proj.weight": "model-00036-of-00045.safetensors",
378
+ "model.layers.50.mlp.up_proj.weight": "model-00036-of-00045.safetensors",
379
+ "model.layers.50.self_attn.k_proj.weight": "model-00036-of-00045.safetensors",
380
+ "model.layers.50.self_attn.o_proj.weight": "model-00036-of-00045.safetensors",
381
+ "model.layers.50.self_attn.q_proj.weight": "model-00036-of-00045.safetensors",
382
+ "model.layers.50.self_attn.v_proj.weight": "model-00036-of-00045.safetensors",
383
+ "model.layers.51.input_layernorm.weight": "model-00037-of-00045.safetensors",
384
+ "model.layers.51.mlp.down_proj.weight": "model-00037-of-00045.safetensors",
385
+ "model.layers.51.mlp.gate_proj.weight": "model-00037-of-00045.safetensors",
386
+ "model.layers.51.mlp.up_proj.weight": "model-00037-of-00045.safetensors",
387
+ "model.layers.51.self_attn.k_proj.weight": "model-00037-of-00045.safetensors",
388
+ "model.layers.51.self_attn.o_proj.weight": "model-00037-of-00045.safetensors",
389
+ "model.layers.51.self_attn.q_proj.weight": "model-00037-of-00045.safetensors",
390
+ "model.layers.51.self_attn.v_proj.weight": "model-00037-of-00045.safetensors",
391
+ "model.layers.52.input_layernorm.weight": "model-00038-of-00045.safetensors",
392
+ "model.layers.52.mlp.down_proj.weight": "model-00038-of-00045.safetensors",
393
+ "model.layers.52.mlp.gate_proj.weight": "model-00037-of-00045.safetensors",
394
+ "model.layers.52.mlp.up_proj.weight": "model-00038-of-00045.safetensors",
395
+ "model.layers.52.self_attn.k_proj.weight": "model-00037-of-00045.safetensors",
396
+ "model.layers.52.self_attn.o_proj.weight": "model-00037-of-00045.safetensors",
397
+ "model.layers.52.self_attn.q_proj.weight": "model-00037-of-00045.safetensors",
398
+ "model.layers.52.self_attn.v_proj.weight": "model-00037-of-00045.safetensors",
399
+ "model.layers.53.input_layernorm.weight": "model-00038-of-00045.safetensors",
400
+ "model.layers.53.mlp.down_proj.weight": "model-00038-of-00045.safetensors",
401
+ "model.layers.53.mlp.gate_proj.weight": "model-00038-of-00045.safetensors",
402
+ "model.layers.53.mlp.up_proj.weight": "model-00038-of-00045.safetensors",
403
+ "model.layers.53.self_attn.k_proj.weight": "model-00038-of-00045.safetensors",
404
+ "model.layers.53.self_attn.o_proj.weight": "model-00038-of-00045.safetensors",
405
+ "model.layers.53.self_attn.q_proj.weight": "model-00038-of-00045.safetensors",
406
+ "model.layers.53.self_attn.v_proj.weight": "model-00038-of-00045.safetensors",
407
+ "model.layers.54.input_layernorm.weight": "model-00039-of-00045.safetensors",
408
+ "model.layers.54.mlp.down_proj.weight": "model-00039-of-00045.safetensors",
409
+ "model.layers.54.mlp.gate_proj.weight": "model-00039-of-00045.safetensors",
410
+ "model.layers.54.mlp.up_proj.weight": "model-00039-of-00045.safetensors",
411
+ "model.layers.54.self_attn.k_proj.weight": "model-00039-of-00045.safetensors",
412
+ "model.layers.54.self_attn.o_proj.weight": "model-00039-of-00045.safetensors",
413
+ "model.layers.54.self_attn.q_proj.weight": "model-00039-of-00045.safetensors",
414
+ "model.layers.54.self_attn.v_proj.weight": "model-00039-of-00045.safetensors",
415
+ "model.layers.55.input_layernorm.weight": "model-00040-of-00045.safetensors",
416
+ "model.layers.55.mlp.down_proj.weight": "model-00040-of-00045.safetensors",
417
+ "model.layers.55.mlp.gate_proj.weight": "model-00039-of-00045.safetensors",
418
+ "model.layers.55.mlp.up_proj.weight": "model-00040-of-00045.safetensors",
419
+ "model.layers.55.self_attn.k_proj.weight": "model-00039-of-00045.safetensors",
420
+ "model.layers.55.self_attn.o_proj.weight": "model-00039-of-00045.safetensors",
421
+ "model.layers.55.self_attn.q_proj.weight": "model-00039-of-00045.safetensors",
422
+ "model.layers.55.self_attn.v_proj.weight": "model-00039-of-00045.safetensors",
423
+ "model.layers.56.input_layernorm.weight": "model-00040-of-00045.safetensors",
424
+ "model.layers.56.mlp.down_proj.weight": "model-00040-of-00045.safetensors",
425
+ "model.layers.56.mlp.gate_proj.weight": "model-00040-of-00045.safetensors",
426
+ "model.layers.56.mlp.up_proj.weight": "model-00040-of-00045.safetensors",
427
+ "model.layers.56.self_attn.k_proj.weight": "model-00040-of-00045.safetensors",
428
+ "model.layers.56.self_attn.o_proj.weight": "model-00040-of-00045.safetensors",
429
+ "model.layers.56.self_attn.q_proj.weight": "model-00040-of-00045.safetensors",
430
+ "model.layers.56.self_attn.v_proj.weight": "model-00040-of-00045.safetensors",
431
+ "model.layers.57.input_layernorm.weight": "model-00041-of-00045.safetensors",
432
+ "model.layers.57.mlp.down_proj.weight": "model-00041-of-00045.safetensors",
433
+ "model.layers.57.mlp.gate_proj.weight": "model-00041-of-00045.safetensors",
434
+ "model.layers.57.mlp.up_proj.weight": "model-00041-of-00045.safetensors",
435
+ "model.layers.57.self_attn.k_proj.weight": "model-00041-of-00045.safetensors",
436
+ "model.layers.57.self_attn.o_proj.weight": "model-00041-of-00045.safetensors",
437
+ "model.layers.57.self_attn.q_proj.weight": "model-00041-of-00045.safetensors",
438
+ "model.layers.57.self_attn.v_proj.weight": "model-00041-of-00045.safetensors",
439
+ "model.layers.58.input_layernorm.weight": "model-00042-of-00045.safetensors",
440
+ "model.layers.58.mlp.down_proj.weight": "model-00042-of-00045.safetensors",
441
+ "model.layers.58.mlp.gate_proj.weight": "model-00041-of-00045.safetensors",
442
+ "model.layers.58.mlp.up_proj.weight": "model-00042-of-00045.safetensors",
443
+ "model.layers.58.self_attn.k_proj.weight": "model-00041-of-00045.safetensors",
444
+ "model.layers.58.self_attn.o_proj.weight": "model-00041-of-00045.safetensors",
445
+ "model.layers.58.self_attn.q_proj.weight": "model-00041-of-00045.safetensors",
446
+ "model.layers.58.self_attn.v_proj.weight": "model-00041-of-00045.safetensors",
447
+ "model.layers.59.input_layernorm.weight": "model-00042-of-00045.safetensors",
448
+ "model.layers.59.mlp.down_proj.weight": "model-00042-of-00045.safetensors",
449
+ "model.layers.59.mlp.gate_proj.weight": "model-00042-of-00045.safetensors",
450
+ "model.layers.59.mlp.up_proj.weight": "model-00042-of-00045.safetensors",
451
+ "model.layers.59.self_attn.k_proj.weight": "model-00042-of-00045.safetensors",
452
+ "model.layers.59.self_attn.o_proj.weight": "model-00042-of-00045.safetensors",
453
+ "model.layers.59.self_attn.q_proj.weight": "model-00042-of-00045.safetensors",
454
+ "model.layers.59.self_attn.v_proj.weight": "model-00042-of-00045.safetensors",
455
+ "model.layers.6.input_layernorm.weight": "model-00007-of-00045.safetensors",
456
+ "model.layers.6.mlp.down_proj.weight": "model-00007-of-00045.safetensors",
457
+ "model.layers.6.mlp.gate_proj.weight": "model-00007-of-00045.safetensors",
458
+ "model.layers.6.mlp.up_proj.weight": "model-00007-of-00045.safetensors",
459
+ "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00045.safetensors",
460
+ "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00045.safetensors",
461
+ "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00045.safetensors",
462
+ "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00045.safetensors",
463
+ "model.layers.60.input_layernorm.weight": "model-00043-of-00045.safetensors",
464
+ "model.layers.60.mlp.down_proj.weight": "model-00043-of-00045.safetensors",
465
+ "model.layers.60.mlp.gate_proj.weight": "model-00043-of-00045.safetensors",
466
+ "model.layers.60.mlp.up_proj.weight": "model-00043-of-00045.safetensors",
467
+ "model.layers.60.self_attn.k_proj.weight": "model-00043-of-00045.safetensors",
468
+ "model.layers.60.self_attn.o_proj.weight": "model-00043-of-00045.safetensors",
469
+ "model.layers.60.self_attn.q_proj.weight": "model-00043-of-00045.safetensors",
470
+ "model.layers.60.self_attn.v_proj.weight": "model-00043-of-00045.safetensors",
471
+ "model.layers.61.input_layernorm.weight": "model-00044-of-00045.safetensors",
472
+ "model.layers.61.mlp.down_proj.weight": "model-00044-of-00045.safetensors",
473
+ "model.layers.61.mlp.gate_proj.weight": "model-00043-of-00045.safetensors",
474
+ "model.layers.61.mlp.up_proj.weight": "model-00044-of-00045.safetensors",
475
+ "model.layers.61.self_attn.k_proj.weight": "model-00043-of-00045.safetensors",
476
+ "model.layers.61.self_attn.o_proj.weight": "model-00043-of-00045.safetensors",
477
+ "model.layers.61.self_attn.q_proj.weight": "model-00043-of-00045.safetensors",
478
+ "model.layers.61.self_attn.v_proj.weight": "model-00043-of-00045.safetensors",
479
+ "model.layers.62.input_layernorm.weight": "model-00044-of-00045.safetensors",
480
+ "model.layers.62.mlp.down_proj.weight": "model-00044-of-00045.safetensors",
481
+ "model.layers.62.mlp.gate_proj.weight": "model-00044-of-00045.safetensors",
482
+ "model.layers.62.mlp.up_proj.weight": "model-00044-of-00045.safetensors",
483
+ "model.layers.62.self_attn.k_proj.weight": "model-00044-of-00045.safetensors",
484
+ "model.layers.62.self_attn.o_proj.weight": "model-00044-of-00045.safetensors",
485
+ "model.layers.62.self_attn.q_proj.weight": "model-00044-of-00045.safetensors",
486
+ "model.layers.62.self_attn.v_proj.weight": "model-00044-of-00045.safetensors",
487
+ "model.layers.63.input_layernorm.weight": "model-00045-of-00045.safetensors",
488
+ "model.layers.63.mlp.down_proj.weight": "model-00045-of-00045.safetensors",
489
+ "model.layers.63.mlp.gate_proj.weight": "model-00045-of-00045.safetensors",
490
+ "model.layers.63.mlp.up_proj.weight": "model-00045-of-00045.safetensors",
491
+ "model.layers.63.self_attn.k_proj.weight": "model-00045-of-00045.safetensors",
492
+ "model.layers.63.self_attn.o_proj.weight": "model-00045-of-00045.safetensors",
493
+ "model.layers.63.self_attn.q_proj.weight": "model-00045-of-00045.safetensors",
494
+ "model.layers.63.self_attn.v_proj.weight": "model-00045-of-00045.safetensors",
495
+ "model.layers.7.input_layernorm.weight": "model-00008-of-00045.safetensors",
496
+ "model.layers.7.mlp.down_proj.weight": "model-00008-of-00045.safetensors",
497
+ "model.layers.7.mlp.gate_proj.weight": "model-00007-of-00045.safetensors",
498
+ "model.layers.7.mlp.up_proj.weight": "model-00008-of-00045.safetensors",
499
+ "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00045.safetensors",
500
+ "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00045.safetensors",
501
+ "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00045.safetensors",
502
+ "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00045.safetensors",
503
+ "model.layers.8.input_layernorm.weight": "model-00008-of-00045.safetensors",
504
+ "model.layers.8.mlp.down_proj.weight": "model-00008-of-00045.safetensors",
505
+ "model.layers.8.mlp.gate_proj.weight": "model-00008-of-00045.safetensors",
506
+ "model.layers.8.mlp.up_proj.weight": "model-00008-of-00045.safetensors",
507
+ "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00045.safetensors",
508
+ "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00045.safetensors",
509
+ "model.layers.8.self_attn.q_proj.weight": "model-00008-of-00045.safetensors",
510
+ "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00045.safetensors",
511
+ "model.layers.9.input_layernorm.weight": "model-00009-of-00045.safetensors",
512
+ "model.layers.9.mlp.down_proj.weight": "model-00009-of-00045.safetensors",
513
+ "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00045.safetensors",
514
+ "model.layers.9.mlp.up_proj.weight": "model-00009-of-00045.safetensors",
515
+ "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00045.safetensors",
516
+ "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00045.safetensors",
517
+ "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00045.safetensors",
518
+ "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00045.safetensors",
519
+ "model.norm.weight": "model-00045-of-00045.safetensors"
520
+ }
521
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<BOS_TOKEN>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|END_OF_TURN_TOKEN|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<PAD>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<UNK>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }