Hugging Face's logo

kainatq
/
Koder-Quantum-14b

Text Generation
Transformers
Safetensors
qwen2
Merge
mergekit
lazymergekit
conversational
text-generation-inference
Model card Files
xet
Community
kainatq commited on
Commit
07f264c
·
verified ·
1 Parent(s): ed86482

Upload folder using huggingface_hub

Browse files
Files changed (38) hide show
  1. README.md +33 -0
  2. added_tokens.json +24 -0
  3. config.json +78 -0
  4. mergekit_config.yml +9 -0
  5. model-00001-of-00030.safetensors +3 -0
  6. model-00002-of-00030.safetensors +3 -0
  7. model-00003-of-00030.safetensors +3 -0
  8. model-00004-of-00030.safetensors +3 -0
  9. model-00005-of-00030.safetensors +3 -0
  10. model-00006-of-00030.safetensors +3 -0
  11. model-00007-of-00030.safetensors +3 -0
  12. model-00008-of-00030.safetensors +3 -0
  13. model-00009-of-00030.safetensors +3 -0
  14. model-00010-of-00030.safetensors +3 -0
  15. model-00011-of-00030.safetensors +3 -0
  16. model-00012-of-00030.safetensors +3 -0
  17. model-00013-of-00030.safetensors +3 -0
  18. model-00014-of-00030.safetensors +3 -0
  19. model-00015-of-00030.safetensors +3 -0
  20. model-00016-of-00030.safetensors +3 -0
  21. model-00017-of-00030.safetensors +3 -0
  22. model-00018-of-00030.safetensors +3 -0
  23. model-00019-of-00030.safetensors +3 -0
  24. model-00020-of-00030.safetensors +3 -0
  25. model-00021-of-00030.safetensors +3 -0
  26. model-00022-of-00030.safetensors +3 -0
  27. model-00023-of-00030.safetensors +3 -0
  28. model-00024-of-00030.safetensors +3 -0
  29. model-00025-of-00030.safetensors +3 -0
  30. model-00026-of-00030.safetensors +3 -0
  31. model-00027-of-00030.safetensors +3 -0
  32. model-00028-of-00030.safetensors +3 -0
  33. model-00029-of-00030.safetensors +3 -0
  34. model-00030-of-00030.safetensors +3 -0
  35. model.safetensors.index.json +587 -0
  36. special_tokens_map.json +31 -0
  37. tokenizer.json +0 -0
  38. tokenizer_config.json +207 -0
README.md ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ tags:
5
+ - merge
6
+ - mergekit
7
+ - lazymergekit
8
+ base_model:
9
+ - v000000/Qwen2.5-Lumen-14B
10
+ - Qwen/Qwen2.5-Coder-14B
11
+ - Qwen/Qwen2.5-Coder-14B-Instruct
12
+ - prithivMLmods/Sombrero-Opus-14B-Elite5
13
+ ---
14
+
15
+ # Koder-Quantum-14b
16
+
17
+ Koder-Quantum-14b is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
18
+ * [v000000/Qwen2.5-Lumen-14B](https://huggingface.co/v000000/Qwen2.5-Lumen-14B)
19
+ * [Qwen/Qwen2.5-Coder-14B](https://huggingface.co/Qwen/Qwen2.5-Coder-14B)
20
+ * [Qwen/Qwen2.5-Coder-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct)
21
+ * [prithivMLmods/Sombrero-Opus-14B-Elite5](https://huggingface.co/prithivMLmods/Sombrero-Opus-14B-Elite5)
22
+
23
+ ## 🧩 Configuration
24
+
25
+ ```yamlmerge_method: model_stock
26
+ base_model: v000000/Qwen2.5-Lumen-14B
27
+ parameters:
28
+ models:
29
+ - model: v000000/Qwen2.5-Lumen-14B
30
+ - model: Qwen/Qwen2.5-Coder-14B
31
+ - model: Qwen/Qwen2.5-Coder-14B-Instruct
32
+ - model: prithivMLmods/Sombrero-Opus-14B-Elite5
33
+ dtype: bfloat16```
added_tokens.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13824,
13
+ "layer_types": [
14
+ "full_attention",
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention",
46
+ "full_attention",
47
+ "full_attention",
48
+ "full_attention",
49
+ "full_attention",
50
+ "full_attention",
51
+ "full_attention",
52
+ "full_attention",
53
+ "full_attention",
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention"
62
+ ],
63
+ "max_position_embeddings": 32768,
64
+ "max_window_layers": 70,
65
+ "model_type": "qwen2",
66
+ "num_attention_heads": 40,
67
+ "num_hidden_layers": 48,
68
+ "num_key_value_heads": 8,
69
+ "rms_norm_eps": 1e-06,
70
+ "rope_scaling": null,
71
+ "rope_theta": 1000000.0,
72
+ "sliding_window": null,
73
+ "tie_word_embeddings": false,
74
+ "transformers_version": "4.57.1",
75
+ "use_cache": true,
76
+ "use_sliding_window": false,
77
+ "vocab_size": 152064
78
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ merge_method: model_stock
2
+ base_model: v000000/Qwen2.5-Lumen-14B
3
+ parameters:
4
+ models:
5
+ - model: v000000/Qwen2.5-Lumen-14B
6
+ - model: Qwen/Qwen2.5-Coder-14B
7
+ - model: Qwen/Qwen2.5-Coder-14B-Instruct
8
+ - model: prithivMLmods/Sombrero-Opus-14B-Elite5
9
+ dtype: bfloat16
model-00001-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2758d153e41c192f4fb62f8d3de1cd93dd01bf3b0934071b2eb32bfea8500be1
3
+ size 1553049728
model-00002-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc2910260ddf86ca22568a72336b6b19a70efcdf90eaefa6c843895e397717e7
3
+ size 1553049744
model-00003-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9cb29886d3b4aa4ca2b95ced14d59aba00f8afa7fa0ac2580b9597f09d5b83e
3
+ size 985720944
model-00004-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49b1235db2a2b228a9e152fd627bc1a8c0688be9a30d1567fc3b47865ea83c3e
3
+ size 949020912
model-00005-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2405527702389d09950908a6c78ec390666bbed8cb2f28c6b72d022057f3b5d
3
+ size 959519312
model-00006-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cfa4531fef2207ed00bb277a9118b48708c29684e80f276e44698c75dfa7df8
3
+ size 959519312
model-00007-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b00311779cf1bfd1be434851e02cefca62b2bd38c62e6ea3783d568f6278fa5
3
+ size 985710624
model-00008-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22644006227ff6d1fc24a2b1ebe9af03738f8b1bc9507a71e97c41d148aada6f
3
+ size 949020920
model-00009-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad3f16d5631430f663527afddbbd0853f7264f24b44e0557236a9f60f0126abc
3
+ size 959519312
model-00010-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db69a901d37a5de94687518c415780da93ea8a59c6a2736a961e603002631e0d
3
+ size 959519304
model-00011-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:714c19493fcb50c266a31c0a9c144a0e6624fba08fa68ebf7bf19dafe6eaa3a6
3
+ size 985710624
model-00012-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e6ec0ab388088f80b37a096be5aa462d861049bb52980b0a8edf9e1dd3e80ce
3
+ size 949020920
model-00013-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a819cb05d3e5684be38acf58a32b5a288ad7200127b9f8a4b08d33a45a77a54
3
+ size 959519312
model-00014-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4f63c933fff050566f71243da6ebecc125bfed50a7b496325edc58d7677c122
3
+ size 959519312
model-00015-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c341b843db1999c75c57afee42efcb42ea52445bf76cda129454374da7fa1063
3
+ size 985710624
model-00016-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ca932ada9692b8001d3263769f1b454c22751597f93193dbc6b1bdf0514cd5b
3
+ size 949020904
model-00017-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74fb1792d61f58bc4ce6ebb577071227aab9299d54451f0f142fcaadd713ffb7
3
+ size 959519312
model-00018-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9f52deee9ba2824f1696b2e66967d7efd6ccc0e344cb9f46e944a7adeced1c6
3
+ size 959519312
model-00019-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d66f6899a83d3ea36823ff26c6245937981b994eceb10867193218d74b0560a2
3
+ size 985710624
model-00020-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e671a2c5d05bcd2da9e4eb76f61a1987e31b57ca7c05f0974936636b2063e344
3
+ size 949020920
model-00021-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:accb8429c13bb18f0f38cd916511338728c95fcb088242578de8474bdb4d93aa
3
+ size 959519312
model-00022-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9298725a7d2b05e920692d6561472c593a279d74844db131223c6ba402896e8
3
+ size 959519304
model-00023-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2aca40cbdf25bcbf8e2f01857b3cf61566548fd62d1da28bd9c2a9ad9b46e32
3
+ size 985710624
model-00024-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a05e7a0576ee485ef90104bb550cfe9cd0a3c1dfe5c6f3dd7fe2e042ee34f2ad
3
+ size 949020920
model-00025-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aafe0d2e74fac0a4d72592613265e09cebf970fc090fbcda87c49d85d7399b8
3
+ size 959519312
model-00026-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eec344649002a01daaa2234329ac17861c2e814d3f6c4b772d8531f1572147e0
3
+ size 959519312
model-00027-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:318cf4de176cc1699c109893c4d7cb38e387c2d51770661522f176c72f3549df
3
+ size 985710616
model-00028-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7254ef5acb451069fba1b4ea5a692a5d812f42cf4d91940c3f1ccd6a53d4df5
3
+ size 949020896
model-00029-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:634b45455399f9b98887099ca80300bc4e2e2378815b703a17ced1a7285967a0
3
+ size 959519288
model-00030-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e566ebeea9b687c1ea000c029124ed77428f2409911b302de86407493322cd39
3
+ size 408980704
model.safetensors.index.json ADDED
@@ -0,0 +1,587 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 29531895808,
4
+ "mergekit_version": "0.1.4"
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00001-of-00030.safetensors",
8
+ "model.embed_tokens.weight": "model-00002-of-00030.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00003-of-00030.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
11
+ "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
12
+ "model.layers.0.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
14
+ "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00030.safetensors",
15
+ "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
16
+ "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
17
+ "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00030.safetensors",
18
+ "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
19
+ "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00030.safetensors",
20
+ "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
21
+ "model.layers.1.input_layernorm.weight": "model-00003-of-00030.safetensors",
22
+ "model.layers.1.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
23
+ "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
25
+ "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
26
+ "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00030.safetensors",
27
+ "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
28
+ "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
29
+ "model.layers.1.self_attn.q_proj.bias": "model-00004-of-00030.safetensors",
30
+ "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
31
+ "model.layers.1.self_attn.v_proj.bias": "model-00004-of-00030.safetensors",
32
+ "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
33
+ "model.layers.10.input_layernorm.weight": "model-00004-of-00030.safetensors",
34
+ "model.layers.10.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
35
+ "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
36
+ "model.layers.10.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
37
+ "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
38
+ "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00030.safetensors",
39
+ "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
40
+ "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
41
+ "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00030.safetensors",
42
+ "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
43
+ "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00030.safetensors",
44
+ "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
45
+ "model.layers.11.input_layernorm.weight": "model-00004-of-00030.safetensors",
46
+ "model.layers.11.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
47
+ "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
48
+ "model.layers.11.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
49
+ "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
50
+ "model.layers.11.self_attn.k_proj.bias": "model-00005-of-00030.safetensors",
51
+ "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
52
+ "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
53
+ "model.layers.11.self_attn.q_proj.bias": "model-00005-of-00030.safetensors",
54
+ "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
55
+ "model.layers.11.self_attn.v_proj.bias": "model-00005-of-00030.safetensors",
56
+ "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
57
+ "model.layers.12.input_layernorm.weight": "model-00005-of-00030.safetensors",
58
+ "model.layers.12.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
59
+ "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
60
+ "model.layers.12.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
61
+ "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
62
+ "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00030.safetensors",
63
+ "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
64
+ "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
65
+ "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00030.safetensors",
66
+ "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
67
+ "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00030.safetensors",
68
+ "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
69
+ "model.layers.13.input_layernorm.weight": "model-00005-of-00030.safetensors",
70
+ "model.layers.13.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
71
+ "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
72
+ "model.layers.13.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
73
+ "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
74
+ "model.layers.13.self_attn.k_proj.bias": "model-00006-of-00030.safetensors",
75
+ "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
76
+ "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
77
+ "model.layers.13.self_attn.q_proj.bias": "model-00006-of-00030.safetensors",
78
+ "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
79
+ "model.layers.13.self_attn.v_proj.bias": "model-00006-of-00030.safetensors",
80
+ "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
81
+ "model.layers.14.input_layernorm.weight": "model-00006-of-00030.safetensors",
82
+ "model.layers.14.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
83
+ "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
84
+ "model.layers.14.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
85
+ "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
86
+ "model.layers.14.self_attn.k_proj.bias": "model-00006-of-00030.safetensors",
87
+ "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
88
+ "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
89
+ "model.layers.14.self_attn.q_proj.bias": "model-00006-of-00030.safetensors",
90
+ "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
91
+ "model.layers.14.self_attn.v_proj.bias": "model-00006-of-00030.safetensors",
92
+ "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
93
+ "model.layers.15.input_layernorm.weight": "model-00006-of-00030.safetensors",
94
+ "model.layers.15.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
95
+ "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
96
+ "model.layers.15.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
97
+ "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
98
+ "model.layers.15.self_attn.k_proj.bias": "model-00007-of-00030.safetensors",
99
+ "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
100
+ "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
101
+ "model.layers.15.self_attn.q_proj.bias": "model-00007-of-00030.safetensors",
102
+ "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
103
+ "model.layers.15.self_attn.v_proj.bias": "model-00007-of-00030.safetensors",
104
+ "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
105
+ "model.layers.16.input_layernorm.weight": "model-00007-of-00030.safetensors",
106
+ "model.layers.16.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
107
+ "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
108
+ "model.layers.16.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
109
+ "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
110
+ "model.layers.16.self_attn.k_proj.bias": "model-00007-of-00030.safetensors",
111
+ "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
112
+ "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
113
+ "model.layers.16.self_attn.q_proj.bias": "model-00008-of-00030.safetensors",
114
+ "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
115
+ "model.layers.16.self_attn.v_proj.bias": "model-00008-of-00030.safetensors",
116
+ "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
117
+ "model.layers.17.input_layernorm.weight": "model-00008-of-00030.safetensors",
118
+ "model.layers.17.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
119
+ "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
120
+ "model.layers.17.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
121
+ "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
122
+ "model.layers.17.self_attn.k_proj.bias": "model-00008-of-00030.safetensors",
123
+ "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
124
+ "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
125
+ "model.layers.17.self_attn.q_proj.bias": "model-00008-of-00030.safetensors",
126
+ "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
127
+ "model.layers.17.self_attn.v_proj.bias": "model-00008-of-00030.safetensors",
128
+ "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
129
+ "model.layers.18.input_layernorm.weight": "model-00008-of-00030.safetensors",
130
+ "model.layers.18.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
131
+ "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
132
+ "model.layers.18.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
133
+ "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
134
+ "model.layers.18.self_attn.k_proj.bias": "model-00009-of-00030.safetensors",
135
+ "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
136
+ "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
137
+ "model.layers.18.self_attn.q_proj.bias": "model-00009-of-00030.safetensors",
138
+ "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
139
+ "model.layers.18.self_attn.v_proj.bias": "model-00009-of-00030.safetensors",
140
+ "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
141
+ "model.layers.19.input_layernorm.weight": "model-00009-of-00030.safetensors",
142
+ "model.layers.19.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
143
+ "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
144
+ "model.layers.19.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
145
+ "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
146
+ "model.layers.19.self_attn.k_proj.bias": "model-00009-of-00030.safetensors",
147
+ "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
148
+ "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
149
+ "model.layers.19.self_attn.q_proj.bias": "model-00009-of-00030.safetensors",
150
+ "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
151
+ "model.layers.19.self_attn.v_proj.bias": "model-00009-of-00030.safetensors",
152
+ "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
153
+ "model.layers.2.input_layernorm.weight": "model-00009-of-00030.safetensors",
154
+ "model.layers.2.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
155
+ "model.layers.2.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
156
+ "model.layers.2.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
157
+ "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
158
+ "model.layers.2.self_attn.k_proj.bias": "model-00010-of-00030.safetensors",
159
+ "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
160
+ "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
161
+ "model.layers.2.self_attn.q_proj.bias": "model-00010-of-00030.safetensors",
162
+ "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
163
+ "model.layers.2.self_attn.v_proj.bias": "model-00010-of-00030.safetensors",
164
+ "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
165
+ "model.layers.20.input_layernorm.weight": "model-00010-of-00030.safetensors",
166
+ "model.layers.20.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
167
+ "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
168
+ "model.layers.20.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
169
+ "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
170
+ "model.layers.20.self_attn.k_proj.bias": "model-00010-of-00030.safetensors",
171
+ "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
172
+ "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
173
+ "model.layers.20.self_attn.q_proj.bias": "model-00010-of-00030.safetensors",
174
+ "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
175
+ "model.layers.20.self_attn.v_proj.bias": "model-00010-of-00030.safetensors",
176
+ "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
177
+ "model.layers.21.input_layernorm.weight": "model-00010-of-00030.safetensors",
178
+ "model.layers.21.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
179
+ "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
180
+ "model.layers.21.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
181
+ "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
182
+ "model.layers.21.self_attn.k_proj.bias": "model-00011-of-00030.safetensors",
183
+ "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
184
+ "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
185
+ "model.layers.21.self_attn.q_proj.bias": "model-00011-of-00030.safetensors",
186
+ "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
187
+ "model.layers.21.self_attn.v_proj.bias": "model-00011-of-00030.safetensors",
188
+ "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
189
+ "model.layers.22.input_layernorm.weight": "model-00011-of-00030.safetensors",
190
+ "model.layers.22.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
191
+ "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
192
+ "model.layers.22.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
193
+ "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
194
+ "model.layers.22.self_attn.k_proj.bias": "model-00011-of-00030.safetensors",
195
+ "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
196
+ "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
197
+ "model.layers.22.self_attn.q_proj.bias": "model-00012-of-00030.safetensors",
198
+ "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
199
+ "model.layers.22.self_attn.v_proj.bias": "model-00012-of-00030.safetensors",
200
+ "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
201
+ "model.layers.23.input_layernorm.weight": "model-00012-of-00030.safetensors",
202
+ "model.layers.23.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
203
+ "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
204
+ "model.layers.23.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
205
+ "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
206
+ "model.layers.23.self_attn.k_proj.bias": "model-00012-of-00030.safetensors",
207
+ "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
208
+ "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
209
+ "model.layers.23.self_attn.q_proj.bias": "model-00012-of-00030.safetensors",
210
+ "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
211
+ "model.layers.23.self_attn.v_proj.bias": "model-00012-of-00030.safetensors",
212
+ "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
213
+ "model.layers.24.input_layernorm.weight": "model-00012-of-00030.safetensors",
214
+ "model.layers.24.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
215
+ "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
216
+ "model.layers.24.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
217
+ "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
218
+ "model.layers.24.self_attn.k_proj.bias": "model-00013-of-00030.safetensors",
219
+ "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
220
+ "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
221
+ "model.layers.24.self_attn.q_proj.bias": "model-00013-of-00030.safetensors",
222
+ "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
223
+ "model.layers.24.self_attn.v_proj.bias": "model-00013-of-00030.safetensors",
224
+ "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
225
+ "model.layers.25.input_layernorm.weight": "model-00013-of-00030.safetensors",
226
+ "model.layers.25.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
227
+ "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
228
+ "model.layers.25.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
229
+ "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
230
+ "model.layers.25.self_attn.k_proj.bias": "model-00013-of-00030.safetensors",
231
+ "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
232
+ "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
233
+ "model.layers.25.self_attn.q_proj.bias": "model-00013-of-00030.safetensors",
234
+ "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
235
+ "model.layers.25.self_attn.v_proj.bias": "model-00013-of-00030.safetensors",
236
+ "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
237
+ "model.layers.26.input_layernorm.weight": "model-00013-of-00030.safetensors",
238
+ "model.layers.26.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
239
+ "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
240
+ "model.layers.26.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
241
+ "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
242
+ "model.layers.26.self_attn.k_proj.bias": "model-00014-of-00030.safetensors",
243
+ "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
244
+ "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
245
+ "model.layers.26.self_attn.q_proj.bias": "model-00014-of-00030.safetensors",
246
+ "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
247
+ "model.layers.26.self_attn.v_proj.bias": "model-00014-of-00030.safetensors",
248
+ "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
249
+ "model.layers.27.input_layernorm.weight": "model-00014-of-00030.safetensors",
250
+ "model.layers.27.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
251
+ "model.layers.27.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
252
+ "model.layers.27.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
253
+ "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
254
+ "model.layers.27.self_attn.k_proj.bias": "model-00014-of-00030.safetensors",
255
+ "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
256
+ "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
257
+ "model.layers.27.self_attn.q_proj.bias": "model-00014-of-00030.safetensors",
258
+ "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
259
+ "model.layers.27.self_attn.v_proj.bias": "model-00014-of-00030.safetensors",
260
+ "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
261
+ "model.layers.28.input_layernorm.weight": "model-00014-of-00030.safetensors",
262
+ "model.layers.28.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
263
+ "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
264
+ "model.layers.28.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
265
+ "model.layers.28.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
266
+ "model.layers.28.self_attn.k_proj.bias": "model-00015-of-00030.safetensors",
267
+ "model.layers.28.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
268
+ "model.layers.28.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
269
+ "model.layers.28.self_attn.q_proj.bias": "model-00015-of-00030.safetensors",
270
+ "model.layers.28.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
271
+ "model.layers.28.self_attn.v_proj.bias": "model-00015-of-00030.safetensors",
272
+ "model.layers.28.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
273
+ "model.layers.29.input_layernorm.weight": "model-00015-of-00030.safetensors",
274
+ "model.layers.29.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
275
+ "model.layers.29.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
276
+ "model.layers.29.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
277
+ "model.layers.29.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
278
+ "model.layers.29.self_attn.k_proj.bias": "model-00015-of-00030.safetensors",
279
+ "model.layers.29.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
280
+ "model.layers.29.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
281
+ "model.layers.29.self_attn.q_proj.bias": "model-00016-of-00030.safetensors",
282
+ "model.layers.29.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
283
+ "model.layers.29.self_attn.v_proj.bias": "model-00016-of-00030.safetensors",
284
+ "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
285
+ "model.layers.3.input_layernorm.weight": "model-00016-of-00030.safetensors",
286
+ "model.layers.3.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
287
+ "model.layers.3.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
288
+ "model.layers.3.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
289
+ "model.layers.3.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
290
+ "model.layers.3.self_attn.k_proj.bias": "model-00016-of-00030.safetensors",
291
+ "model.layers.3.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
292
+ "model.layers.3.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
293
+ "model.layers.3.self_attn.q_proj.bias": "model-00016-of-00030.safetensors",
294
+ "model.layers.3.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
295
+ "model.layers.3.self_attn.v_proj.bias": "model-00016-of-00030.safetensors",
296
+ "model.layers.3.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
297
+ "model.layers.30.input_layernorm.weight": "model-00016-of-00030.safetensors",
298
+ "model.layers.30.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
299
+ "model.layers.30.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
300
+ "model.layers.30.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
301
+ "model.layers.30.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
302
+ "model.layers.30.self_attn.k_proj.bias": "model-00017-of-00030.safetensors",
303
+ "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
304
+ "model.layers.30.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
305
+ "model.layers.30.self_attn.q_proj.bias": "model-00017-of-00030.safetensors",
306
+ "model.layers.30.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
307
+ "model.layers.30.self_attn.v_proj.bias": "model-00017-of-00030.safetensors",
308
+ "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
309
+ "model.layers.31.input_layernorm.weight": "model-00017-of-00030.safetensors",
310
+ "model.layers.31.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
311
+ "model.layers.31.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
312
+ "model.layers.31.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
313
+ "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
314
+ "model.layers.31.self_attn.k_proj.bias": "model-00017-of-00030.safetensors",
315
+ "model.layers.31.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
316
+ "model.layers.31.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
317
+ "model.layers.31.self_attn.q_proj.bias": "model-00017-of-00030.safetensors",
318
+ "model.layers.31.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
319
+ "model.layers.31.self_attn.v_proj.bias": "model-00017-of-00030.safetensors",
320
+ "model.layers.31.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
321
+ "model.layers.32.input_layernorm.weight": "model-00017-of-00030.safetensors",
322
+ "model.layers.32.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
323
+ "model.layers.32.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
324
+ "model.layers.32.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
325
+ "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
326
+ "model.layers.32.self_attn.k_proj.bias": "model-00018-of-00030.safetensors",
327
+ "model.layers.32.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
328
+ "model.layers.32.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
329
+ "model.layers.32.self_attn.q_proj.bias": "model-00018-of-00030.safetensors",
330
+ "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
331
+ "model.layers.32.self_attn.v_proj.bias": "model-00018-of-00030.safetensors",
332
+ "model.layers.32.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
333
+ "model.layers.33.input_layernorm.weight": "model-00018-of-00030.safetensors",
334
+ "model.layers.33.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
335
+ "model.layers.33.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
336
+ "model.layers.33.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
337
+ "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
338
+ "model.layers.33.self_attn.k_proj.bias": "model-00018-of-00030.safetensors",
339
+ "model.layers.33.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
340
+ "model.layers.33.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
341
+ "model.layers.33.self_attn.q_proj.bias": "model-00018-of-00030.safetensors",
342
+ "model.layers.33.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
343
+ "model.layers.33.self_attn.v_proj.bias": "model-00018-of-00030.safetensors",
344
+ "model.layers.33.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
345
+ "model.layers.34.input_layernorm.weight": "model-00018-of-00030.safetensors",
346
+ "model.layers.34.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
347
+ "model.layers.34.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
348
+ "model.layers.34.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
349
+ "model.layers.34.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
350
+ "model.layers.34.self_attn.k_proj.bias": "model-00019-of-00030.safetensors",
351
+ "model.layers.34.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
352
+ "model.layers.34.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
353
+ "model.layers.34.self_attn.q_proj.bias": "model-00019-of-00030.safetensors",
354
+ "model.layers.34.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
355
+ "model.layers.34.self_attn.v_proj.bias": "model-00019-of-00030.safetensors",
356
+ "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
357
+ "model.layers.35.input_layernorm.weight": "model-00019-of-00030.safetensors",
358
+ "model.layers.35.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
359
+ "model.layers.35.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
360
+ "model.layers.35.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
361
+ "model.layers.35.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
362
+ "model.layers.35.self_attn.k_proj.bias": "model-00019-of-00030.safetensors",
363
+ "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
364
+ "model.layers.35.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
365
+ "model.layers.35.self_attn.q_proj.bias": "model-00020-of-00030.safetensors",
366
+ "model.layers.35.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
367
+ "model.layers.35.self_attn.v_proj.bias": "model-00020-of-00030.safetensors",
368
+ "model.layers.35.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
369
+ "model.layers.36.input_layernorm.weight": "model-00020-of-00030.safetensors",
370
+ "model.layers.36.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
371
+ "model.layers.36.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
372
+ "model.layers.36.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
373
+ "model.layers.36.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
374
+ "model.layers.36.self_attn.k_proj.bias": "model-00020-of-00030.safetensors",
375
+ "model.layers.36.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
376
+ "model.layers.36.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
377
+ "model.layers.36.self_attn.q_proj.bias": "model-00020-of-00030.safetensors",
378
+ "model.layers.36.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
379
+ "model.layers.36.self_attn.v_proj.bias": "model-00020-of-00030.safetensors",
380
+ "model.layers.36.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
381
+ "model.layers.37.input_layernorm.weight": "model-00020-of-00030.safetensors",
382
+ "model.layers.37.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
383
+ "model.layers.37.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
384
+ "model.layers.37.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
385
+ "model.layers.37.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
386
+ "model.layers.37.self_attn.k_proj.bias": "model-00021-of-00030.safetensors",
387
+ "model.layers.37.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
388
+ "model.layers.37.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
389
+ "model.layers.37.self_attn.q_proj.bias": "model-00021-of-00030.safetensors",
390
+ "model.layers.37.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
391
+ "model.layers.37.self_attn.v_proj.bias": "model-00021-of-00030.safetensors",
392
+ "model.layers.37.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
393
+ "model.layers.38.input_layernorm.weight": "model-00021-of-00030.safetensors",
394
+ "model.layers.38.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
395
+ "model.layers.38.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
396
+ "model.layers.38.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
397
+ "model.layers.38.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
398
+ "model.layers.38.self_attn.k_proj.bias": "model-00021-of-00030.safetensors",
399
+ "model.layers.38.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
400
+ "model.layers.38.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
401
+ "model.layers.38.self_attn.q_proj.bias": "model-00021-of-00030.safetensors",
402
+ "model.layers.38.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
403
+ "model.layers.38.self_attn.v_proj.bias": "model-00021-of-00030.safetensors",
404
+ "model.layers.38.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
405
+ "model.layers.39.input_layernorm.weight": "model-00021-of-00030.safetensors",
406
+ "model.layers.39.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
407
+ "model.layers.39.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
408
+ "model.layers.39.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
409
+ "model.layers.39.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
410
+ "model.layers.39.self_attn.k_proj.bias": "model-00022-of-00030.safetensors",
411
+ "model.layers.39.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
412
+ "model.layers.39.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
413
+ "model.layers.39.self_attn.q_proj.bias": "model-00022-of-00030.safetensors",
414
+ "model.layers.39.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
415
+ "model.layers.39.self_attn.v_proj.bias": "model-00022-of-00030.safetensors",
416
+ "model.layers.39.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
417
+ "model.layers.4.input_layernorm.weight": "model-00022-of-00030.safetensors",
418
+ "model.layers.4.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
419
+ "model.layers.4.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
420
+ "model.layers.4.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
421
+ "model.layers.4.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
422
+ "model.layers.4.self_attn.k_proj.bias": "model-00022-of-00030.safetensors",
423
+ "model.layers.4.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
424
+ "model.layers.4.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
425
+ "model.layers.4.self_attn.q_proj.bias": "model-00022-of-00030.safetensors",
426
+ "model.layers.4.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
427
+ "model.layers.4.self_attn.v_proj.bias": "model-00022-of-00030.safetensors",
428
+ "model.layers.4.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
429
+ "model.layers.40.input_layernorm.weight": "model-00022-of-00030.safetensors",
430
+ "model.layers.40.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
431
+ "model.layers.40.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
432
+ "model.layers.40.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
433
+ "model.layers.40.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
434
+ "model.layers.40.self_attn.k_proj.bias": "model-00023-of-00030.safetensors",
435
+ "model.layers.40.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
436
+ "model.layers.40.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
437
+ "model.layers.40.self_attn.q_proj.bias": "model-00023-of-00030.safetensors",
438
+ "model.layers.40.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
439
+ "model.layers.40.self_attn.v_proj.bias": "model-00023-of-00030.safetensors",
440
+ "model.layers.40.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
441
+ "model.layers.41.input_layernorm.weight": "model-00023-of-00030.safetensors",
442
+ "model.layers.41.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
443
+ "model.layers.41.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
444
+ "model.layers.41.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
445
+ "model.layers.41.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
446
+ "model.layers.41.self_attn.k_proj.bias": "model-00023-of-00030.safetensors",
447
+ "model.layers.41.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
448
+ "model.layers.41.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
449
+ "model.layers.41.self_attn.q_proj.bias": "model-00024-of-00030.safetensors",
450
+ "model.layers.41.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
451
+ "model.layers.41.self_attn.v_proj.bias": "model-00024-of-00030.safetensors",
452
+ "model.layers.41.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
453
+ "model.layers.42.input_layernorm.weight": "model-00024-of-00030.safetensors",
454
+ "model.layers.42.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
455
+ "model.layers.42.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
456
+ "model.layers.42.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
457
+ "model.layers.42.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
458
+ "model.layers.42.self_attn.k_proj.bias": "model-00024-of-00030.safetensors",
459
+ "model.layers.42.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
460
+ "model.layers.42.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
461
+ "model.layers.42.self_attn.q_proj.bias": "model-00024-of-00030.safetensors",
462
+ "model.layers.42.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
463
+ "model.layers.42.self_attn.v_proj.bias": "model-00024-of-00030.safetensors",
464
+ "model.layers.42.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
465
+ "model.layers.43.input_layernorm.weight": "model-00024-of-00030.safetensors",
466
+ "model.layers.43.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
467
+ "model.layers.43.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
468
+ "model.layers.43.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
469
+ "model.layers.43.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
470
+ "model.layers.43.self_attn.k_proj.bias": "model-00025-of-00030.safetensors",
471
+ "model.layers.43.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
472
+ "model.layers.43.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
473
+ "model.layers.43.self_attn.q_proj.bias": "model-00025-of-00030.safetensors",
474
+ "model.layers.43.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
475
+ "model.layers.43.self_attn.v_proj.bias": "model-00025-of-00030.safetensors",
476
+ "model.layers.43.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
477
+ "model.layers.44.input_layernorm.weight": "model-00025-of-00030.safetensors",
478
+ "model.layers.44.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
479
+ "model.layers.44.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
480
+ "model.layers.44.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
481
+ "model.layers.44.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
482
+ "model.layers.44.self_attn.k_proj.bias": "model-00025-of-00030.safetensors",
483
+ "model.layers.44.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
484
+ "model.layers.44.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
485
+ "model.layers.44.self_attn.q_proj.bias": "model-00025-of-00030.safetensors",
486
+ "model.layers.44.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
487
+ "model.layers.44.self_attn.v_proj.bias": "model-00025-of-00030.safetensors",
488
+ "model.layers.44.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
489
+ "model.layers.45.input_layernorm.weight": "model-00025-of-00030.safetensors",
490
+ "model.layers.45.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
491
+ "model.layers.45.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
492
+ "model.layers.45.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
493
+ "model.layers.45.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
494
+ "model.layers.45.self_attn.k_proj.bias": "model-00026-of-00030.safetensors",
495
+ "model.layers.45.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
496
+ "model.layers.45.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
497
+ "model.layers.45.self_attn.q_proj.bias": "model-00026-of-00030.safetensors",
498
+ "model.layers.45.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
499
+ "model.layers.45.self_attn.v_proj.bias": "model-00026-of-00030.safetensors",
500
+ "model.layers.45.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
501
+ "model.layers.46.input_layernorm.weight": "model-00026-of-00030.safetensors",
502
+ "model.layers.46.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
503
+ "model.layers.46.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
504
+ "model.layers.46.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
505
+ "model.layers.46.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
506
+ "model.layers.46.self_attn.k_proj.bias": "model-00026-of-00030.safetensors",
507
+ "model.layers.46.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
508
+ "model.layers.46.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
509
+ "model.layers.46.self_attn.q_proj.bias": "model-00026-of-00030.safetensors",
510
+ "model.layers.46.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
511
+ "model.layers.46.self_attn.v_proj.bias": "model-00026-of-00030.safetensors",
512
+ "model.layers.46.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
513
+ "model.layers.47.input_layernorm.weight": "model-00026-of-00030.safetensors",
514
+ "model.layers.47.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
515
+ "model.layers.47.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
516
+ "model.layers.47.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
517
+ "model.layers.47.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
518
+ "model.layers.47.self_attn.k_proj.bias": "model-00027-of-00030.safetensors",
519
+ "model.layers.47.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
520
+ "model.layers.47.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
521
+ "model.layers.47.self_attn.q_proj.bias": "model-00027-of-00030.safetensors",
522
+ "model.layers.47.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
523
+ "model.layers.47.self_attn.v_proj.bias": "model-00027-of-00030.safetensors",
524
+ "model.layers.47.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
525
+ "model.layers.5.input_layernorm.weight": "model-00027-of-00030.safetensors",
526
+ "model.layers.5.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
527
+ "model.layers.5.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
528
+ "model.layers.5.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
529
+ "model.layers.5.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
530
+ "model.layers.5.self_attn.k_proj.bias": "model-00027-of-00030.safetensors",
531
+ "model.layers.5.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
532
+ "model.layers.5.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
533
+ "model.layers.5.self_attn.q_proj.bias": "model-00028-of-00030.safetensors",
534
+ "model.layers.5.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
535
+ "model.layers.5.self_attn.v_proj.bias": "model-00028-of-00030.safetensors",
536
+ "model.layers.5.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
537
+ "model.layers.6.input_layernorm.weight": "model-00028-of-00030.safetensors",
538
+ "model.layers.6.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
539
+ "model.layers.6.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
540
+ "model.layers.6.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
541
+ "model.layers.6.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
542
+ "model.layers.6.self_attn.k_proj.bias": "model-00028-of-00030.safetensors",
543
+ "model.layers.6.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
544
+ "model.layers.6.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
545
+ "model.layers.6.self_attn.q_proj.bias": "model-00028-of-00030.safetensors",
546
+ "model.layers.6.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
547
+ "model.layers.6.self_attn.v_proj.bias": "model-00028-of-00030.safetensors",
548
+ "model.layers.6.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
549
+ "model.layers.7.input_layernorm.weight": "model-00028-of-00030.safetensors",
550
+ "model.layers.7.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
551
+ "model.layers.7.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
552
+ "model.layers.7.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
553
+ "model.layers.7.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
554
+ "model.layers.7.self_attn.k_proj.bias": "model-00029-of-00030.safetensors",
555
+ "model.layers.7.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
556
+ "model.layers.7.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
557
+ "model.layers.7.self_attn.q_proj.bias": "model-00029-of-00030.safetensors",
558
+ "model.layers.7.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
559
+ "model.layers.7.self_attn.v_proj.bias": "model-00029-of-00030.safetensors",
560
+ "model.layers.7.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
561
+ "model.layers.8.input_layernorm.weight": "model-00029-of-00030.safetensors",
562
+ "model.layers.8.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
563
+ "model.layers.8.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
564
+ "model.layers.8.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
565
+ "model.layers.8.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
566
+ "model.layers.8.self_attn.k_proj.bias": "model-00029-of-00030.safetensors",
567
+ "model.layers.8.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
568
+ "model.layers.8.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
569
+ "model.layers.8.self_attn.q_proj.bias": "model-00029-of-00030.safetensors",
570
+ "model.layers.8.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
571
+ "model.layers.8.self_attn.v_proj.bias": "model-00029-of-00030.safetensors",
572
+ "model.layers.8.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
573
+ "model.layers.9.input_layernorm.weight": "model-00029-of-00030.safetensors",
574
+ "model.layers.9.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
575
+ "model.layers.9.mlp.gate_proj.weight": "model-00030-of-00030.safetensors",
576
+ "model.layers.9.mlp.up_proj.weight": "model-00030-of-00030.safetensors",
577
+ "model.layers.9.post_attention_layernorm.weight": "model-00030-of-00030.safetensors",
578
+ "model.layers.9.self_attn.k_proj.bias": "model-00030-of-00030.safetensors",
579
+ "model.layers.9.self_attn.k_proj.weight": "model-00030-of-00030.safetensors",
580
+ "model.layers.9.self_attn.o_proj.weight": "model-00030-of-00030.safetensors",
581
+ "model.layers.9.self_attn.q_proj.bias": "model-00030-of-00030.safetensors",
582
+ "model.layers.9.self_attn.q_proj.weight": "model-00030-of-00030.safetensors",
583
+ "model.layers.9.self_attn.v_proj.bias": "model-00030-of-00030.safetensors",
584
+ "model.layers.9.self_attn.v_proj.weight": "model-00030-of-00030.safetensors",
585
+ "model.norm.weight": "model-00030-of-00030.safetensors"
586
+ }
587
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ }
181
+ },
182
+ "additional_special_tokens": [
183
+ "<|im_start|>",
184
+ "<|im_end|>",
185
+ "<|object_ref_start|>",
186
+ "<|object_ref_end|>",
187
+ "<|box_start|>",
188
+ "<|box_end|>",
189
+ "<|quad_start|>",
190
+ "<|quad_end|>",
191
+ "<|vision_start|>",
192
+ "<|vision_end|>",
193
+ "<|vision_pad|>",
194
+ "<|image_pad|>",
195
+ "<|video_pad|>"
196
+ ],
197
+ "bos_token": null,
198
+ "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "model_max_length": 131072,
203
+ "pad_token": "<|endoftext|>",
204
+ "split_special_tokens": false,
205
+ "tokenizer_class": "Qwen2Tokenizer",
206
+ "unk_token": null
207
+ }