Hugging Face's logo

Jessylg27
/
specialized-coding-logic-llm

PEFT
Safetensors
English
French
qwen2
code
logic
reasoning
qwen2.5
unsloth
sft
trl
Model card Files
xet
Community
Jessylg27 commited on
Commit
ea27c7f
·
verified ·
1 Parent(s): d59f4a5

Upload folder using huggingface_hub

Browse files
Files changed (25) hide show
  1. README.md +5 -5
  2. adapter_config.json +7 -7
  3. adapter_model.safetensors +2 -2
  4. added_tokens.json +25 -0
  5. config.json +83 -25
  6. merges.txt +0 -0
  7. model-00001-of-00014.safetensors +3 -0
  8. model-00002-of-00014.safetensors +3 -0
  9. model-00003-of-00014.safetensors +3 -0
  10. model-00004-of-00014.safetensors +3 -0
  11. model-00005-of-00014.safetensors +3 -0
  12. model-00006-of-00014.safetensors +3 -0
  13. model-00007-of-00014.safetensors +3 -0
  14. model-00008-of-00014.safetensors +3 -0
  15. model-00009-of-00014.safetensors +3 -0
  16. model-00010-of-00014.safetensors +3 -0
  17. model-00011-of-00014.safetensors +3 -0
  18. model-00012-of-00014.safetensors +3 -0
  19. model-00013-of-00014.safetensors +3 -0
  20. model-00014-of-00014.safetensors +3 -0
  21. model.safetensors.index.json +772 -255
  22. special_tokens_map.json +17 -9
  23. tokenizer.json +2 -2
  24. tokenizer_config.json +79 -1929
  25. vocab.json +0 -0
README.md CHANGED
@@ -1,9 +1,9 @@
1
  ---
2
- base_model: unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
3
  library_name: peft
4
- model_name: Mon_Modele_Llama
5
  tags:
6
- - base_model:adapter:unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit
7
  - lora
8
  - sft
9
  - transformers
@@ -13,9 +13,9 @@ licence: license
13
  pipeline_tag: text-generation
14
  ---
15
 
16
- # Model Card for Mon_Modele_Llama
17
 
18
- This model is a fine-tuned version of [unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit](https://huggingface.co/unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit).
19
  It has been trained using [TRL](https://github.com/huggingface/trl).
20
 
21
  ## Quick start
 
1
  ---
2
+ base_model: unsloth/qwen2.5-coder-32b-instruct-bnb-4bit
3
  library_name: peft
4
+ model_name: model
5
  tags:
6
+ - base_model:adapter:unsloth/qwen2.5-coder-32b-instruct-bnb-4bit
7
  - lora
8
  - sft
9
  - transformers
 
13
  pipeline_tag: text-generation
14
  ---
15
 
16
+ # Model Card for model
17
 
18
+ This model is a fine-tuned version of [unsloth/qwen2.5-coder-32b-instruct-bnb-4bit](https://huggingface.co/unsloth/qwen2.5-coder-32b-instruct-bnb-4bit).
19
  It has been trained using [TRL](https://github.com/huggingface/trl).
20
 
21
  ## Quick start
adapter_config.json CHANGED
@@ -3,11 +3,11 @@
3
  "alpha_pattern": {},
4
  "arrow_config": null,
5
  "auto_mapping": {
6
- "base_model_class": "LlamaForCausalLM",
7
- "parent_library": "transformers.models.llama.modeling_llama",
8
  "unsloth_fixed": true
9
  },
10
- "base_model_name_or_path": "unsloth/llama-3.2-3b-instruct-unsloth-bnb-4bit",
11
  "bias": "none",
12
  "corda_config": null,
13
  "ensure_weight_tying": false,
@@ -33,13 +33,13 @@
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
 
 
36
  "gate_proj",
37
  "down_proj",
38
- "up_proj",
39
- "o_proj",
40
- "v_proj",
41
  "k_proj",
42
- "q_proj"
 
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
 
3
  "alpha_pattern": {},
4
  "arrow_config": null,
5
  "auto_mapping": {
6
+ "base_model_class": "Qwen2ForCausalLM",
7
+ "parent_library": "transformers.models.qwen2.modeling_qwen2",
8
  "unsloth_fixed": true
9
  },
10
+ "base_model_name_or_path": "unsloth/qwen2.5-coder-32b-instruct-bnb-4bit",
11
  "bias": "none",
12
  "corda_config": null,
13
  "ensure_weight_tying": false,
 
33
  "rank_pattern": {},
34
  "revision": null,
35
  "target_modules": [
36
+ "q_proj",
37
+ "o_proj",
38
  "gate_proj",
39
  "down_proj",
 
 
 
40
  "k_proj",
41
+ "v_proj",
42
+ "up_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c5e80f16177da61b4b881c2bc2e89154ac272276e4523924410d6984981b2c9
3
- size 97307544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d78ad7a4ff610ee2a0bc0d954309434916fb2a93651554cb9444e98d056e64d3
3
+ size 536991984
added_tokens.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|PAD_TOKEN|>": 151665,
5
+ "<|box_end|>": 151649,
6
+ "<|box_start|>": 151648,
7
+ "<|endoftext|>": 151643,
8
+ "<|file_sep|>": 151664,
9
+ "<|fim_middle|>": 151660,
10
+ "<|fim_pad|>": 151662,
11
+ "<|fim_prefix|>": 151659,
12
+ "<|fim_suffix|>": 151661,
13
+ "<|im_end|>": 151645,
14
+ "<|im_start|>": 151644,
15
+ "<|image_pad|>": 151655,
16
+ "<|object_ref_end|>": 151647,
17
+ "<|object_ref_start|>": 151646,
18
+ "<|quad_end|>": 151651,
19
+ "<|quad_start|>": 151650,
20
+ "<|repo_name|>": 151663,
21
+ "<|video_pad|>": 151656,
22
+ "<|vision_end|>": 151653,
23
+ "<|vision_pad|>": 151654,
24
+ "<|vision_start|>": 151652
25
+ }
config.json CHANGED
@@ -1,38 +1,96 @@
1
  {
2
  "architectures": [
3
- "LlamaForCausalLM"
4
  ],
5
- "attention_bias": false,
6
  "attention_dropout": 0.0,
7
- "bos_token_id": 128000,
8
  "torch_dtype": "bfloat16",
9
- "eos_token_id": 128009,
10
- "head_dim": 128,
11
  "hidden_act": "silu",
12
- "hidden_size": 3072,
13
  "initializer_range": 0.02,
14
- "intermediate_size": 8192,
15
- "max_position_embeddings": 131072,
16
- "mlp_bias": false,
17
- "model_type": "llama",
18
- "num_attention_heads": 24,
19
- "num_hidden_layers": 28,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20
  "num_key_value_heads": 8,
21
- "pad_token_id": 128004,
22
- "pretraining_tp": 1,
23
- "rms_norm_eps": 1e-05,
24
- "rope_scaling": {
25
- "factor": 32.0,
26
- "high_freq_factor": 4.0,
27
- "low_freq_factor": 1.0,
28
- "original_max_position_embeddings": 8192,
29
- "rope_type": "llama3"
30
- },
31
- "rope_theta": 500000.0,
32
- "tie_word_embeddings": true,
33
  "transformers_version": "4.57.3",
34
  "unsloth_fixed": true,
35
  "unsloth_version": "2026.1.3",
36
  "use_cache": true,
37
- "vocab_size": 128256
 
38
  }
 
1
  {
2
  "architectures": [
3
+ "Qwen2ForCausalLM"
4
  ],
 
5
  "attention_dropout": 0.0,
 
6
  "torch_dtype": "bfloat16",
7
+ "eos_token_id": 151645,
 
8
  "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
  "initializer_range": 0.02,
11
+ "intermediate_size": 27648,
12
+ "layer_types": [
13
+ "full_attention",
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
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention"
77
+ ],
78
+ "max_position_embeddings": 32768,
79
+ "max_window_layers": 70,
80
+ "model_type": "qwen2",
81
+ "num_attention_heads": 40,
82
+ "num_hidden_layers": 64,
83
  "num_key_value_heads": 8,
84
+ "pad_token_id": 151665,
85
+ "rms_norm_eps": 1e-06,
86
+ "rope_scaling": null,
87
+ "rope_theta": 1000000.0,
88
+ "sliding_window": null,
89
+ "tie_word_embeddings": false,
 
 
 
 
 
 
90
  "transformers_version": "4.57.3",
91
  "unsloth_fixed": true,
92
  "unsloth_version": "2026.1.3",
93
  "use_cache": true,
94
+ "use_sliding_window": false,
95
+ "vocab_size": 152064
96
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adb7961d556f392969c770d63c425062503f3448f2a5b800ae577cbe3907ea7b
3
+ size 4891730992
model-00002-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:304876107b828a36354a318b6660e401e0b60c5e3c0959b558157628a9cab7e9
3
+ size 4876059352
model-00003-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:141fabd77155b9747fb5961ecfc93e0ec14591b41703a2ea69060f26c01fa8ac
3
+ size 4876059384
model-00004-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3745a64bbbeb5011823a768a2ea3ba0feecfb2f21c0a48866978ad515020a34f
3
+ size 4876059416
model-00005-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:add239dcff71f899fbc5f0a22aa1745d5954044385ce46cf0ef0bcbf178e68e7
3
+ size 4876059416
model-00006-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92e4c77b2746805647307b26e266a8dfaa4669c486daef5a967ee9a288c26a5b
3
+ size 4876059416
model-00007-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:042d6d35c86794a50be5506fe86ee54a67899f57465fc4a08341cd960420840a
3
+ size 4876059416
model-00008-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e28a49305cb327dc8bd53fe5678b26b07d3b824343dcfea119562b20b32d55ff
3
+ size 4876059416
model-00009-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59875cba39959c38385d0018d4e0e093da20783d6ab1e72fffdb439d307e093c
3
+ size 4876059416
model-00010-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f717edeafc543332c8df42b4ecbe6b15ffc6451a52c4ac7eeda6f8f3d023eb4f
3
+ size 4876059416
model-00011-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:190a001b299c0351895cb3892aca196d2fbf06541e1f7cce71fedeb5e403919d
3
+ size 4876059416
model-00012-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f019e7ac5e81583113fbff3e77223be0e3dd450e369ad207b7c478ed93eccb6
3
+ size 4876059416
model-00013-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1957acb85db5457fcd18c0b5d90605d04e68e2704980884fbcfa2d5ff8f64ee
3
+ size 4876059416
model-00014-of-00014.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e01df2a39c9516306b352b7ad68b5a9dd1eed1a5bec5db67fa3a2981d1e630df
3
+ size 2123397800
model.safetensors.index.json CHANGED
@@ -1,261 +1,778 @@
1
  {
2
  "metadata": {
3
- "total_size": 6425499648
4
  },
5
  "weight_map": {
6
- "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
7
- "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
8
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
9
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
10
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
11
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
12
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
13
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
14
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
15
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
16
- "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
17
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
18
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
19
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
20
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
21
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
22
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
23
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
24
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
25
- "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
26
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
28
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
29
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
30
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
31
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
32
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
33
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
34
- "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
35
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
36
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
37
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
38
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
39
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
40
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
41
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
42
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
43
- "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
44
- "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
45
- "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
46
- "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
49
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
50
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
- "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
- "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
- "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
58
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
59
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
60
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
61
- "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
62
- "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
63
- "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
64
- "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
65
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
66
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
67
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
68
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
69
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
70
- "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
71
- "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
72
- "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
73
- "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
74
- "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
75
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
76
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
77
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
78
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
79
- "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
80
- "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
81
- "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
82
- "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
83
- "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
84
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
85
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
86
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
87
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
88
- "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
89
- "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
90
- "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
91
- "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
92
- "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
93
- "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
94
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
95
- "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
96
- "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
97
- "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
98
- "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
99
- "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
100
- "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
101
- "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
102
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
105
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
106
- "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
107
- "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
108
- "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
109
- "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
110
- "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
111
- "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
112
- "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
113
- "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
114
- "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
115
- "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
116
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
117
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
118
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
119
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
120
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
121
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
122
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
123
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
124
- "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
125
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
126
- "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
127
- "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
128
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
129
- "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
130
- "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
131
- "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
132
- "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
133
- "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
134
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
135
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
136
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
137
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
138
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
139
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
140
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
141
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
142
- "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
143
- "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
144
- "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
145
- "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
146
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
147
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
148
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
149
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
150
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
151
- "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
- "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
- "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
154
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
155
- "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
157
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
158
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
159
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
160
- "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
161
- "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
162
- "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
163
- "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
164
- "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
165
- "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
166
- "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
167
- "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
168
- "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
169
- "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
170
- "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
171
- "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
172
- "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
173
- "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
174
- "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
175
- "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
176
- "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
177
- "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
178
- "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
179
- "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
180
- "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
181
- "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
182
- "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
183
- "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
184
- "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
185
- "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
186
- "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
187
- "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
188
- "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
189
- "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
190
- "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
191
- "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
192
- "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
193
- "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
194
- "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
195
- "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
196
- "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
197
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
198
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
199
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
200
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
201
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
202
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
203
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
204
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
205
- "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
206
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
207
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
208
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
209
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
210
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
211
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
212
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
213
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
214
- "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
215
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
216
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
217
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
218
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
219
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
220
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
221
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
222
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
223
- "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
224
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
225
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
226
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
227
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
228
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
229
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
230
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
231
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
232
- "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
233
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
234
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
235
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
236
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
237
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
238
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
239
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
240
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
241
- "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
242
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
243
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
244
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
245
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
246
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
247
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
248
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
249
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
250
- "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
251
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
252
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
253
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
254
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
255
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
256
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
257
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
258
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
259
- "model.norm.weight": "model-00002-of-00002.safetensors"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
260
  }
261
  }
 
1
  {
2
  "metadata": {
3
+ "total_size": 65527752704
4
  },
5
  "weight_map": {
6
+ "lm_head.weight": "model-00014-of-00014.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
13
+ "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
14
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
15
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
16
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
17
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
18
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
19
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
20
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
21
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
22
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
23
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
24
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
25
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
26
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
27
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
28
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
29
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
30
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
31
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
32
+ "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors",
33
+ "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
34
+ "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
35
+ "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
36
+ "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
37
+ "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
38
+ "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
39
+ "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
40
+ "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
41
+ "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
42
+ "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
43
+ "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
44
+ "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors",
45
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
46
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
47
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
48
+ "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
49
+ "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
50
+ "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
51
+ "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
52
+ "model.layers.11.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
53
+ "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
54
+ "model.layers.11.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
55
+ "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
56
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors",
57
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
58
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
59
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
60
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
61
+ "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
62
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
63
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
64
+ "model.layers.12.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
65
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
66
+ "model.layers.12.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
67
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
68
+ "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors",
69
+ "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
70
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
71
+ "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
72
+ "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
73
+ "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
74
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
75
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
76
+ "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
77
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
78
+ "model.layers.13.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
79
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
80
+ "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors",
81
+ "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
82
+ "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
83
+ "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
84
+ "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
85
+ "model.layers.14.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
86
+ "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
87
+ "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
88
+ "model.layers.14.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
89
+ "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
90
+ "model.layers.14.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
91
+ "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
92
+ "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors",
93
+ "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
94
+ "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
95
+ "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
96
+ "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
97
+ "model.layers.15.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
98
+ "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
99
+ "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
100
+ "model.layers.15.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
101
+ "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
102
+ "model.layers.15.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
103
+ "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
104
+ "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors",
105
+ "model.layers.16.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
106
+ "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
107
+ "model.layers.16.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
108
+ "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
109
+ "model.layers.16.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
110
+ "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
111
+ "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
112
+ "model.layers.16.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
113
+ "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
114
+ "model.layers.16.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
115
+ "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
116
+ "model.layers.17.input_layernorm.weight": "model-00004-of-00014.safetensors",
117
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
118
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
119
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
120
+ "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
121
+ "model.layers.17.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
122
+ "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
123
+ "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
124
+ "model.layers.17.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
125
+ "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
126
+ "model.layers.17.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
127
+ "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
128
+ "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors",
129
+ "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
130
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
131
+ "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
132
+ "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
133
+ "model.layers.18.self_attn.k_proj.bias": "model-00004-of-00014.safetensors",
134
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
135
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
136
+ "model.layers.18.self_attn.q_proj.bias": "model-00004-of-00014.safetensors",
137
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
138
+ "model.layers.18.self_attn.v_proj.bias": "model-00004-of-00014.safetensors",
139
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
140
+ "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors",
141
+ "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
142
+ "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
143
+ "model.layers.19.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
144
+ "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
145
+ "model.layers.19.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
146
+ "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
147
+ "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
148
+ "model.layers.19.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
149
+ "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
150
+ "model.layers.19.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
151
+ "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
152
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00014.safetensors",
153
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
154
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
155
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
156
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
157
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
158
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
159
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
160
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
161
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
162
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
163
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
164
+ "model.layers.20.input_layernorm.weight": "model-00005-of-00014.safetensors",
165
+ "model.layers.20.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
166
+ "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
167
+ "model.layers.20.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
168
+ "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
169
+ "model.layers.20.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
170
+ "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
171
+ "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
172
+ "model.layers.20.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
173
+ "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
174
+ "model.layers.20.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
175
+ "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
176
+ "model.layers.21.input_layernorm.weight": "model-00005-of-00014.safetensors",
177
+ "model.layers.21.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
178
+ "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
179
+ "model.layers.21.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
180
+ "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
181
+ "model.layers.21.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
182
+ "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
183
+ "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
184
+ "model.layers.21.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
185
+ "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
186
+ "model.layers.21.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
187
+ "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
188
+ "model.layers.22.input_layernorm.weight": "model-00005-of-00014.safetensors",
189
+ "model.layers.22.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
190
+ "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
191
+ "model.layers.22.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
192
+ "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
193
+ "model.layers.22.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
194
+ "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
195
+ "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
196
+ "model.layers.22.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
197
+ "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
198
+ "model.layers.22.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
199
+ "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
200
+ "model.layers.23.input_layernorm.weight": "model-00006-of-00014.safetensors",
201
+ "model.layers.23.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
202
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
203
+ "model.layers.23.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
204
+ "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
205
+ "model.layers.23.self_attn.k_proj.bias": "model-00005-of-00014.safetensors",
206
+ "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
207
+ "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
208
+ "model.layers.23.self_attn.q_proj.bias": "model-00005-of-00014.safetensors",
209
+ "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
210
+ "model.layers.23.self_attn.v_proj.bias": "model-00005-of-00014.safetensors",
211
+ "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
212
+ "model.layers.24.input_layernorm.weight": "model-00006-of-00014.safetensors",
213
+ "model.layers.24.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
214
+ "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
215
+ "model.layers.24.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
216
+ "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
217
+ "model.layers.24.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
218
+ "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
219
+ "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
220
+ "model.layers.24.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
221
+ "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
222
+ "model.layers.24.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
223
+ "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
224
+ "model.layers.25.input_layernorm.weight": "model-00006-of-00014.safetensors",
225
+ "model.layers.25.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
226
+ "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
227
+ "model.layers.25.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
228
+ "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
229
+ "model.layers.25.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
230
+ "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
231
+ "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
232
+ "model.layers.25.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
233
+ "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
234
+ "model.layers.25.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
235
+ "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
236
+ "model.layers.26.input_layernorm.weight": "model-00006-of-00014.safetensors",
237
+ "model.layers.26.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
238
+ "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
239
+ "model.layers.26.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
240
+ "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
241
+ "model.layers.26.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
242
+ "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
243
+ "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
244
+ "model.layers.26.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
245
+ "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
246
+ "model.layers.26.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
247
+ "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
248
+ "model.layers.27.input_layernorm.weight": "model-00006-of-00014.safetensors",
249
+ "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
250
+ "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
251
+ "model.layers.27.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
252
+ "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
253
+ "model.layers.27.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
254
+ "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
255
+ "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
256
+ "model.layers.27.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
257
+ "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
258
+ "model.layers.27.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
259
+ "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
260
+ "model.layers.28.input_layernorm.weight": "model-00007-of-00014.safetensors",
261
+ "model.layers.28.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
262
+ "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
263
+ "model.layers.28.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
264
+ "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
265
+ "model.layers.28.self_attn.k_proj.bias": "model-00006-of-00014.safetensors",
266
+ "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
267
+ "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
268
+ "model.layers.28.self_attn.q_proj.bias": "model-00006-of-00014.safetensors",
269
+ "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
270
+ "model.layers.28.self_attn.v_proj.bias": "model-00006-of-00014.safetensors",
271
+ "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
272
+ "model.layers.29.input_layernorm.weight": "model-00007-of-00014.safetensors",
273
+ "model.layers.29.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
274
+ "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
275
+ "model.layers.29.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
276
+ "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
277
+ "model.layers.29.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
278
+ "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
279
+ "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
280
+ "model.layers.29.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
281
+ "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
282
+ "model.layers.29.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
283
+ "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
284
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
285
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
286
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
287
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
288
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
289
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00014.safetensors",
290
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
291
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
292
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00014.safetensors",
293
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
294
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00014.safetensors",
295
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
296
+ "model.layers.30.input_layernorm.weight": "model-00007-of-00014.safetensors",
297
+ "model.layers.30.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
298
+ "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
299
+ "model.layers.30.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
300
+ "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
301
+ "model.layers.30.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
302
+ "model.layers.30.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
303
+ "model.layers.30.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
304
+ "model.layers.30.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
305
+ "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
306
+ "model.layers.30.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
307
+ "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
308
+ "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors",
309
+ "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
310
+ "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
311
+ "model.layers.31.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
312
+ "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
313
+ "model.layers.31.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
314
+ "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
315
+ "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
316
+ "model.layers.31.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
318
+ "model.layers.31.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
320
+ "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors",
321
+ "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
322
+ "model.layers.32.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
323
+ "model.layers.32.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
324
+ "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
325
+ "model.layers.32.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
326
+ "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
327
+ "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
328
+ "model.layers.32.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
329
+ "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
330
+ "model.layers.32.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
331
+ "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
332
+ "model.layers.33.input_layernorm.weight": "model-00008-of-00014.safetensors",
333
+ "model.layers.33.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
334
+ "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
335
+ "model.layers.33.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
336
+ "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
337
+ "model.layers.33.self_attn.k_proj.bias": "model-00007-of-00014.safetensors",
338
+ "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
339
+ "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
340
+ "model.layers.33.self_attn.q_proj.bias": "model-00007-of-00014.safetensors",
341
+ "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
342
+ "model.layers.33.self_attn.v_proj.bias": "model-00007-of-00014.safetensors",
343
+ "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
344
+ "model.layers.34.input_layernorm.weight": "model-00008-of-00014.safetensors",
345
+ "model.layers.34.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
346
+ "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
347
+ "model.layers.34.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
348
+ "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
349
+ "model.layers.34.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
350
+ "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
351
+ "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
352
+ "model.layers.34.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
353
+ "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
354
+ "model.layers.34.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
355
+ "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
356
+ "model.layers.35.input_layernorm.weight": "model-00008-of-00014.safetensors",
357
+ "model.layers.35.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
358
+ "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
359
+ "model.layers.35.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
360
+ "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
361
+ "model.layers.35.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
362
+ "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
363
+ "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
364
+ "model.layers.35.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
365
+ "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
366
+ "model.layers.35.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
367
+ "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
368
+ "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors",
369
+ "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
370
+ "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
371
+ "model.layers.36.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
372
+ "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
373
+ "model.layers.36.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
374
+ "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
375
+ "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
376
+ "model.layers.36.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
377
+ "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
378
+ "model.layers.36.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
379
+ "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
380
+ "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors",
381
+ "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
382
+ "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
383
+ "model.layers.37.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
384
+ "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
385
+ "model.layers.37.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
386
+ "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
387
+ "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
388
+ "model.layers.37.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
389
+ "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
390
+ "model.layers.37.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
391
+ "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
392
+ "model.layers.38.input_layernorm.weight": "model-00009-of-00014.safetensors",
393
+ "model.layers.38.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
394
+ "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
395
+ "model.layers.38.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
396
+ "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
397
+ "model.layers.38.self_attn.k_proj.bias": "model-00008-of-00014.safetensors",
398
+ "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
399
+ "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
400
+ "model.layers.38.self_attn.q_proj.bias": "model-00008-of-00014.safetensors",
401
+ "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
402
+ "model.layers.38.self_attn.v_proj.bias": "model-00008-of-00014.safetensors",
403
+ "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
404
+ "model.layers.39.input_layernorm.weight": "model-00009-of-00014.safetensors",
405
+ "model.layers.39.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
406
+ "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
407
+ "model.layers.39.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
408
+ "model.layers.39.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
409
+ "model.layers.39.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
410
+ "model.layers.39.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
411
+ "model.layers.39.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
412
+ "model.layers.39.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
413
+ "model.layers.39.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
414
+ "model.layers.39.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
415
+ "model.layers.39.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
416
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
417
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
418
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
419
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
420
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
421
+ "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
422
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
423
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
424
+ "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
425
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
426
+ "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
427
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
428
+ "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors",
429
+ "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
430
+ "model.layers.40.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
431
+ "model.layers.40.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
432
+ "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
433
+ "model.layers.40.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
434
+ "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
435
+ "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
436
+ "model.layers.40.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
437
+ "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
438
+ "model.layers.40.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
439
+ "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
440
+ "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors",
441
+ "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
442
+ "model.layers.41.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
443
+ "model.layers.41.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
444
+ "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
445
+ "model.layers.41.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
446
+ "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
447
+ "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
448
+ "model.layers.41.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
449
+ "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
450
+ "model.layers.41.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
451
+ "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
452
+ "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors",
453
+ "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
454
+ "model.layers.42.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
455
+ "model.layers.42.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
456
+ "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
457
+ "model.layers.42.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
458
+ "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
459
+ "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
460
+ "model.layers.42.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
461
+ "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
462
+ "model.layers.42.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
463
+ "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
464
+ "model.layers.43.input_layernorm.weight": "model-00010-of-00014.safetensors",
465
+ "model.layers.43.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
466
+ "model.layers.43.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
467
+ "model.layers.43.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
468
+ "model.layers.43.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
469
+ "model.layers.43.self_attn.k_proj.bias": "model-00009-of-00014.safetensors",
470
+ "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
471
+ "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
472
+ "model.layers.43.self_attn.q_proj.bias": "model-00009-of-00014.safetensors",
473
+ "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
474
+ "model.layers.43.self_attn.v_proj.bias": "model-00009-of-00014.safetensors",
475
+ "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
476
+ "model.layers.44.input_layernorm.weight": "model-00010-of-00014.safetensors",
477
+ "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
478
+ "model.layers.44.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
479
+ "model.layers.44.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
480
+ "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
481
+ "model.layers.44.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
482
+ "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
483
+ "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
484
+ "model.layers.44.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
485
+ "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
486
+ "model.layers.44.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
487
+ "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
488
+ "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors",
489
+ "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
490
+ "model.layers.45.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
491
+ "model.layers.45.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
492
+ "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
493
+ "model.layers.45.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
494
+ "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
495
+ "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
496
+ "model.layers.45.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
497
+ "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
498
+ "model.layers.45.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
499
+ "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
500
+ "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors",
501
+ "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
502
+ "model.layers.46.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
503
+ "model.layers.46.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
504
+ "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
505
+ "model.layers.46.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
506
+ "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
507
+ "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
508
+ "model.layers.46.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
509
+ "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
510
+ "model.layers.46.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
511
+ "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
512
+ "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors",
513
+ "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
514
+ "model.layers.47.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
515
+ "model.layers.47.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
516
+ "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
517
+ "model.layers.47.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
518
+ "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
519
+ "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
520
+ "model.layers.47.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
521
+ "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
522
+ "model.layers.47.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
523
+ "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
524
+ "model.layers.48.input_layernorm.weight": "model-00011-of-00014.safetensors",
525
+ "model.layers.48.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
526
+ "model.layers.48.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
527
+ "model.layers.48.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
528
+ "model.layers.48.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
529
+ "model.layers.48.self_attn.k_proj.bias": "model-00010-of-00014.safetensors",
530
+ "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
531
+ "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
532
+ "model.layers.48.self_attn.q_proj.bias": "model-00010-of-00014.safetensors",
533
+ "model.layers.48.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
534
+ "model.layers.48.self_attn.v_proj.bias": "model-00010-of-00014.safetensors",
535
+ "model.layers.48.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
536
+ "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors",
537
+ "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
538
+ "model.layers.49.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
539
+ "model.layers.49.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
540
+ "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
541
+ "model.layers.49.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
542
+ "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
543
+ "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
544
+ "model.layers.49.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
545
+ "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
546
+ "model.layers.49.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
547
+ "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
548
+ "model.layers.5.input_layernorm.weight": "model-00002-of-00014.safetensors",
549
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
550
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
551
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
552
+ "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
553
+ "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
554
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
555
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
556
+ "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
557
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
558
+ "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
559
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
560
+ "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors",
561
+ "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
562
+ "model.layers.50.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
563
+ "model.layers.50.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
564
+ "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
565
+ "model.layers.50.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
566
+ "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
567
+ "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
568
+ "model.layers.50.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
569
+ "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
570
+ "model.layers.50.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
571
+ "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
572
+ "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors",
573
+ "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
574
+ "model.layers.51.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
575
+ "model.layers.51.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
576
+ "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
577
+ "model.layers.51.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
578
+ "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
579
+ "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
580
+ "model.layers.51.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
581
+ "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
582
+ "model.layers.51.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
583
+ "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
584
+ "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors",
585
+ "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
586
+ "model.layers.52.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
587
+ "model.layers.52.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
588
+ "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
589
+ "model.layers.52.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
590
+ "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
591
+ "model.layers.52.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
592
+ "model.layers.52.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
593
+ "model.layers.52.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
594
+ "model.layers.52.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
595
+ "model.layers.52.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
596
+ "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors",
597
+ "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
598
+ "model.layers.53.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
599
+ "model.layers.53.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
600
+ "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
601
+ "model.layers.53.self_attn.k_proj.bias": "model-00011-of-00014.safetensors",
602
+ "model.layers.53.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
603
+ "model.layers.53.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
604
+ "model.layers.53.self_attn.q_proj.bias": "model-00011-of-00014.safetensors",
605
+ "model.layers.53.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
606
+ "model.layers.53.self_attn.v_proj.bias": "model-00011-of-00014.safetensors",
607
+ "model.layers.53.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
608
+ "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors",
609
+ "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
610
+ "model.layers.54.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
611
+ "model.layers.54.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
612
+ "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
613
+ "model.layers.54.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
614
+ "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
615
+ "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
616
+ "model.layers.54.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
617
+ "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
618
+ "model.layers.54.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
619
+ "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
620
+ "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors",
621
+ "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
622
+ "model.layers.55.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
623
+ "model.layers.55.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
624
+ "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
625
+ "model.layers.55.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
626
+ "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
627
+ "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
628
+ "model.layers.55.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
629
+ "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
630
+ "model.layers.55.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
631
+ "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
632
+ "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors",
633
+ "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
634
+ "model.layers.56.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
635
+ "model.layers.56.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
636
+ "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
637
+ "model.layers.56.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
638
+ "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
639
+ "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
640
+ "model.layers.56.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
641
+ "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
642
+ "model.layers.56.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
643
+ "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
644
+ "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors",
645
+ "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
646
+ "model.layers.57.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
647
+ "model.layers.57.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
648
+ "model.layers.57.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
649
+ "model.layers.57.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
650
+ "model.layers.57.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
651
+ "model.layers.57.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
652
+ "model.layers.57.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
653
+ "model.layers.57.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
654
+ "model.layers.57.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
655
+ "model.layers.57.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
656
+ "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors",
657
+ "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
658
+ "model.layers.58.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
659
+ "model.layers.58.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
660
+ "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
661
+ "model.layers.58.self_attn.k_proj.bias": "model-00012-of-00014.safetensors",
662
+ "model.layers.58.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
663
+ "model.layers.58.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
664
+ "model.layers.58.self_attn.q_proj.bias": "model-00012-of-00014.safetensors",
665
+ "model.layers.58.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
666
+ "model.layers.58.self_attn.v_proj.bias": "model-00012-of-00014.safetensors",
667
+ "model.layers.58.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
668
+ "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors",
669
+ "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
670
+ "model.layers.59.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
671
+ "model.layers.59.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
672
+ "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
673
+ "model.layers.59.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
674
+ "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
675
+ "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
676
+ "model.layers.59.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
677
+ "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
678
+ "model.layers.59.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
679
+ "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
680
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00014.safetensors",
681
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
682
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
683
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
684
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
685
+ "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
686
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
687
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
688
+ "model.layers.6.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
689
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
690
+ "model.layers.6.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
691
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
692
+ "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors",
693
+ "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
694
+ "model.layers.60.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
695
+ "model.layers.60.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
696
+ "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
697
+ "model.layers.60.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
698
+ "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
699
+ "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
700
+ "model.layers.60.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
701
+ "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
702
+ "model.layers.60.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
703
+ "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
704
+ "model.layers.61.input_layernorm.weight": "model-00013-of-00014.safetensors",
705
+ "model.layers.61.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
706
+ "model.layers.61.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
707
+ "model.layers.61.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
708
+ "model.layers.61.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
709
+ "model.layers.61.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
710
+ "model.layers.61.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
711
+ "model.layers.61.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
712
+ "model.layers.61.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
713
+ "model.layers.61.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
714
+ "model.layers.61.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
715
+ "model.layers.61.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
716
+ "model.layers.62.input_layernorm.weight": "model-00013-of-00014.safetensors",
717
+ "model.layers.62.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
718
+ "model.layers.62.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
719
+ "model.layers.62.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
720
+ "model.layers.62.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
721
+ "model.layers.62.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
722
+ "model.layers.62.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
723
+ "model.layers.62.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
724
+ "model.layers.62.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
725
+ "model.layers.62.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
726
+ "model.layers.62.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
727
+ "model.layers.62.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
728
+ "model.layers.63.input_layernorm.weight": "model-00014-of-00014.safetensors",
729
+ "model.layers.63.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
730
+ "model.layers.63.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
731
+ "model.layers.63.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
732
+ "model.layers.63.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
733
+ "model.layers.63.self_attn.k_proj.bias": "model-00013-of-00014.safetensors",
734
+ "model.layers.63.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
735
+ "model.layers.63.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
736
+ "model.layers.63.self_attn.q_proj.bias": "model-00013-of-00014.safetensors",
737
+ "model.layers.63.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
738
+ "model.layers.63.self_attn.v_proj.bias": "model-00013-of-00014.safetensors",
739
+ "model.layers.63.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
740
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00014.safetensors",
741
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
742
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
743
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
744
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
745
+ "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
746
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
747
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
748
+ "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
749
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
750
+ "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
751
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
752
+ "model.layers.8.input_layernorm.weight": "model-00003-of-00014.safetensors",
753
+ "model.layers.8.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
754
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
755
+ "model.layers.8.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
756
+ "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
757
+ "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00014.safetensors",
758
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
759
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
760
+ "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00014.safetensors",
761
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
762
+ "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00014.safetensors",
763
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
764
+ "model.layers.9.input_layernorm.weight": "model-00003-of-00014.safetensors",
765
+ "model.layers.9.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
766
+ "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
767
+ "model.layers.9.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
768
+ "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
769
+ "model.layers.9.self_attn.k_proj.bias": "model-00003-of-00014.safetensors",
770
+ "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
771
+ "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
772
+ "model.layers.9.self_attn.q_proj.bias": "model-00003-of-00014.safetensors",
773
+ "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
774
+ "model.layers.9.self_attn.v_proj.bias": "model-00003-of-00014.safetensors",
775
+ "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
776
+ "model.norm.weight": "model-00014-of-00014.safetensors"
777
  }
778
  }
special_tokens_map.json CHANGED
@@ -1,20 +1,28 @@
1
  {
2
- "bos_token": {
3
- "content": "<|begin_of_text|>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
 
 
 
 
 
 
 
 
9
  "eos_token": {
10
- "content": "<|eot_id|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
  "pad_token": {
17
- "content": "<|finetune_right_pad_id|>",
18
  "lstrip": false,
19
  "normalized": false,
20
  "rstrip": false,
 
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": "<|PAD_TOKEN|>",
26
  "lstrip": false,
27
  "normalized": false,
28
  "rstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
- size 17209920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
3
+ size 11422086
tokenizer_config.json CHANGED
@@ -1,2048 +1,185 @@
1
  {
2
- "add_bos_token": true,
 
3
  "added_tokens_decoder": {
4
- "128000": {
5
- "content": "<|begin_of_text|>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
- "128001": {
13
- "content": "<|end_of_text|>",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
- "128002": {
21
- "content": "<|reserved_special_token_0|>",
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
- "128003": {
29
- "content": "<|reserved_special_token_1|>",
30
  "lstrip": false,
31
  "normalized": false,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
- "128004": {
37
- "content": "<|finetune_right_pad_id|>",
38
  "lstrip": false,
39
  "normalized": false,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
43
  },
44
- "128005": {
45
- "content": "<|reserved_special_token_2|>",
46
  "lstrip": false,
47
  "normalized": false,
48
  "rstrip": false,
49
  "single_word": false,
50
  "special": true
51
  },
52
- "128006": {
53
- "content": "<|start_header_id|>",
54
  "lstrip": false,
55
  "normalized": false,
56
  "rstrip": false,
57
  "single_word": false,
58
  "special": true
59
  },
60
- "128007": {
61
- "content": "<|end_header_id|>",
62
  "lstrip": false,
63
  "normalized": false,
64
  "rstrip": false,
65
  "single_word": false,
66
  "special": true
67
  },
68
- "128008": {
69
- "content": "<|eom_id|>",
70
  "lstrip": false,
71
  "normalized": false,
72
  "rstrip": false,
73
  "single_word": false,
74
  "special": true
75
  },
76
- "128009": {
77
- "content": "<|eot_id|>",
78
  "lstrip": false,
79
  "normalized": false,
80
  "rstrip": false,
81
  "single_word": false,
82
  "special": true
83
  },
84
- "128010": {
85
- "content": "<|python_tag|>",
86
  "lstrip": false,
87
  "normalized": false,
88
  "rstrip": false,
89
  "single_word": false,
90
  "special": true
91
  },
92
- "128011": {
93
- "content": "<|reserved_special_token_3|>",
94
  "lstrip": false,
95
  "normalized": false,
96
  "rstrip": false,
97
  "single_word": false,
98
  "special": true
99
  },
100
- "128012": {
101
- "content": "<|reserved_special_token_4|>",
102
  "lstrip": false,
103
  "normalized": false,
104
  "rstrip": false,
105
  "single_word": false,
106
  "special": true
107
  },
108
- "128013": {
109
- "content": "<|reserved_special_token_5|>",
110
  "lstrip": false,
111
  "normalized": false,
112
  "rstrip": false,
113
  "single_word": false,
114
  "special": true
115
  },
116
- "128014": {
117
- "content": "<|reserved_special_token_6|>",
118
  "lstrip": false,
119
  "normalized": false,
120
  "rstrip": false,
121
  "single_word": false,
122
- "special": true
123
- },
124
- "128015": {
125
- "content": "<|reserved_special_token_7|>",
126
- "lstrip": false,
127
- "normalized": false,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": true
131
- },
132
- "128016": {
133
- "content": "<|reserved_special_token_8|>",
134
- "lstrip": false,
135
- "normalized": false,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": true
139
- },
140
- "128017": {
141
- "content": "<|reserved_special_token_9|>",
142
- "lstrip": false,
143
- "normalized": false,
144
- "rstrip": false,
145
- "single_word": false,
146
- "special": true
147
- },
148
- "128018": {
149
- "content": "<|reserved_special_token_10|>",
150
- "lstrip": false,
151
- "normalized": false,
152
- "rstrip": false,
153
- "single_word": false,
154
- "special": true
155
- },
156
- "128019": {
157
- "content": "<|reserved_special_token_11|>",
158
- "lstrip": false,
159
- "normalized": false,
160
- "rstrip": false,
161
- "single_word": false,
162
- "special": true
163
- },
164
- "128020": {
165
- "content": "<|reserved_special_token_12|>",
166
- "lstrip": false,
167
- "normalized": false,
168
- "rstrip": false,
169
- "single_word": false,
170
- "special": true
171
- },
172
- "128021": {
173
- "content": "<|reserved_special_token_13|>",
174
- "lstrip": false,
175
- "normalized": false,
176
- "rstrip": false,
177
- "single_word": false,
178
- "special": true
179
- },
180
- "128022": {
181
- "content": "<|reserved_special_token_14|>",
182
- "lstrip": false,
183
- "normalized": false,
184
- "rstrip": false,
185
- "single_word": false,
186
- "special": true
187
- },
188
- "128023": {
189
- "content": "<|reserved_special_token_15|>",
190
- "lstrip": false,
191
- "normalized": false,
192
- "rstrip": false,
193
- "single_word": false,
194
- "special": true
195
- },
196
- "128024": {
197
- "content": "<|reserved_special_token_16|>",
198
- "lstrip": false,
199
- "normalized": false,
200
- "rstrip": false,
201
- "single_word": false,
202
- "special": true
203
- },
204
- "128025": {
205
- "content": "<|reserved_special_token_17|>",
206
- "lstrip": false,
207
- "normalized": false,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": true
211
- },
212
- "128026": {
213
- "content": "<|reserved_special_token_18|>",
214
- "lstrip": false,
215
- "normalized": false,
216
- "rstrip": false,
217
- "single_word": false,
218
- "special": true
219
- },
220
- "128027": {
221
- "content": "<|reserved_special_token_19|>",
222
- "lstrip": false,
223
- "normalized": false,
224
- "rstrip": false,
225
- "single_word": false,
226
- "special": true
227
- },
228
- "128028": {
229
- "content": "<|reserved_special_token_20|>",
230
- "lstrip": false,
231
- "normalized": false,
232
- "rstrip": false,
233
- "single_word": false,
234
- "special": true
235
- },
236
- "128029": {
237
- "content": "<|reserved_special_token_21|>",
238
- "lstrip": false,
239
- "normalized": false,
240
- "rstrip": false,
241
- "single_word": false,
242
- "special": true
243
- },
244
- "128030": {
245
- "content": "<|reserved_special_token_22|>",
246
- "lstrip": false,
247
- "normalized": false,
248
- "rstrip": false,
249
- "single_word": false,
250
- "special": true
251
- },
252
- "128031": {
253
- "content": "<|reserved_special_token_23|>",
254
- "lstrip": false,
255
- "normalized": false,
256
- "rstrip": false,
257
- "single_word": false,
258
- "special": true
259
- },
260
- "128032": {
261
- "content": "<|reserved_special_token_24|>",
262
- "lstrip": false,
263
- "normalized": false,
264
- "rstrip": false,
265
- "single_word": false,
266
- "special": true
267
- },
268
- "128033": {
269
- "content": "<|reserved_special_token_25|>",
270
- "lstrip": false,
271
- "normalized": false,
272
- "rstrip": false,
273
- "single_word": false,
274
- "special": true
275
- },
276
- "128034": {
277
- "content": "<|reserved_special_token_26|>",
278
- "lstrip": false,
279
- "normalized": false,
280
- "rstrip": false,
281
- "single_word": false,
282
- "special": true
283
- },
284
- "128035": {
285
- "content": "<|reserved_special_token_27|>",
286
- "lstrip": false,
287
- "normalized": false,
288
- "rstrip": false,
289
- "single_word": false,
290
- "special": true
291
- },
292
- "128036": {
293
- "content": "<|reserved_special_token_28|>",
294
- "lstrip": false,
295
- "normalized": false,
296
- "rstrip": false,
297
- "single_word": false,
298
- "special": true
299
- },
300
- "128037": {
301
- "content": "<|reserved_special_token_29|>",
302
- "lstrip": false,
303
- "normalized": false,
304
- "rstrip": false,
305
- "single_word": false,
306
- "special": true
307
- },
308
- "128038": {
309
- "content": "<|reserved_special_token_30|>",
310
- "lstrip": false,
311
- "normalized": false,
312
- "rstrip": false,
313
- "single_word": false,
314
- "special": true
315
- },
316
- "128039": {
317
- "content": "<|reserved_special_token_31|>",
318
- "lstrip": false,
319
- "normalized": false,
320
- "rstrip": false,
321
- "single_word": false,
322
- "special": true
323
- },
324
- "128040": {
325
- "content": "<|reserved_special_token_32|>",
326
- "lstrip": false,
327
- "normalized": false,
328
- "rstrip": false,
329
- "single_word": false,
330
- "special": true
331
- },
332
- "128041": {
333
- "content": "<|reserved_special_token_33|>",
334
- "lstrip": false,
335
- "normalized": false,
336
- "rstrip": false,
337
- "single_word": false,
338
- "special": true
339
- },
340
- "128042": {
341
- "content": "<|reserved_special_token_34|>",
342
- "lstrip": false,
343
- "normalized": false,
344
- "rstrip": false,
345
- "single_word": false,
346
- "special": true
347
- },
348
- "128043": {
349
- "content": "<|reserved_special_token_35|>",
350
- "lstrip": false,
351
- "normalized": false,
352
- "rstrip": false,
353
- "single_word": false,
354
- "special": true
355
- },
356
- "128044": {
357
- "content": "<|reserved_special_token_36|>",
358
- "lstrip": false,
359
- "normalized": false,
360
- "rstrip": false,
361
- "single_word": false,
362
- "special": true
363
- },
364
- "128045": {
365
- "content": "<|reserved_special_token_37|>",
366
- "lstrip": false,
367
- "normalized": false,
368
- "rstrip": false,
369
- "single_word": false,
370
- "special": true
371
- },
372
- "128046": {
373
- "content": "<|reserved_special_token_38|>",
374
- "lstrip": false,
375
- "normalized": false,
376
- "rstrip": false,
377
- "single_word": false,
378
- "special": true
379
- },
380
- "128047": {
381
- "content": "<|reserved_special_token_39|>",
382
- "lstrip": false,
383
- "normalized": false,
384
- "rstrip": false,
385
- "single_word": false,
386
- "special": true
387
- },
388
- "128048": {
389
- "content": "<|reserved_special_token_40|>",
390
- "lstrip": false,
391
- "normalized": false,
392
- "rstrip": false,
393
- "single_word": false,
394
- "special": true
395
- },
396
- "128049": {
397
- "content": "<|reserved_special_token_41|>",
398
- "lstrip": false,
399
- "normalized": false,
400
- "rstrip": false,
401
- "single_word": false,
402
- "special": true
403
- },
404
- "128050": {
405
- "content": "<|reserved_special_token_42|>",
406
- "lstrip": false,
407
- "normalized": false,
408
- "rstrip": false,
409
- "single_word": false,
410
- "special": true
411
- },
412
- "128051": {
413
- "content": "<|reserved_special_token_43|>",
414
- "lstrip": false,
415
- "normalized": false,
416
- "rstrip": false,
417
- "single_word": false,
418
- "special": true
419
- },
420
- "128052": {
421
- "content": "<|reserved_special_token_44|>",
422
- "lstrip": false,
423
- "normalized": false,
424
- "rstrip": false,
425
- "single_word": false,
426
- "special": true
427
- },
428
- "128053": {
429
- "content": "<|reserved_special_token_45|>",
430
- "lstrip": false,
431
- "normalized": false,
432
- "rstrip": false,
433
- "single_word": false,
434
- "special": true
435
- },
436
- "128054": {
437
- "content": "<|reserved_special_token_46|>",
438
- "lstrip": false,
439
- "normalized": false,
440
- "rstrip": false,
441
- "single_word": false,
442
- "special": true
443
- },
444
- "128055": {
445
- "content": "<|reserved_special_token_47|>",
446
- "lstrip": false,
447
- "normalized": false,
448
- "rstrip": false,
449
- "single_word": false,
450
- "special": true
451
- },
452
- "128056": {
453
- "content": "<|reserved_special_token_48|>",
454
- "lstrip": false,
455
- "normalized": false,
456
- "rstrip": false,
457
- "single_word": false,
458
- "special": true
459
- },
460
- "128057": {
461
- "content": "<|reserved_special_token_49|>",
462
- "lstrip": false,
463
- "normalized": false,
464
- "rstrip": false,
465
- "single_word": false,
466
- "special": true
467
- },
468
- "128058": {
469
- "content": "<|reserved_special_token_50|>",
470
- "lstrip": false,
471
- "normalized": false,
472
- "rstrip": false,
473
- "single_word": false,
474
- "special": true
475
- },
476
- "128059": {
477
- "content": "<|reserved_special_token_51|>",
478
- "lstrip": false,
479
- "normalized": false,
480
- "rstrip": false,
481
- "single_word": false,
482
- "special": true
483
- },
484
- "128060": {
485
- "content": "<|reserved_special_token_52|>",
486
- "lstrip": false,
487
- "normalized": false,
488
- "rstrip": false,
489
- "single_word": false,
490
- "special": true
491
- },
492
- "128061": {
493
- "content": "<|reserved_special_token_53|>",
494
- "lstrip": false,
495
- "normalized": false,
496
- "rstrip": false,
497
- "single_word": false,
498
- "special": true
499
- },
500
- "128062": {
501
- "content": "<|reserved_special_token_54|>",
502
- "lstrip": false,
503
- "normalized": false,
504
- "rstrip": false,
505
- "single_word": false,
506
- "special": true
507
- },
508
- "128063": {
509
- "content": "<|reserved_special_token_55|>",
510
- "lstrip": false,
511
- "normalized": false,
512
- "rstrip": false,
513
- "single_word": false,
514
- "special": true
515
- },
516
- "128064": {
517
- "content": "<|reserved_special_token_56|>",
518
- "lstrip": false,
519
- "normalized": false,
520
- "rstrip": false,
521
- "single_word": false,
522
- "special": true
523
- },
524
- "128065": {
525
- "content": "<|reserved_special_token_57|>",
526
- "lstrip": false,
527
- "normalized": false,
528
- "rstrip": false,
529
- "single_word": false,
530
- "special": true
531
- },
532
- "128066": {
533
- "content": "<|reserved_special_token_58|>",
534
- "lstrip": false,
535
- "normalized": false,
536
- "rstrip": false,
537
- "single_word": false,
538
- "special": true
539
- },
540
- "128067": {
541
- "content": "<|reserved_special_token_59|>",
542
- "lstrip": false,
543
- "normalized": false,
544
- "rstrip": false,
545
- "single_word": false,
546
- "special": true
547
- },
548
- "128068": {
549
- "content": "<|reserved_special_token_60|>",
550
- "lstrip": false,
551
- "normalized": false,
552
- "rstrip": false,
553
- "single_word": false,
554
- "special": true
555
- },
556
- "128069": {
557
- "content": "<|reserved_special_token_61|>",
558
- "lstrip": false,
559
- "normalized": false,
560
- "rstrip": false,
561
- "single_word": false,
562
- "special": true
563
- },
564
- "128070": {
565
- "content": "<|reserved_special_token_62|>",
566
- "lstrip": false,
567
- "normalized": false,
568
- "rstrip": false,
569
- "single_word": false,
570
- "special": true
571
- },
572
- "128071": {
573
- "content": "<|reserved_special_token_63|>",
574
- "lstrip": false,
575
- "normalized": false,
576
- "rstrip": false,
577
- "single_word": false,
578
- "special": true
579
- },
580
- "128072": {
581
- "content": "<|reserved_special_token_64|>",
582
- "lstrip": false,
583
- "normalized": false,
584
- "rstrip": false,
585
- "single_word": false,
586
- "special": true
587
- },
588
- "128073": {
589
- "content": "<|reserved_special_token_65|>",
590
- "lstrip": false,
591
- "normalized": false,
592
- "rstrip": false,
593
- "single_word": false,
594
- "special": true
595
- },
596
- "128074": {
597
- "content": "<|reserved_special_token_66|>",
598
- "lstrip": false,
599
- "normalized": false,
600
- "rstrip": false,
601
- "single_word": false,
602
- "special": true
603
- },
604
- "128075": {
605
- "content": "<|reserved_special_token_67|>",
606
- "lstrip": false,
607
- "normalized": false,
608
- "rstrip": false,
609
- "single_word": false,
610
- "special": true
611
- },
612
- "128076": {
613
- "content": "<|reserved_special_token_68|>",
614
- "lstrip": false,
615
- "normalized": false,
616
- "rstrip": false,
617
- "single_word": false,
618
- "special": true
619
- },
620
- "128077": {
621
- "content": "<|reserved_special_token_69|>",
622
- "lstrip": false,
623
- "normalized": false,
624
- "rstrip": false,
625
- "single_word": false,
626
- "special": true
627
- },
628
- "128078": {
629
- "content": "<|reserved_special_token_70|>",
630
- "lstrip": false,
631
- "normalized": false,
632
- "rstrip": false,
633
- "single_word": false,
634
- "special": true
635
- },
636
- "128079": {
637
- "content": "<|reserved_special_token_71|>",
638
- "lstrip": false,
639
- "normalized": false,
640
- "rstrip": false,
641
- "single_word": false,
642
- "special": true
643
- },
644
- "128080": {
645
- "content": "<|reserved_special_token_72|>",
646
- "lstrip": false,
647
- "normalized": false,
648
- "rstrip": false,
649
- "single_word": false,
650
- "special": true
651
- },
652
- "128081": {
653
- "content": "<|reserved_special_token_73|>",
654
- "lstrip": false,
655
- "normalized": false,
656
- "rstrip": false,
657
- "single_word": false,
658
- "special": true
659
- },
660
- "128082": {
661
- "content": "<|reserved_special_token_74|>",
662
- "lstrip": false,
663
- "normalized": false,
664
- "rstrip": false,
665
- "single_word": false,
666
- "special": true
667
- },
668
- "128083": {
669
- "content": "<|reserved_special_token_75|>",
670
- "lstrip": false,
671
- "normalized": false,
672
- "rstrip": false,
673
- "single_word": false,
674
- "special": true
675
- },
676
- "128084": {
677
- "content": "<|reserved_special_token_76|>",
678
- "lstrip": false,
679
- "normalized": false,
680
- "rstrip": false,
681
- "single_word": false,
682
- "special": true
683
- },
684
- "128085": {
685
- "content": "<|reserved_special_token_77|>",
686
- "lstrip": false,
687
- "normalized": false,
688
- "rstrip": false,
689
- "single_word": false,
690
- "special": true
691
- },
692
- "128086": {
693
- "content": "<|reserved_special_token_78|>",
694
- "lstrip": false,
695
- "normalized": false,
696
- "rstrip": false,
697
- "single_word": false,
698
- "special": true
699
- },
700
- "128087": {
701
- "content": "<|reserved_special_token_79|>",
702
- "lstrip": false,
703
- "normalized": false,
704
- "rstrip": false,
705
- "single_word": false,
706
- "special": true
707
- },
708
- "128088": {
709
- "content": "<|reserved_special_token_80|>",
710
- "lstrip": false,
711
- "normalized": false,
712
- "rstrip": false,
713
- "single_word": false,
714
- "special": true
715
- },
716
- "128089": {
717
- "content": "<|reserved_special_token_81|>",
718
- "lstrip": false,
719
- "normalized": false,
720
- "rstrip": false,
721
- "single_word": false,
722
- "special": true
723
- },
724
- "128090": {
725
- "content": "<|reserved_special_token_82|>",
726
- "lstrip": false,
727
- "normalized": false,
728
- "rstrip": false,
729
- "single_word": false,
730
- "special": true
731
- },
732
- "128091": {
733
- "content": "<|reserved_special_token_83|>",
734
- "lstrip": false,
735
- "normalized": false,
736
- "rstrip": false,
737
- "single_word": false,
738
- "special": true
739
- },
740
- "128092": {
741
- "content": "<|reserved_special_token_84|>",
742
- "lstrip": false,
743
- "normalized": false,
744
- "rstrip": false,
745
- "single_word": false,
746
- "special": true
747
- },
748
- "128093": {
749
- "content": "<|reserved_special_token_85|>",
750
- "lstrip": false,
751
- "normalized": false,
752
- "rstrip": false,
753
- "single_word": false,
754
- "special": true
755
- },
756
- "128094": {
757
- "content": "<|reserved_special_token_86|>",
758
- "lstrip": false,
759
- "normalized": false,
760
- "rstrip": false,
761
- "single_word": false,
762
- "special": true
763
- },
764
- "128095": {
765
- "content": "<|reserved_special_token_87|>",
766
- "lstrip": false,
767
- "normalized": false,
768
- "rstrip": false,
769
- "single_word": false,
770
- "special": true
771
- },
772
- "128096": {
773
- "content": "<|reserved_special_token_88|>",
774
- "lstrip": false,
775
- "normalized": false,
776
- "rstrip": false,
777
- "single_word": false,
778
- "special": true
779
- },
780
- "128097": {
781
- "content": "<|reserved_special_token_89|>",
782
- "lstrip": false,
783
- "normalized": false,
784
- "rstrip": false,
785
- "single_word": false,
786
- "special": true
787
- },
788
- "128098": {
789
- "content": "<|reserved_special_token_90|>",
790
- "lstrip": false,
791
- "normalized": false,
792
- "rstrip": false,
793
- "single_word": false,
794
- "special": true
795
- },
796
- "128099": {
797
- "content": "<|reserved_special_token_91|>",
798
- "lstrip": false,
799
- "normalized": false,
800
- "rstrip": false,
801
- "single_word": false,
802
- "special": true
803
- },
804
- "128100": {
805
- "content": "<|reserved_special_token_92|>",
806
- "lstrip": false,
807
- "normalized": false,
808
- "rstrip": false,
809
- "single_word": false,
810
- "special": true
811
- },
812
- "128101": {
813
- "content": "<|reserved_special_token_93|>",
814
- "lstrip": false,
815
- "normalized": false,
816
- "rstrip": false,
817
- "single_word": false,
818
- "special": true
819
- },
820
- "128102": {
821
- "content": "<|reserved_special_token_94|>",
822
- "lstrip": false,
823
- "normalized": false,
824
- "rstrip": false,
825
- "single_word": false,
826
- "special": true
827
- },
828
- "128103": {
829
- "content": "<|reserved_special_token_95|>",
830
- "lstrip": false,
831
- "normalized": false,
832
- "rstrip": false,
833
- "single_word": false,
834
- "special": true
835
- },
836
- "128104": {
837
- "content": "<|reserved_special_token_96|>",
838
- "lstrip": false,
839
- "normalized": false,
840
- "rstrip": false,
841
- "single_word": false,
842
- "special": true
843
- },
844
- "128105": {
845
- "content": "<|reserved_special_token_97|>",
846
- "lstrip": false,
847
- "normalized": false,
848
- "rstrip": false,
849
- "single_word": false,
850
- "special": true
851
- },
852
- "128106": {
853
- "content": "<|reserved_special_token_98|>",
854
- "lstrip": false,
855
- "normalized": false,
856
- "rstrip": false,
857
- "single_word": false,
858
- "special": true
859
- },
860
- "128107": {
861
- "content": "<|reserved_special_token_99|>",
862
- "lstrip": false,
863
- "normalized": false,
864
- "rstrip": false,
865
- "single_word": false,
866
- "special": true
867
- },
868
- "128108": {
869
- "content": "<|reserved_special_token_100|>",
870
- "lstrip": false,
871
- "normalized": false,
872
- "rstrip": false,
873
- "single_word": false,
874
- "special": true
875
- },
876
- "128109": {
877
- "content": "<|reserved_special_token_101|>",
878
- "lstrip": false,
879
- "normalized": false,
880
- "rstrip": false,
881
- "single_word": false,
882
- "special": true
883
- },
884
- "128110": {
885
- "content": "<|reserved_special_token_102|>",
886
- "lstrip": false,
887
- "normalized": false,
888
- "rstrip": false,
889
- "single_word": false,
890
- "special": true
891
- },
892
- "128111": {
893
- "content": "<|reserved_special_token_103|>",
894
- "lstrip": false,
895
- "normalized": false,
896
- "rstrip": false,
897
- "single_word": false,
898
- "special": true
899
- },
900
- "128112": {
901
- "content": "<|reserved_special_token_104|>",
902
- "lstrip": false,
903
- "normalized": false,
904
- "rstrip": false,
905
- "single_word": false,
906
- "special": true
907
- },
908
- "128113": {
909
- "content": "<|reserved_special_token_105|>",
910
- "lstrip": false,
911
- "normalized": false,
912
- "rstrip": false,
913
- "single_word": false,
914
- "special": true
915
- },
916
- "128114": {
917
- "content": "<|reserved_special_token_106|>",
918
- "lstrip": false,
919
- "normalized": false,
920
- "rstrip": false,
921
- "single_word": false,
922
- "special": true
923
- },
924
- "128115": {
925
- "content": "<|reserved_special_token_107|>",
926
- "lstrip": false,
927
- "normalized": false,
928
- "rstrip": false,
929
- "single_word": false,
930
- "special": true
931
- },
932
- "128116": {
933
- "content": "<|reserved_special_token_108|>",
934
- "lstrip": false,
935
- "normalized": false,
936
- "rstrip": false,
937
- "single_word": false,
938
- "special": true
939
- },
940
- "128117": {
941
- "content": "<|reserved_special_token_109|>",
942
- "lstrip": false,
943
- "normalized": false,
944
- "rstrip": false,
945
- "single_word": false,
946
- "special": true
947
- },
948
- "128118": {
949
- "content": "<|reserved_special_token_110|>",
950
- "lstrip": false,
951
- "normalized": false,
952
- "rstrip": false,
953
- "single_word": false,
954
- "special": true
955
- },
956
- "128119": {
957
- "content": "<|reserved_special_token_111|>",
958
- "lstrip": false,
959
- "normalized": false,
960
- "rstrip": false,
961
- "single_word": false,
962
- "special": true
963
- },
964
- "128120": {
965
- "content": "<|reserved_special_token_112|>",
966
- "lstrip": false,
967
- "normalized": false,
968
- "rstrip": false,
969
- "single_word": false,
970
- "special": true
971
- },
972
- "128121": {
973
- "content": "<|reserved_special_token_113|>",
974
- "lstrip": false,
975
- "normalized": false,
976
- "rstrip": false,
977
- "single_word": false,
978
- "special": true
979
- },
980
- "128122": {
981
- "content": "<|reserved_special_token_114|>",
982
- "lstrip": false,
983
- "normalized": false,
984
- "rstrip": false,
985
- "single_word": false,
986
- "special": true
987
- },
988
- "128123": {
989
- "content": "<|reserved_special_token_115|>",
990
- "lstrip": false,
991
- "normalized": false,
992
- "rstrip": false,
993
- "single_word": false,
994
- "special": true
995
- },
996
- "128124": {
997
- "content": "<|reserved_special_token_116|>",
998
- "lstrip": false,
999
- "normalized": false,
1000
- "rstrip": false,
1001
- "single_word": false,
1002
- "special": true
1003
- },
1004
- "128125": {
1005
- "content": "<|reserved_special_token_117|>",
1006
- "lstrip": false,
1007
- "normalized": false,
1008
- "rstrip": false,
1009
- "single_word": false,
1010
- "special": true
1011
- },
1012
- "128126": {
1013
- "content": "<|reserved_special_token_118|>",
1014
- "lstrip": false,
1015
- "normalized": false,
1016
- "rstrip": false,
1017
- "single_word": false,
1018
- "special": true
1019
- },
1020
- "128127": {
1021
- "content": "<|reserved_special_token_119|>",
1022
- "lstrip": false,
1023
- "normalized": false,
1024
- "rstrip": false,
1025
- "single_word": false,
1026
- "special": true
1027
- },
1028
- "128128": {
1029
- "content": "<|reserved_special_token_120|>",
1030
- "lstrip": false,
1031
- "normalized": false,
1032
- "rstrip": false,
1033
- "single_word": false,
1034
- "special": true
1035
- },
1036
- "128129": {
1037
- "content": "<|reserved_special_token_121|>",
1038
- "lstrip": false,
1039
- "normalized": false,
1040
- "rstrip": false,
1041
- "single_word": false,
1042
- "special": true
1043
- },
1044
- "128130": {
1045
- "content": "<|reserved_special_token_122|>",
1046
- "lstrip": false,
1047
- "normalized": false,
1048
- "rstrip": false,
1049
- "single_word": false,
1050
- "special": true
1051
- },
1052
- "128131": {
1053
- "content": "<|reserved_special_token_123|>",
1054
- "lstrip": false,
1055
- "normalized": false,
1056
- "rstrip": false,
1057
- "single_word": false,
1058
- "special": true
1059
- },
1060
- "128132": {
1061
- "content": "<|reserved_special_token_124|>",
1062
- "lstrip": false,
1063
- "normalized": false,
1064
- "rstrip": false,
1065
- "single_word": false,
1066
- "special": true
1067
- },
1068
- "128133": {
1069
- "content": "<|reserved_special_token_125|>",
1070
- "lstrip": false,
1071
- "normalized": false,
1072
- "rstrip": false,
1073
- "single_word": false,
1074
- "special": true
1075
- },
1076
- "128134": {
1077
- "content": "<|reserved_special_token_126|>",
1078
- "lstrip": false,
1079
- "normalized": false,
1080
- "rstrip": false,
1081
- "single_word": false,
1082
- "special": true
1083
- },
1084
- "128135": {
1085
- "content": "<|reserved_special_token_127|>",
1086
- "lstrip": false,
1087
- "normalized": false,
1088
- "rstrip": false,
1089
- "single_word": false,
1090
- "special": true
1091
- },
1092
- "128136": {
1093
- "content": "<|reserved_special_token_128|>",
1094
- "lstrip": false,
1095
- "normalized": false,
1096
- "rstrip": false,
1097
- "single_word": false,
1098
- "special": true
1099
- },
1100
- "128137": {
1101
- "content": "<|reserved_special_token_129|>",
1102
- "lstrip": false,
1103
- "normalized": false,
1104
- "rstrip": false,
1105
- "single_word": false,
1106
- "special": true
1107
- },
1108
- "128138": {
1109
- "content": "<|reserved_special_token_130|>",
1110
- "lstrip": false,
1111
- "normalized": false,
1112
- "rstrip": false,
1113
- "single_word": false,
1114
- "special": true
1115
- },
1116
- "128139": {
1117
- "content": "<|reserved_special_token_131|>",
1118
- "lstrip": false,
1119
- "normalized": false,
1120
- "rstrip": false,
1121
- "single_word": false,
1122
- "special": true
1123
- },
1124
- "128140": {
1125
- "content": "<|reserved_special_token_132|>",
1126
- "lstrip": false,
1127
- "normalized": false,
1128
- "rstrip": false,
1129
- "single_word": false,
1130
- "special": true
1131
- },
1132
- "128141": {
1133
- "content": "<|reserved_special_token_133|>",
1134
- "lstrip": false,
1135
- "normalized": false,
1136
- "rstrip": false,
1137
- "single_word": false,
1138
- "special": true
1139
- },
1140
- "128142": {
1141
- "content": "<|reserved_special_token_134|>",
1142
- "lstrip": false,
1143
- "normalized": false,
1144
- "rstrip": false,
1145
- "single_word": false,
1146
- "special": true
1147
- },
1148
- "128143": {
1149
- "content": "<|reserved_special_token_135|>",
1150
- "lstrip": false,
1151
- "normalized": false,
1152
- "rstrip": false,
1153
- "single_word": false,
1154
- "special": true
1155
- },
1156
- "128144": {
1157
- "content": "<|reserved_special_token_136|>",
1158
- "lstrip": false,
1159
- "normalized": false,
1160
- "rstrip": false,
1161
- "single_word": false,
1162
- "special": true
1163
- },
1164
- "128145": {
1165
- "content": "<|reserved_special_token_137|>",
1166
- "lstrip": false,
1167
- "normalized": false,
1168
- "rstrip": false,
1169
- "single_word": false,
1170
- "special": true
1171
- },
1172
- "128146": {
1173
- "content": "<|reserved_special_token_138|>",
1174
- "lstrip": false,
1175
- "normalized": false,
1176
- "rstrip": false,
1177
- "single_word": false,
1178
- "special": true
1179
- },
1180
- "128147": {
1181
- "content": "<|reserved_special_token_139|>",
1182
- "lstrip": false,
1183
- "normalized": false,
1184
- "rstrip": false,
1185
- "single_word": false,
1186
- "special": true
1187
- },
1188
- "128148": {
1189
- "content": "<|reserved_special_token_140|>",
1190
- "lstrip": false,
1191
- "normalized": false,
1192
- "rstrip": false,
1193
- "single_word": false,
1194
- "special": true
1195
- },
1196
- "128149": {
1197
- "content": "<|reserved_special_token_141|>",
1198
- "lstrip": false,
1199
- "normalized": false,
1200
- "rstrip": false,
1201
- "single_word": false,
1202
- "special": true
1203
- },
1204
- "128150": {
1205
- "content": "<|reserved_special_token_142|>",
1206
- "lstrip": false,
1207
- "normalized": false,
1208
- "rstrip": false,
1209
- "single_word": false,
1210
- "special": true
1211
- },
1212
- "128151": {
1213
- "content": "<|reserved_special_token_143|>",
1214
- "lstrip": false,
1215
- "normalized": false,
1216
- "rstrip": false,
1217
- "single_word": false,
1218
- "special": true
1219
- },
1220
- "128152": {
1221
- "content": "<|reserved_special_token_144|>",
1222
- "lstrip": false,
1223
- "normalized": false,
1224
- "rstrip": false,
1225
- "single_word": false,
1226
- "special": true
1227
- },
1228
- "128153": {
1229
- "content": "<|reserved_special_token_145|>",
1230
- "lstrip": false,
1231
- "normalized": false,
1232
- "rstrip": false,
1233
- "single_word": false,
1234
- "special": true
1235
- },
1236
- "128154": {
1237
- "content": "<|reserved_special_token_146|>",
1238
- "lstrip": false,
1239
- "normalized": false,
1240
- "rstrip": false,
1241
- "single_word": false,
1242
- "special": true
1243
- },
1244
- "128155": {
1245
- "content": "<|reserved_special_token_147|>",
1246
- "lstrip": false,
1247
- "normalized": false,
1248
- "rstrip": false,
1249
- "single_word": false,
1250
- "special": true
1251
- },
1252
- "128156": {
1253
- "content": "<|reserved_special_token_148|>",
1254
- "lstrip": false,
1255
- "normalized": false,
1256
- "rstrip": false,
1257
- "single_word": false,
1258
- "special": true
1259
- },
1260
- "128157": {
1261
- "content": "<|reserved_special_token_149|>",
1262
- "lstrip": false,
1263
- "normalized": false,
1264
- "rstrip": false,
1265
- "single_word": false,
1266
- "special": true
1267
- },
1268
- "128158": {
1269
- "content": "<|reserved_special_token_150|>",
1270
- "lstrip": false,
1271
- "normalized": false,
1272
- "rstrip": false,
1273
- "single_word": false,
1274
- "special": true
1275
- },
1276
- "128159": {
1277
- "content": "<|reserved_special_token_151|>",
1278
- "lstrip": false,
1279
- "normalized": false,
1280
- "rstrip": false,
1281
- "single_word": false,
1282
- "special": true
1283
- },
1284
- "128160": {
1285
- "content": "<|reserved_special_token_152|>",
1286
- "lstrip": false,
1287
- "normalized": false,
1288
- "rstrip": false,
1289
- "single_word": false,
1290
- "special": true
1291
- },
1292
- "128161": {
1293
- "content": "<|reserved_special_token_153|>",
1294
- "lstrip": false,
1295
- "normalized": false,
1296
- "rstrip": false,
1297
- "single_word": false,
1298
- "special": true
1299
- },
1300
- "128162": {
1301
- "content": "<|reserved_special_token_154|>",
1302
- "lstrip": false,
1303
- "normalized": false,
1304
- "rstrip": false,
1305
- "single_word": false,
1306
- "special": true
1307
- },
1308
- "128163": {
1309
- "content": "<|reserved_special_token_155|>",
1310
- "lstrip": false,
1311
- "normalized": false,
1312
- "rstrip": false,
1313
- "single_word": false,
1314
- "special": true
1315
- },
1316
- "128164": {
1317
- "content": "<|reserved_special_token_156|>",
1318
- "lstrip": false,
1319
- "normalized": false,
1320
- "rstrip": false,
1321
- "single_word": false,
1322
- "special": true
1323
- },
1324
- "128165": {
1325
- "content": "<|reserved_special_token_157|>",
1326
- "lstrip": false,
1327
- "normalized": false,
1328
- "rstrip": false,
1329
- "single_word": false,
1330
- "special": true
1331
- },
1332
- "128166": {
1333
- "content": "<|reserved_special_token_158|>",
1334
- "lstrip": false,
1335
- "normalized": false,
1336
- "rstrip": false,
1337
- "single_word": false,
1338
- "special": true
1339
- },
1340
- "128167": {
1341
- "content": "<|reserved_special_token_159|>",
1342
- "lstrip": false,
1343
- "normalized": false,
1344
- "rstrip": false,
1345
- "single_word": false,
1346
- "special": true
1347
- },
1348
- "128168": {
1349
- "content": "<|reserved_special_token_160|>",
1350
- "lstrip": false,
1351
- "normalized": false,
1352
- "rstrip": false,
1353
- "single_word": false,
1354
- "special": true
1355
- },
1356
- "128169": {
1357
- "content": "<|reserved_special_token_161|>",
1358
- "lstrip": false,
1359
- "normalized": false,
1360
- "rstrip": false,
1361
- "single_word": false,
1362
- "special": true
1363
- },
1364
- "128170": {
1365
- "content": "<|reserved_special_token_162|>",
1366
- "lstrip": false,
1367
- "normalized": false,
1368
- "rstrip": false,
1369
- "single_word": false,
1370
- "special": true
1371
- },
1372
- "128171": {
1373
- "content": "<|reserved_special_token_163|>",
1374
- "lstrip": false,
1375
- "normalized": false,
1376
- "rstrip": false,
1377
- "single_word": false,
1378
- "special": true
1379
- },
1380
- "128172": {
1381
- "content": "<|reserved_special_token_164|>",
1382
- "lstrip": false,
1383
- "normalized": false,
1384
- "rstrip": false,
1385
- "single_word": false,
1386
- "special": true
1387
- },
1388
- "128173": {
1389
- "content": "<|reserved_special_token_165|>",
1390
- "lstrip": false,
1391
- "normalized": false,
1392
- "rstrip": false,
1393
- "single_word": false,
1394
- "special": true
1395
- },
1396
- "128174": {
1397
- "content": "<|reserved_special_token_166|>",
1398
- "lstrip": false,
1399
- "normalized": false,
1400
- "rstrip": false,
1401
- "single_word": false,
1402
- "special": true
1403
- },
1404
- "128175": {
1405
- "content": "<|reserved_special_token_167|>",
1406
- "lstrip": false,
1407
- "normalized": false,
1408
- "rstrip": false,
1409
- "single_word": false,
1410
- "special": true
1411
- },
1412
- "128176": {
1413
- "content": "<|reserved_special_token_168|>",
1414
- "lstrip": false,
1415
- "normalized": false,
1416
- "rstrip": false,
1417
- "single_word": false,
1418
- "special": true
1419
- },
1420
- "128177": {
1421
- "content": "<|reserved_special_token_169|>",
1422
- "lstrip": false,
1423
- "normalized": false,
1424
- "rstrip": false,
1425
- "single_word": false,
1426
- "special": true
1427
- },
1428
- "128178": {
1429
- "content": "<|reserved_special_token_170|>",
1430
- "lstrip": false,
1431
- "normalized": false,
1432
- "rstrip": false,
1433
- "single_word": false,
1434
- "special": true
1435
- },
1436
- "128179": {
1437
- "content": "<|reserved_special_token_171|>",
1438
- "lstrip": false,
1439
- "normalized": false,
1440
- "rstrip": false,
1441
- "single_word": false,
1442
- "special": true
1443
- },
1444
- "128180": {
1445
- "content": "<|reserved_special_token_172|>",
1446
- "lstrip": false,
1447
- "normalized": false,
1448
- "rstrip": false,
1449
- "single_word": false,
1450
- "special": true
1451
- },
1452
- "128181": {
1453
- "content": "<|reserved_special_token_173|>",
1454
- "lstrip": false,
1455
- "normalized": false,
1456
- "rstrip": false,
1457
- "single_word": false,
1458
- "special": true
1459
- },
1460
- "128182": {
1461
- "content": "<|reserved_special_token_174|>",
1462
- "lstrip": false,
1463
- "normalized": false,
1464
- "rstrip": false,
1465
- "single_word": false,
1466
- "special": true
1467
- },
1468
- "128183": {
1469
- "content": "<|reserved_special_token_175|>",
1470
- "lstrip": false,
1471
- "normalized": false,
1472
- "rstrip": false,
1473
- "single_word": false,
1474
- "special": true
1475
- },
1476
- "128184": {
1477
- "content": "<|reserved_special_token_176|>",
1478
- "lstrip": false,
1479
- "normalized": false,
1480
- "rstrip": false,
1481
- "single_word": false,
1482
- "special": true
1483
- },
1484
- "128185": {
1485
- "content": "<|reserved_special_token_177|>",
1486
- "lstrip": false,
1487
- "normalized": false,
1488
- "rstrip": false,
1489
- "single_word": false,
1490
- "special": true
1491
- },
1492
- "128186": {
1493
- "content": "<|reserved_special_token_178|>",
1494
- "lstrip": false,
1495
- "normalized": false,
1496
- "rstrip": false,
1497
- "single_word": false,
1498
- "special": true
1499
- },
1500
- "128187": {
1501
- "content": "<|reserved_special_token_179|>",
1502
- "lstrip": false,
1503
- "normalized": false,
1504
- "rstrip": false,
1505
- "single_word": false,
1506
- "special": true
1507
- },
1508
- "128188": {
1509
- "content": "<|reserved_special_token_180|>",
1510
- "lstrip": false,
1511
- "normalized": false,
1512
- "rstrip": false,
1513
- "single_word": false,
1514
- "special": true
1515
- },
1516
- "128189": {
1517
- "content": "<|reserved_special_token_181|>",
1518
- "lstrip": false,
1519
- "normalized": false,
1520
- "rstrip": false,
1521
- "single_word": false,
1522
- "special": true
1523
- },
1524
- "128190": {
1525
- "content": "<|reserved_special_token_182|>",
1526
- "lstrip": false,
1527
- "normalized": false,
1528
- "rstrip": false,
1529
- "single_word": false,
1530
- "special": true
1531
- },
1532
- "128191": {
1533
- "content": "<|reserved_special_token_183|>",
1534
- "lstrip": false,
1535
- "normalized": false,
1536
- "rstrip": false,
1537
- "single_word": false,
1538
- "special": true
1539
- },
1540
- "128192": {
1541
- "content": "<|reserved_special_token_184|>",
1542
- "lstrip": false,
1543
- "normalized": false,
1544
- "rstrip": false,
1545
- "single_word": false,
1546
- "special": true
1547
- },
1548
- "128193": {
1549
- "content": "<|reserved_special_token_185|>",
1550
- "lstrip": false,
1551
- "normalized": false,
1552
- "rstrip": false,
1553
- "single_word": false,
1554
- "special": true
1555
- },
1556
- "128194": {
1557
- "content": "<|reserved_special_token_186|>",
1558
- "lstrip": false,
1559
- "normalized": false,
1560
- "rstrip": false,
1561
- "single_word": false,
1562
- "special": true
1563
- },
1564
- "128195": {
1565
- "content": "<|reserved_special_token_187|>",
1566
- "lstrip": false,
1567
- "normalized": false,
1568
- "rstrip": false,
1569
- "single_word": false,
1570
- "special": true
1571
- },
1572
- "128196": {
1573
- "content": "<|reserved_special_token_188|>",
1574
- "lstrip": false,
1575
- "normalized": false,
1576
- "rstrip": false,
1577
- "single_word": false,
1578
- "special": true
1579
- },
1580
- "128197": {
1581
- "content": "<|reserved_special_token_189|>",
1582
- "lstrip": false,
1583
- "normalized": false,
1584
- "rstrip": false,
1585
- "single_word": false,
1586
- "special": true
1587
- },
1588
- "128198": {
1589
- "content": "<|reserved_special_token_190|>",
1590
- "lstrip": false,
1591
- "normalized": false,
1592
- "rstrip": false,
1593
- "single_word": false,
1594
- "special": true
1595
- },
1596
- "128199": {
1597
- "content": "<|reserved_special_token_191|>",
1598
- "lstrip": false,
1599
- "normalized": false,
1600
- "rstrip": false,
1601
- "single_word": false,
1602
- "special": true
1603
- },
1604
- "128200": {
1605
- "content": "<|reserved_special_token_192|>",
1606
- "lstrip": false,
1607
- "normalized": false,
1608
- "rstrip": false,
1609
- "single_word": false,
1610
- "special": true
1611
- },
1612
- "128201": {
1613
- "content": "<|reserved_special_token_193|>",
1614
- "lstrip": false,
1615
- "normalized": false,
1616
- "rstrip": false,
1617
- "single_word": false,
1618
- "special": true
1619
- },
1620
- "128202": {
1621
- "content": "<|reserved_special_token_194|>",
1622
- "lstrip": false,
1623
- "normalized": false,
1624
- "rstrip": false,
1625
- "single_word": false,
1626
- "special": true
1627
- },
1628
- "128203": {
1629
- "content": "<|reserved_special_token_195|>",
1630
- "lstrip": false,
1631
- "normalized": false,
1632
- "rstrip": false,
1633
- "single_word": false,
1634
- "special": true
1635
- },
1636
- "128204": {
1637
- "content": "<|reserved_special_token_196|>",
1638
- "lstrip": false,
1639
- "normalized": false,
1640
- "rstrip": false,
1641
- "single_word": false,
1642
- "special": true
1643
- },
1644
- "128205": {
1645
- "content": "<|reserved_special_token_197|>",
1646
- "lstrip": false,
1647
- "normalized": false,
1648
- "rstrip": false,
1649
- "single_word": false,
1650
- "special": true
1651
- },
1652
- "128206": {
1653
- "content": "<|reserved_special_token_198|>",
1654
- "lstrip": false,
1655
- "normalized": false,
1656
- "rstrip": false,
1657
- "single_word": false,
1658
- "special": true
1659
- },
1660
- "128207": {
1661
- "content": "<|reserved_special_token_199|>",
1662
- "lstrip": false,
1663
- "normalized": false,
1664
- "rstrip": false,
1665
- "single_word": false,
1666
- "special": true
1667
- },
1668
- "128208": {
1669
- "content": "<|reserved_special_token_200|>",
1670
- "lstrip": false,
1671
- "normalized": false,
1672
- "rstrip": false,
1673
- "single_word": false,
1674
- "special": true
1675
- },
1676
- "128209": {
1677
- "content": "<|reserved_special_token_201|>",
1678
- "lstrip": false,
1679
- "normalized": false,
1680
- "rstrip": false,
1681
- "single_word": false,
1682
- "special": true
1683
- },
1684
- "128210": {
1685
- "content": "<|reserved_special_token_202|>",
1686
- "lstrip": false,
1687
- "normalized": false,
1688
- "rstrip": false,
1689
- "single_word": false,
1690
- "special": true
1691
- },
1692
- "128211": {
1693
- "content": "<|reserved_special_token_203|>",
1694
- "lstrip": false,
1695
- "normalized": false,
1696
- "rstrip": false,
1697
- "single_word": false,
1698
- "special": true
1699
- },
1700
- "128212": {
1701
- "content": "<|reserved_special_token_204|>",
1702
- "lstrip": false,
1703
- "normalized": false,
1704
- "rstrip": false,
1705
- "single_word": false,
1706
- "special": true
1707
- },
1708
- "128213": {
1709
- "content": "<|reserved_special_token_205|>",
1710
- "lstrip": false,
1711
- "normalized": false,
1712
- "rstrip": false,
1713
- "single_word": false,
1714
- "special": true
1715
- },
1716
- "128214": {
1717
- "content": "<|reserved_special_token_206|>",
1718
- "lstrip": false,
1719
- "normalized": false,
1720
- "rstrip": false,
1721
- "single_word": false,
1722
- "special": true
1723
- },
1724
- "128215": {
1725
- "content": "<|reserved_special_token_207|>",
1726
- "lstrip": false,
1727
- "normalized": false,
1728
- "rstrip": false,
1729
- "single_word": false,
1730
- "special": true
1731
- },
1732
- "128216": {
1733
- "content": "<|reserved_special_token_208|>",
1734
- "lstrip": false,
1735
- "normalized": false,
1736
- "rstrip": false,
1737
- "single_word": false,
1738
- "special": true
1739
- },
1740
- "128217": {
1741
- "content": "<|reserved_special_token_209|>",
1742
- "lstrip": false,
1743
- "normalized": false,
1744
- "rstrip": false,
1745
- "single_word": false,
1746
- "special": true
1747
- },
1748
- "128218": {
1749
- "content": "<|reserved_special_token_210|>",
1750
- "lstrip": false,
1751
- "normalized": false,
1752
- "rstrip": false,
1753
- "single_word": false,
1754
- "special": true
1755
- },
1756
- "128219": {
1757
- "content": "<|reserved_special_token_211|>",
1758
- "lstrip": false,
1759
- "normalized": false,
1760
- "rstrip": false,
1761
- "single_word": false,
1762
- "special": true
1763
- },
1764
- "128220": {
1765
- "content": "<|reserved_special_token_212|>",
1766
- "lstrip": false,
1767
- "normalized": false,
1768
- "rstrip": false,
1769
- "single_word": false,
1770
- "special": true
1771
- },
1772
- "128221": {
1773
- "content": "<|reserved_special_token_213|>",
1774
- "lstrip": false,
1775
- "normalized": false,
1776
- "rstrip": false,
1777
- "single_word": false,
1778
- "special": true
1779
- },
1780
- "128222": {
1781
- "content": "<|reserved_special_token_214|>",
1782
- "lstrip": false,
1783
- "normalized": false,
1784
- "rstrip": false,
1785
- "single_word": false,
1786
- "special": true
1787
- },
1788
- "128223": {
1789
- "content": "<|reserved_special_token_215|>",
1790
- "lstrip": false,
1791
- "normalized": false,
1792
- "rstrip": false,
1793
- "single_word": false,
1794
- "special": true
1795
- },
1796
- "128224": {
1797
- "content": "<|reserved_special_token_216|>",
1798
- "lstrip": false,
1799
- "normalized": false,
1800
- "rstrip": false,
1801
- "single_word": false,
1802
- "special": true
1803
- },
1804
- "128225": {
1805
- "content": "<|reserved_special_token_217|>",
1806
- "lstrip": false,
1807
- "normalized": false,
1808
- "rstrip": false,
1809
- "single_word": false,
1810
- "special": true
1811
- },
1812
- "128226": {
1813
- "content": "<|reserved_special_token_218|>",
1814
- "lstrip": false,
1815
- "normalized": false,
1816
- "rstrip": false,
1817
- "single_word": false,
1818
- "special": true
1819
- },
1820
- "128227": {
1821
- "content": "<|reserved_special_token_219|>",
1822
- "lstrip": false,
1823
- "normalized": false,
1824
- "rstrip": false,
1825
- "single_word": false,
1826
- "special": true
1827
- },
1828
- "128228": {
1829
- "content": "<|reserved_special_token_220|>",
1830
- "lstrip": false,
1831
- "normalized": false,
1832
- "rstrip": false,
1833
- "single_word": false,
1834
- "special": true
1835
- },
1836
- "128229": {
1837
- "content": "<|reserved_special_token_221|>",
1838
- "lstrip": false,
1839
- "normalized": false,
1840
- "rstrip": false,
1841
- "single_word": false,
1842
- "special": true
1843
- },
1844
- "128230": {
1845
- "content": "<|reserved_special_token_222|>",
1846
- "lstrip": false,
1847
- "normalized": false,
1848
- "rstrip": false,
1849
- "single_word": false,
1850
- "special": true
1851
- },
1852
- "128231": {
1853
- "content": "<|reserved_special_token_223|>",
1854
- "lstrip": false,
1855
- "normalized": false,
1856
- "rstrip": false,
1857
- "single_word": false,
1858
- "special": true
1859
- },
1860
- "128232": {
1861
- "content": "<|reserved_special_token_224|>",
1862
- "lstrip": false,
1863
- "normalized": false,
1864
- "rstrip": false,
1865
- "single_word": false,
1866
- "special": true
1867
- },
1868
- "128233": {
1869
- "content": "<|reserved_special_token_225|>",
1870
- "lstrip": false,
1871
- "normalized": false,
1872
- "rstrip": false,
1873
- "single_word": false,
1874
- "special": true
1875
- },
1876
- "128234": {
1877
- "content": "<|reserved_special_token_226|>",
1878
- "lstrip": false,
1879
- "normalized": false,
1880
- "rstrip": false,
1881
- "single_word": false,
1882
- "special": true
1883
- },
1884
- "128235": {
1885
- "content": "<|reserved_special_token_227|>",
1886
- "lstrip": false,
1887
- "normalized": false,
1888
- "rstrip": false,
1889
- "single_word": false,
1890
- "special": true
1891
- },
1892
- "128236": {
1893
- "content": "<|reserved_special_token_228|>",
1894
- "lstrip": false,
1895
- "normalized": false,
1896
- "rstrip": false,
1897
- "single_word": false,
1898
- "special": true
1899
- },
1900
- "128237": {
1901
- "content": "<|reserved_special_token_229|>",
1902
- "lstrip": false,
1903
- "normalized": false,
1904
- "rstrip": false,
1905
- "single_word": false,
1906
- "special": true
1907
- },
1908
- "128238": {
1909
- "content": "<|reserved_special_token_230|>",
1910
- "lstrip": false,
1911
- "normalized": false,
1912
- "rstrip": false,
1913
- "single_word": false,
1914
- "special": true
1915
- },
1916
- "128239": {
1917
- "content": "<|reserved_special_token_231|>",
1918
- "lstrip": false,
1919
- "normalized": false,
1920
- "rstrip": false,
1921
- "single_word": false,
1922
- "special": true
1923
- },
1924
- "128240": {
1925
- "content": "<|reserved_special_token_232|>",
1926
- "lstrip": false,
1927
- "normalized": false,
1928
- "rstrip": false,
1929
- "single_word": false,
1930
- "special": true
1931
- },
1932
- "128241": {
1933
- "content": "<|reserved_special_token_233|>",
1934
- "lstrip": false,
1935
- "normalized": false,
1936
- "rstrip": false,
1937
- "single_word": false,
1938
- "special": true
1939
- },
1940
- "128242": {
1941
- "content": "<|reserved_special_token_234|>",
1942
- "lstrip": false,
1943
- "normalized": false,
1944
- "rstrip": false,
1945
- "single_word": false,
1946
- "special": true
1947
- },
1948
- "128243": {
1949
- "content": "<|reserved_special_token_235|>",
1950
- "lstrip": false,
1951
- "normalized": false,
1952
- "rstrip": false,
1953
- "single_word": false,
1954
- "special": true
1955
- },
1956
- "128244": {
1957
- "content": "<|reserved_special_token_236|>",
1958
- "lstrip": false,
1959
- "normalized": false,
1960
- "rstrip": false,
1961
- "single_word": false,
1962
- "special": true
1963
- },
1964
- "128245": {
1965
- "content": "<|reserved_special_token_237|>",
1966
- "lstrip": false,
1967
- "normalized": false,
1968
- "rstrip": false,
1969
- "single_word": false,
1970
- "special": true
1971
- },
1972
- "128246": {
1973
- "content": "<|reserved_special_token_238|>",
1974
- "lstrip": false,
1975
- "normalized": false,
1976
- "rstrip": false,
1977
- "single_word": false,
1978
- "special": true
1979
- },
1980
- "128247": {
1981
- "content": "<|reserved_special_token_239|>",
1982
- "lstrip": false,
1983
- "normalized": false,
1984
- "rstrip": false,
1985
- "single_word": false,
1986
- "special": true
1987
  },
1988
- "128248": {
1989
- "content": "<|reserved_special_token_240|>",
1990
  "lstrip": false,
1991
  "normalized": false,
1992
  "rstrip": false,
1993
  "single_word": false,
1994
- "special": true
1995
  },
1996
- "128249": {
1997
- "content": "<|reserved_special_token_241|>",
1998
  "lstrip": false,
1999
  "normalized": false,
2000
  "rstrip": false,
2001
  "single_word": false,
2002
- "special": true
2003
  },
2004
- "128250": {
2005
- "content": "<|reserved_special_token_242|>",
2006
  "lstrip": false,
2007
  "normalized": false,
2008
  "rstrip": false,
2009
  "single_word": false,
2010
- "special": true
2011
  },
2012
- "128251": {
2013
- "content": "<|reserved_special_token_243|>",
2014
  "lstrip": false,
2015
  "normalized": false,
2016
  "rstrip": false,
2017
  "single_word": false,
2018
- "special": true
2019
  },
2020
- "128252": {
2021
- "content": "<|reserved_special_token_244|>",
2022
  "lstrip": false,
2023
  "normalized": false,
2024
  "rstrip": false,
2025
  "single_word": false,
2026
- "special": true
2027
  },
2028
- "128253": {
2029
- "content": "<|reserved_special_token_245|>",
2030
  "lstrip": false,
2031
  "normalized": false,
2032
  "rstrip": false,
2033
  "single_word": false,
2034
- "special": true
2035
  },
2036
- "128254": {
2037
- "content": "<|reserved_special_token_246|>",
2038
  "lstrip": false,
2039
  "normalized": false,
2040
  "rstrip": false,
2041
  "single_word": false,
2042
- "special": true
2043
  },
2044
- "128255": {
2045
- "content": "<|reserved_special_token_247|>",
2046
  "lstrip": false,
2047
  "normalized": false,
2048
  "rstrip": false,
@@ -2050,18 +187,31 @@
2050
  "special": true
2051
  }
2052
  },
2053
- "bos_token": "<|begin_of_text|>",
2054
- "clean_up_tokenization_spaces": true,
2055
- "eos_token": "<|eot_id|>",
2056
- "extra_special_tokens": {},
2057
- "model_input_names": [
2058
- "input_ids",
2059
- "attention_mask"
 
 
 
 
 
 
 
2060
  ],
2061
- "model_max_length": 131072,
2062
- "pad_token": "<|finetune_right_pad_id|>",
 
 
 
 
 
2063
  "padding_side": "left",
2064
- "tokenizer_class": "PreTrainedTokenizerFast",
 
2065
  "unk_token": null,
2066
  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\n\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\n\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content'] %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\n\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\n\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n"
2067
  }
 
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
+ "151665": {
182
+ "content": "<|PAD_TOKEN|>",
183
  "lstrip": false,
184
  "normalized": false,
185
  "rstrip": false,
 
187
  "special": true
188
  }
189
  },
190
+ "additional_special_tokens": [
191
+ "<|im_start|>",
192
+ "<|im_end|>",
193
+ "<|object_ref_start|>",
194
+ "<|object_ref_end|>",
195
+ "<|box_start|>",
196
+ "<|box_end|>",
197
+ "<|quad_start|>",
198
+ "<|quad_end|>",
199
+ "<|vision_start|>",
200
+ "<|vision_end|>",
201
+ "<|vision_pad|>",
202
+ "<|image_pad|>",
203
+ "<|video_pad|>"
204
  ],
205
+ "bos_token": null,
206
+ "clean_up_tokenization_spaces": false,
207
+ "eos_token": "<|im_end|>",
208
+ "errors": "replace",
209
+ "extra_special_tokens": {},
210
+ "model_max_length": 32768,
211
+ "pad_token": "<|PAD_TOKEN|>",
212
  "padding_side": "left",
213
+ "split_special_tokens": false,
214
+ "tokenizer_class": "Qwen2Tokenizer",
215
  "unk_token": null,
216
  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\n\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\n\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content'] %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\n\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\n\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n"
217
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff