Text Generation
Transformers
Safetensors
PyTorch
English
mistral
finetuned
quantized
4-bit precision
AWQ
instruct
conversational
Inference Endpoints
text-generation-inference
finetune
chatml
DPO
RLHF
gpt4
synthetic data
distillation
awq
Suparious commited on
Commit
862377f
1 Parent(s): 5f82e61

Upload supporting files and README

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ bagel.png filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -1,3 +1,170 @@
1
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ tags:
3
+ - finetuned
4
+ - quantized
5
+ - 4-bit
6
+ - AWQ
7
+ - transformers
8
+ - pytorch
9
+ - mistral
10
+ - instruct
11
+ - text-generation
12
+ - conversational
13
+ - license:apache-2.0
14
+ - autotrain_compatible
15
+ - endpoints_compatible
16
+ - text-generation-inference
17
+ - region:us
18
+ - finetune
19
+ - chatml
20
+ - DPO
21
+ - RLHF
22
+ - gpt4
23
+ - synthetic data
24
+ - distillation
25
  license: apache-2.0
26
+ base_model: mistralai/mistral-7b-v0.1
27
+ datasets:
28
+ - ai2_arc
29
+ - allenai/ultrafeedback_binarized_cleaned
30
+ - argilla/distilabel-intel-orca-dpo-pairs
31
+ - jondurbin/airoboros-3.2
32
+ - codeparrot/apps
33
+ - facebook/belebele
34
+ - bluemoon-fandom-1-1-rp-cleaned
35
+ - boolq
36
+ - camel-ai/biology
37
+ - camel-ai/chemistry
38
+ - camel-ai/math
39
+ - camel-ai/physics
40
+ - jondurbin/contextual-dpo-v0.1
41
+ - jondurbin/gutenberg-dpo-v0.1
42
+ - jondurbin/py-dpo-v0.1
43
+ - jondurbin/truthy-dpo-v0.1
44
+ - LDJnr/Capybara
45
+ - jondurbin/cinematika-v0.1
46
+ - WizardLM/WizardLM_evol_instruct_70k
47
+ - glaiveai/glaive-function-calling-v2
48
+ - jondurbin/gutenberg-dpo-v0.1
49
+ - grimulkan/LimaRP-augmented
50
+ - lmsys/lmsys-chat-1m
51
+ - ParisNeo/lollms_aware_dataset
52
+ - TIGER-Lab/MathInstruct
53
+ - Muennighoff/natural-instructions
54
+ - openbookqa
55
+ - kingbri/PIPPA-shareGPT
56
+ - piqa
57
+ - Vezora/Tested-22k-Python-Alpaca
58
+ - ropes
59
+ - cakiki/rosetta-code
60
+ - Open-Orca/SlimOrca
61
+ - b-mc2/sql-create-context
62
+ - squad_v2
63
+ - mattpscott/airoboros-summarization
64
+ - migtissera/Synthia-v1.3
65
+ - unalignment/toxic-dpo-v0.2
66
+ - WhiteRabbitNeo/WRN-Chapter-1
67
+ - WhiteRabbitNeo/WRN-Chapter-2
68
+ - winogrande
69
+ language:
70
+ - en
71
+ quantized_by: Suparious
72
+ pipeline_tag: text-generation
73
+ model_creator: jondurbin
74
+ model_name: bagel 7B v0.4 DPO
75
+ inference: false
76
+ prompt_template: '{bos}<|im_start|>{role}
77
+
78
+ {text}
79
+
80
+ <|im_end|>{eos}
81
+ '
82
  ---
83
+
84
+ # A bagel, with everything
85
+
86
+ - Model creator: [jondurbin](https://huggingface.co/jondurbin)
87
+ - Original model: [OpenHermes Mistral 2.5 7B DPO](https://huggingface.co/jondurbin/bagel-dpo-7b-v0.4)
88
+
89
+ ![bagel](bagel.png)
90
+
91
+ ## Model Description
92
+
93
+ This is a fine-tune of mistral-7b-v0.1, which underwent additional fine-tuning using direct preference optimization (DPO).
94
+
95
+ See [bagel](https://github.com/jondurbin/bagel) for additional details on the datasets.
96
+
97
+ The non-DPO version is available [here](https://huggingface.co/jondurbin/bagel-dpo-7b-v0.4), and is likely superior for roleplay.
98
+
99
+ Compute generously provided by [MassedCompute](https://massedcompute.com/?utm_source=huggingface&utm_creative_format=model_card&utm_content=creator_jon)
100
+
101
+ ## How to use
102
+
103
+ ### Install the necessary packages
104
+
105
+ ```bash
106
+ pip install --upgrade autoawq autoawq-kernels
107
+ ```
108
+
109
+ ### Example Python code
110
+
111
+ ```python
112
+ from awq import AutoAWQForCausalLM
113
+ from transformers import AutoTokenizer, TextStreamer
114
+
115
+ model_path = "solidrust/bagel-dpo-7b-v0.4-AWQ"
116
+ system_message = "You are Hermes, incarnated a powerful AI."
117
+
118
+ # Load model
119
+ model = AutoAWQForCausalLM.from_quantized(model_path,
120
+ fuse_layers=True)
121
+ tokenizer = AutoTokenizer.from_pretrained(model_path,
122
+ trust_remote_code=True)
123
+ streamer = TextStreamer(tokenizer,
124
+ skip_prompt=True,
125
+ skip_special_tokens=True)
126
+
127
+ # Convert prompt to tokens
128
+ prompt_template = """\
129
+ <|im_start|>system
130
+ {system_message}<|im_end|>
131
+ <|im_start|>user
132
+ {prompt}<|im_end|>
133
+ <|im_start|>assistant"""
134
+
135
+ prompt = "You're standing on the surface of the Earth. "\
136
+ "You walk one mile south, one mile west and one mile north. "\
137
+ "You end up exactly where you started. Where are you?"
138
+
139
+ tokens = tokenizer(prompt_template.format(system_message=system_message,prompt=prompt),
140
+ return_tensors='pt').input_ids.cuda()
141
+
142
+ # Generate output
143
+ generation_output = model.generate(tokens,
144
+ streamer=streamer,
145
+ max_new_tokens=512)
146
+ ```
147
+
148
+ ### About AWQ
149
+
150
+ AWQ is an efficient, accurate and blazing-fast low-bit weight quantization method, currently supporting 4-bit quantization. Compared to GPTQ, it offers faster Transformers-based inference with equivalent or better quality compared to the most commonly used GPTQ settings.
151
+
152
+ AWQ models are currently supported on Linux and Windows, with NVidia GPUs only. macOS users: please use GGUF models instead.
153
+
154
+ It is supported by:
155
+
156
+ - [Text Generation Webui](https://github.com/oobabooga/text-generation-webui) - using Loader: AutoAWQ
157
+ - [vLLM](https://github.com/vllm-project/vllm) - version 0.2.2 or later for support for all model types.
158
+ - [Hugging Face Text Generation Inference (TGI)](https://github.com/huggingface/text-generation-inference)
159
+ - [Transformers](https://huggingface.co/docs/transformers) version 4.35.0 and later, from any code or client that supports Transformers
160
+ - [AutoAWQ](https://github.com/casper-hansen/AutoAWQ) - for use from Python code
161
+
162
+ ## Prompt template: ChatML
163
+
164
+ ```plaintext
165
+ <|im_start|>system
166
+ {system_message}<|im_end|>
167
+ <|im_start|>user
168
+ {prompt}<|im_end|>
169
+ <|im_start|>assistant
170
+ ```
added_tokens.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32001,
3
+ "<|im_start|>": 32000,
4
+ "<|special_0|>": 32002,
5
+ "<|special_10|>": 32012,
6
+ "<|special_11|>": 32013,
7
+ "<|special_12|>": 32014,
8
+ "<|special_13|>": 32015,
9
+ "<|special_14|>": 32016,
10
+ "<|special_15|>": 32017,
11
+ "<|special_16|>": 32018,
12
+ "<|special_17|>": 32019,
13
+ "<|special_18|>": 32020,
14
+ "<|special_19|>": 32021,
15
+ "<|special_1|>": 32003,
16
+ "<|special_20|>": 32022,
17
+ "<|special_21|>": 32023,
18
+ "<|special_22|>": 32024,
19
+ "<|special_23|>": 32025,
20
+ "<|special_24|>": 32026,
21
+ "<|special_25|>": 32027,
22
+ "<|special_26|>": 32028,
23
+ "<|special_27|>": 32029,
24
+ "<|special_28|>": 32030,
25
+ "<|special_29|>": 32031,
26
+ "<|special_2|>": 32004,
27
+ "<|special_30|>": 32032,
28
+ "<|special_31|>": 32033,
29
+ "<|special_32|>": 32034,
30
+ "<|special_33|>": 32035,
31
+ "<|special_34|>": 32036,
32
+ "<|special_35|>": 32037,
33
+ "<|special_36|>": 32038,
34
+ "<|special_37|>": 32039,
35
+ "<|special_38|>": 32040,
36
+ "<|special_39|>": 32041,
37
+ "<|special_3|>": 32005,
38
+ "<|special_40|>": 32042,
39
+ "<|special_41|>": 32043,
40
+ "<|special_42|>": 32044,
41
+ "<|special_43|>": 32045,
42
+ "<|special_44|>": 32046,
43
+ "<|special_45|>": 32047,
44
+ "<|special_46|>": 32048,
45
+ "<|special_47|>": 32049,
46
+ "<|special_48|>": 32050,
47
+ "<|special_49|>": 32051,
48
+ "<|special_4|>": 32006,
49
+ "<|special_50|>": 32052,
50
+ "<|special_51|>": 32053,
51
+ "<|special_52|>": 32054,
52
+ "<|special_53|>": 32055,
53
+ "<|special_54|>": 32056,
54
+ "<|special_55|>": 32057,
55
+ "<|special_56|>": 32058,
56
+ "<|special_57|>": 32059,
57
+ "<|special_58|>": 32060,
58
+ "<|special_59|>": 32061,
59
+ "<|special_5|>": 32007,
60
+ "<|special_60|>": 32062,
61
+ "<|special_61|>": 32063,
62
+ "<|special_6|>": 32008,
63
+ "<|special_7|>": 32009,
64
+ "<|special_8|>": 32010,
65
+ "<|special_9|>": 32011
66
+ }
bagel.png ADDED

Git LFS Details

  • SHA256: 9d922a78a6f7d2de37f094d9eef558fd87dfc8e8df293c195aae27cb402b4160
  • Pointer size: 132 Bytes
  • Size of remote file: 2.15 MB
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/srv/home/shaun/.cache/huggingface/hub/models--jondurbin--bagel-dpo-7b-v0.4/snapshots/1407000b20cf38cf59d7a2d1143cb0883abe5ab3",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "quantization_config": {
19
+ "bits": 4,
20
+ "group_size": 128,
21
+ "modules_to_not_convert": null,
22
+ "quant_method": "awq",
23
+ "version": "gemm",
24
+ "zero_point": true
25
+ },
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_theta": 1000000.0,
28
+ "sliding_window": null,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "float16",
31
+ "transformers_version": "4.38.1",
32
+ "use_cache": false,
33
+ "vocab_size": 32064
34
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "do_sample": true,
5
+ "eos_token_id": 2,
6
+ "transformers_version": "4.38.1"
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|special_0|>",
6
+ "<|special_1|>",
7
+ "<|special_2|>",
8
+ "<|special_3|>",
9
+ "<|special_4|>",
10
+ "<|special_5|>",
11
+ "<|special_6|>",
12
+ "<|special_7|>",
13
+ "<|special_8|>",
14
+ "<|special_9|>",
15
+ "<|special_10|>",
16
+ "<|special_11|>",
17
+ "<|special_12|>",
18
+ "<|special_13|>",
19
+ "<|special_14|>",
20
+ "<|special_15|>",
21
+ "<|special_16|>",
22
+ "<|special_17|>",
23
+ "<|special_18|>",
24
+ "<|special_19|>",
25
+ "<|special_20|>",
26
+ "<|special_21|>",
27
+ "<|special_22|>",
28
+ "<|special_23|>",
29
+ "<|special_24|>",
30
+ "<|special_25|>",
31
+ "<|special_26|>",
32
+ "<|special_27|>",
33
+ "<|special_28|>",
34
+ "<|special_29|>",
35
+ "<|special_30|>",
36
+ "<|special_31|>",
37
+ "<|special_32|>",
38
+ "<|special_33|>",
39
+ "<|special_34|>",
40
+ "<|special_35|>",
41
+ "<|special_36|>",
42
+ "<|special_37|>",
43
+ "<|special_38|>",
44
+ "<|special_39|>",
45
+ "<|special_40|>",
46
+ "<|special_41|>",
47
+ "<|special_42|>",
48
+ "<|special_43|>",
49
+ "<|special_44|>",
50
+ "<|special_45|>",
51
+ "<|special_46|>",
52
+ "<|special_47|>",
53
+ "<|special_48|>",
54
+ "<|special_49|>",
55
+ "<|special_50|>",
56
+ "<|special_51|>",
57
+ "<|special_52|>",
58
+ "<|special_53|>",
59
+ "<|special_54|>",
60
+ "<|special_55|>",
61
+ "<|special_56|>",
62
+ "<|special_57|>",
63
+ "<|special_58|>",
64
+ "<|special_59|>",
65
+ "<|special_60|>",
66
+ "<|special_61|>"
67
+ ],
68
+ "bos_token": {
69
+ "content": "<s>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false
74
+ },
75
+ "eos_token": {
76
+ "content": "</s>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false
81
+ },
82
+ "pad_token": {
83
+ "content": "<unk>",
84
+ "lstrip": false,
85
+ "normalized": false,
86
+ "rstrip": false,
87
+ "single_word": false
88
+ },
89
+ "unk_token": {
90
+ "content": "<unk>",
91
+ "lstrip": false,
92
+ "normalized": false,
93
+ "rstrip": false,
94
+ "single_word": false
95
+ }
96
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,622 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": true,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "32000": {
31
+ "content": "<|im_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|im_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|special_0|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|special_1|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|special_2|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "32005": {
71
+ "content": "<|special_3|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "32006": {
79
+ "content": "<|special_4|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "32007": {
87
+ "content": "<|special_5|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "32008": {
95
+ "content": "<|special_6|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "32009": {
103
+ "content": "<|special_7|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "32010": {
111
+ "content": "<|special_8|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "32011": {
119
+ "content": "<|special_9|>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": true
125
+ },
126
+ "32012": {
127
+ "content": "<|special_10|>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": true
133
+ },
134
+ "32013": {
135
+ "content": "<|special_11|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": true
141
+ },
142
+ "32014": {
143
+ "content": "<|special_12|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": true
149
+ },
150
+ "32015": {
151
+ "content": "<|special_13|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": true
157
+ },
158
+ "32016": {
159
+ "content": "<|special_14|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": true
165
+ },
166
+ "32017": {
167
+ "content": "<|special_15|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": true
173
+ },
174
+ "32018": {
175
+ "content": "<|special_16|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": true
181
+ },
182
+ "32019": {
183
+ "content": "<|special_17|>",
184
+ "lstrip": false,
185
+ "normalized": false,
186
+ "rstrip": false,
187
+ "single_word": false,
188
+ "special": true
189
+ },
190
+ "32020": {
191
+ "content": "<|special_18|>",
192
+ "lstrip": false,
193
+ "normalized": false,
194
+ "rstrip": false,
195
+ "single_word": false,
196
+ "special": true
197
+ },
198
+ "32021": {
199
+ "content": "<|special_19|>",
200
+ "lstrip": false,
201
+ "normalized": false,
202
+ "rstrip": false,
203
+ "single_word": false,
204
+ "special": true
205
+ },
206
+ "32022": {
207
+ "content": "<|special_20|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false,
212
+ "special": true
213
+ },
214
+ "32023": {
215
+ "content": "<|special_21|>",
216
+ "lstrip": false,
217
+ "normalized": false,
218
+ "rstrip": false,
219
+ "single_word": false,
220
+ "special": true
221
+ },
222
+ "32024": {
223
+ "content": "<|special_22|>",
224
+ "lstrip": false,
225
+ "normalized": false,
226
+ "rstrip": false,
227
+ "single_word": false,
228
+ "special": true
229
+ },
230
+ "32025": {
231
+ "content": "<|special_23|>",
232
+ "lstrip": false,
233
+ "normalized": false,
234
+ "rstrip": false,
235
+ "single_word": false,
236
+ "special": true
237
+ },
238
+ "32026": {
239
+ "content": "<|special_24|>",
240
+ "lstrip": false,
241
+ "normalized": false,
242
+ "rstrip": false,
243
+ "single_word": false,
244
+ "special": true
245
+ },
246
+ "32027": {
247
+ "content": "<|special_25|>",
248
+ "lstrip": false,
249
+ "normalized": false,
250
+ "rstrip": false,
251
+ "single_word": false,
252
+ "special": true
253
+ },
254
+ "32028": {
255
+ "content": "<|special_26|>",
256
+ "lstrip": false,
257
+ "normalized": false,
258
+ "rstrip": false,
259
+ "single_word": false,
260
+ "special": true
261
+ },
262
+ "32029": {
263
+ "content": "<|special_27|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false,
268
+ "special": true
269
+ },
270
+ "32030": {
271
+ "content": "<|special_28|>",
272
+ "lstrip": false,
273
+ "normalized": false,
274
+ "rstrip": false,
275
+ "single_word": false,
276
+ "special": true
277
+ },
278
+ "32031": {
279
+ "content": "<|special_29|>",
280
+ "lstrip": false,
281
+ "normalized": false,
282
+ "rstrip": false,
283
+ "single_word": false,
284
+ "special": true
285
+ },
286
+ "32032": {
287
+ "content": "<|special_30|>",
288
+ "lstrip": false,
289
+ "normalized": false,
290
+ "rstrip": false,
291
+ "single_word": false,
292
+ "special": true
293
+ },
294
+ "32033": {
295
+ "content": "<|special_31|>",
296
+ "lstrip": false,
297
+ "normalized": false,
298
+ "rstrip": false,
299
+ "single_word": false,
300
+ "special": true
301
+ },
302
+ "32034": {
303
+ "content": "<|special_32|>",
304
+ "lstrip": false,
305
+ "normalized": false,
306
+ "rstrip": false,
307
+ "single_word": false,
308
+ "special": true
309
+ },
310
+ "32035": {
311
+ "content": "<|special_33|>",
312
+ "lstrip": false,
313
+ "normalized": false,
314
+ "rstrip": false,
315
+ "single_word": false,
316
+ "special": true
317
+ },
318
+ "32036": {
319
+ "content": "<|special_34|>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false,
324
+ "special": true
325
+ },
326
+ "32037": {
327
+ "content": "<|special_35|>",
328
+ "lstrip": false,
329
+ "normalized": false,
330
+ "rstrip": false,
331
+ "single_word": false,
332
+ "special": true
333
+ },
334
+ "32038": {
335
+ "content": "<|special_36|>",
336
+ "lstrip": false,
337
+ "normalized": false,
338
+ "rstrip": false,
339
+ "single_word": false,
340
+ "special": true
341
+ },
342
+ "32039": {
343
+ "content": "<|special_37|>",
344
+ "lstrip": false,
345
+ "normalized": false,
346
+ "rstrip": false,
347
+ "single_word": false,
348
+ "special": true
349
+ },
350
+ "32040": {
351
+ "content": "<|special_38|>",
352
+ "lstrip": false,
353
+ "normalized": false,
354
+ "rstrip": false,
355
+ "single_word": false,
356
+ "special": true
357
+ },
358
+ "32041": {
359
+ "content": "<|special_39|>",
360
+ "lstrip": false,
361
+ "normalized": false,
362
+ "rstrip": false,
363
+ "single_word": false,
364
+ "special": true
365
+ },
366
+ "32042": {
367
+ "content": "<|special_40|>",
368
+ "lstrip": false,
369
+ "normalized": false,
370
+ "rstrip": false,
371
+ "single_word": false,
372
+ "special": true
373
+ },
374
+ "32043": {
375
+ "content": "<|special_41|>",
376
+ "lstrip": false,
377
+ "normalized": false,
378
+ "rstrip": false,
379
+ "single_word": false,
380
+ "special": true
381
+ },
382
+ "32044": {
383
+ "content": "<|special_42|>",
384
+ "lstrip": false,
385
+ "normalized": false,
386
+ "rstrip": false,
387
+ "single_word": false,
388
+ "special": true
389
+ },
390
+ "32045": {
391
+ "content": "<|special_43|>",
392
+ "lstrip": false,
393
+ "normalized": false,
394
+ "rstrip": false,
395
+ "single_word": false,
396
+ "special": true
397
+ },
398
+ "32046": {
399
+ "content": "<|special_44|>",
400
+ "lstrip": false,
401
+ "normalized": false,
402
+ "rstrip": false,
403
+ "single_word": false,
404
+ "special": true
405
+ },
406
+ "32047": {
407
+ "content": "<|special_45|>",
408
+ "lstrip": false,
409
+ "normalized": false,
410
+ "rstrip": false,
411
+ "single_word": false,
412
+ "special": true
413
+ },
414
+ "32048": {
415
+ "content": "<|special_46|>",
416
+ "lstrip": false,
417
+ "normalized": false,
418
+ "rstrip": false,
419
+ "single_word": false,
420
+ "special": true
421
+ },
422
+ "32049": {
423
+ "content": "<|special_47|>",
424
+ "lstrip": false,
425
+ "normalized": false,
426
+ "rstrip": false,
427
+ "single_word": false,
428
+ "special": true
429
+ },
430
+ "32050": {
431
+ "content": "<|special_48|>",
432
+ "lstrip": false,
433
+ "normalized": false,
434
+ "rstrip": false,
435
+ "single_word": false,
436
+ "special": true
437
+ },
438
+ "32051": {
439
+ "content": "<|special_49|>",
440
+ "lstrip": false,
441
+ "normalized": false,
442
+ "rstrip": false,
443
+ "single_word": false,
444
+ "special": true
445
+ },
446
+ "32052": {
447
+ "content": "<|special_50|>",
448
+ "lstrip": false,
449
+ "normalized": false,
450
+ "rstrip": false,
451
+ "single_word": false,
452
+ "special": true
453
+ },
454
+ "32053": {
455
+ "content": "<|special_51|>",
456
+ "lstrip": false,
457
+ "normalized": false,
458
+ "rstrip": false,
459
+ "single_word": false,
460
+ "special": true
461
+ },
462
+ "32054": {
463
+ "content": "<|special_52|>",
464
+ "lstrip": false,
465
+ "normalized": false,
466
+ "rstrip": false,
467
+ "single_word": false,
468
+ "special": true
469
+ },
470
+ "32055": {
471
+ "content": "<|special_53|>",
472
+ "lstrip": false,
473
+ "normalized": false,
474
+ "rstrip": false,
475
+ "single_word": false,
476
+ "special": true
477
+ },
478
+ "32056": {
479
+ "content": "<|special_54|>",
480
+ "lstrip": false,
481
+ "normalized": false,
482
+ "rstrip": false,
483
+ "single_word": false,
484
+ "special": true
485
+ },
486
+ "32057": {
487
+ "content": "<|special_55|>",
488
+ "lstrip": false,
489
+ "normalized": false,
490
+ "rstrip": false,
491
+ "single_word": false,
492
+ "special": true
493
+ },
494
+ "32058": {
495
+ "content": "<|special_56|>",
496
+ "lstrip": false,
497
+ "normalized": false,
498
+ "rstrip": false,
499
+ "single_word": false,
500
+ "special": true
501
+ },
502
+ "32059": {
503
+ "content": "<|special_57|>",
504
+ "lstrip": false,
505
+ "normalized": false,
506
+ "rstrip": false,
507
+ "single_word": false,
508
+ "special": true
509
+ },
510
+ "32060": {
511
+ "content": "<|special_58|>",
512
+ "lstrip": false,
513
+ "normalized": false,
514
+ "rstrip": false,
515
+ "single_word": false,
516
+ "special": true
517
+ },
518
+ "32061": {
519
+ "content": "<|special_59|>",
520
+ "lstrip": false,
521
+ "normalized": false,
522
+ "rstrip": false,
523
+ "single_word": false,
524
+ "special": true
525
+ },
526
+ "32062": {
527
+ "content": "<|special_60|>",
528
+ "lstrip": false,
529
+ "normalized": false,
530
+ "rstrip": false,
531
+ "single_word": false,
532
+ "special": true
533
+ },
534
+ "32063": {
535
+ "content": "<|special_61|>",
536
+ "lstrip": false,
537
+ "normalized": false,
538
+ "rstrip": false,
539
+ "single_word": false,
540
+ "special": true
541
+ }
542
+ },
543
+ "additional_special_tokens": [
544
+ "<|im_start|>",
545
+ "<|im_end|>",
546
+ "<|special_0|>",
547
+ "<|special_1|>",
548
+ "<|special_2|>",
549
+ "<|special_3|>",
550
+ "<|special_4|>",
551
+ "<|special_5|>",
552
+ "<|special_6|>",
553
+ "<|special_7|>",
554
+ "<|special_8|>",
555
+ "<|special_9|>",
556
+ "<|special_10|>",
557
+ "<|special_11|>",
558
+ "<|special_12|>",
559
+ "<|special_13|>",
560
+ "<|special_14|>",
561
+ "<|special_15|>",
562
+ "<|special_16|>",
563
+ "<|special_17|>",
564
+ "<|special_18|>",
565
+ "<|special_19|>",
566
+ "<|special_20|>",
567
+ "<|special_21|>",
568
+ "<|special_22|>",
569
+ "<|special_23|>",
570
+ "<|special_24|>",
571
+ "<|special_25|>",
572
+ "<|special_26|>",
573
+ "<|special_27|>",
574
+ "<|special_28|>",
575
+ "<|special_29|>",
576
+ "<|special_30|>",
577
+ "<|special_31|>",
578
+ "<|special_32|>",
579
+ "<|special_33|>",
580
+ "<|special_34|>",
581
+ "<|special_35|>",
582
+ "<|special_36|>",
583
+ "<|special_37|>",
584
+ "<|special_38|>",
585
+ "<|special_39|>",
586
+ "<|special_40|>",
587
+ "<|special_41|>",
588
+ "<|special_42|>",
589
+ "<|special_43|>",
590
+ "<|special_44|>",
591
+ "<|special_45|>",
592
+ "<|special_46|>",
593
+ "<|special_47|>",
594
+ "<|special_48|>",
595
+ "<|special_49|>",
596
+ "<|special_50|>",
597
+ "<|special_51|>",
598
+ "<|special_52|>",
599
+ "<|special_53|>",
600
+ "<|special_54|>",
601
+ "<|special_55|>",
602
+ "<|special_56|>",
603
+ "<|special_57|>",
604
+ "<|special_58|>",
605
+ "<|special_59|>",
606
+ "<|special_60|>",
607
+ "<|special_61|>"
608
+ ],
609
+ "bos_token": "<s>",
610
+ "chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx == 0 -%}\n{{- bos_token + '[INST] <<SYS>>\\nYou are a helpful, unbiased, uncensored assistant.\\n<</SYS>>\\n\\n' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
611
+ "clean_up_tokenization_spaces": false,
612
+ "eos_token": "</s>",
613
+ "legacy": true,
614
+ "model_max_length": 1000000000000000019884624838656,
615
+ "pad_token": "<unk>",
616
+ "padding_side": "right",
617
+ "sp_model_kwargs": {},
618
+ "spaces_between_special_tokens": false,
619
+ "tokenizer_class": "LlamaTokenizer",
620
+ "unk_token": "<unk>",
621
+ "use_default_system_prompt": false
622
+ }