Hugging Face's logo

Visdom9
/
Norah

Text Generation
Transformers
Safetensors
French
English
mistral
conversational
Eval Results
text-generation-inference
Model card Files
xet
Community
root commited on
Commit
db82ee8
·
0 Parent(s):

Uploading TinyMistral-248M-v3 to HF

Browse files
Files changed (8) hide show
  1. .gitattributes +35 -0
  2. README.md +244 -0
  3. config.json +27 -0
  4. generation_config.json +6 -0
  5. model.safetensors +3 -0
  6. special_tokens_map.json +34 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +91 -0
.gitattributes ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
README.md ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - en
4
+ license: apache-2.0
5
+ datasets:
6
+ - Locutusque/TM-DATA-V2
7
+ - LLM360/TxT360
8
+ - mlfoundations/dclm-baseline-1.0
9
+ - Skylion007/openwebtext
10
+ - JeanKaddour/minipile
11
+ - eminorhan/gutenberg_en
12
+ model-index:
13
+ - name: TinyMistral-248M-v3
14
+ results:
15
+ - task:
16
+ type: text-generation
17
+ name: Text Generation
18
+ dataset:
19
+ name: IFEval (0-Shot)
20
+ type: HuggingFaceH4/ifeval
21
+ args:
22
+ num_few_shot: 0
23
+ metrics:
24
+ - type: inst_level_strict_acc and prompt_level_strict_acc
25
+ value: 16.39
26
+ name: strict accuracy
27
+ source:
28
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=M4-ai/TinyMistral-248M-v3
29
+ name: Open LLM Leaderboard
30
+ - task:
31
+ type: text-generation
32
+ name: Text Generation
33
+ dataset:
34
+ name: BBH (3-Shot)
35
+ type: BBH
36
+ args:
37
+ num_few_shot: 3
38
+ metrics:
39
+ - type: acc_norm
40
+ value: 1.78
41
+ name: normalized accuracy
42
+ source:
43
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=M4-ai/TinyMistral-248M-v3
44
+ name: Open LLM Leaderboard
45
+ - task:
46
+ type: text-generation
47
+ name: Text Generation
48
+ dataset:
49
+ name: MATH Lvl 5 (4-Shot)
50
+ type: hendrycks/competition_math
51
+ args:
52
+ num_few_shot: 4
53
+ metrics:
54
+ - type: exact_match
55
+ value: 0.0
56
+ name: exact match
57
+ source:
58
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=M4-ai/TinyMistral-248M-v3
59
+ name: Open LLM Leaderboard
60
+ - task:
61
+ type: text-generation
62
+ name: Text Generation
63
+ dataset:
64
+ name: GPQA (0-shot)
65
+ type: Idavidrein/gpqa
66
+ args:
67
+ num_few_shot: 0
68
+ metrics:
69
+ - type: acc_norm
70
+ value: 0.0
71
+ name: acc_norm
72
+ source:
73
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=M4-ai/TinyMistral-248M-v3
74
+ name: Open LLM Leaderboard
75
+ - task:
76
+ type: text-generation
77
+ name: Text Generation
78
+ dataset:
79
+ name: MuSR (0-shot)
80
+ type: TAUR-Lab/MuSR
81
+ args:
82
+ num_few_shot: 0
83
+ metrics:
84
+ - type: acc_norm
85
+ value: 5.15
86
+ name: acc_norm
87
+ source:
88
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=M4-ai/TinyMistral-248M-v3
89
+ name: Open LLM Leaderboard
90
+ - task:
91
+ type: text-generation
92
+ name: Text Generation
93
+ dataset:
94
+ name: MMLU-PRO (5-shot)
95
+ type: TIGER-Lab/MMLU-Pro
96
+ config: main
97
+ split: test
98
+ args:
99
+ num_few_shot: 5
100
+ metrics:
101
+ - type: acc
102
+ value: 1.47
103
+ name: accuracy
104
+ source:
105
+ url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=M4-ai/TinyMistral-248M-v3
106
+ name: Open LLM Leaderboard
107
+ ---
108
+
109
+ still in training. Trained on about ~21 billion tokens so far.
110
+
111
+ | Tasks |Version| Filter |n-shot| Metric | | Value | |Stderr|
112
+ |----------------------------------------|-------|----------------|-----:|-----------|---|------:|---|-----:|
113
+ |Open LLM Leaderboard | N/A| | | | | | | |
114
+ | - arc_challenge | 1|none | 25|acc |↑ | 0.2005|± |0.0117|
115
+ | | |none | 25|acc_norm |↑ | 0.2406|± |0.0125|
116
+ | - gsm8k | 3|flexible-extract| 5|exact_match|↑ | 0.0083|± |0.0025|
117
+ | | |strict-match | 5|exact_match|↑ | 0.0000|± |0.0000|
118
+ | - hellaswag | 1|none | 10|acc |↑ | 0.2724|± |0.0044|
119
+ | | |none | 10|acc_norm |↑ | 0.2838|± |0.0045|
120
+ | - mmlu | 2|none | |acc |↑ | 0.2290|± |0.0035|
121
+ | - humanities | 2|none | |acc |↑ | 0.2380|± |0.0062|
122
+ | - formal_logic | 1|none | 5|acc |↑ | 0.2460|± |0.0385|
123
+ | - high_school_european_history | 1|none | 5|acc |↑ | 0.1818|± |0.0301|
124
+ | - high_school_us_history | 1|none | 5|acc |↑ | 0.2647|± |0.0310|
125
+ | - high_school_world_history | 1|none | 5|acc |↑ | 0.2911|± |0.0296|
126
+ | - international_law | 1|none | 5|acc |↑ | 0.2149|± |0.0375|
127
+ | - jurisprudence | 1|none | 5|acc |↑ | 0.2685|± |0.0428|
128
+ | - logical_fallacies | 1|none | 5|acc |↑ | 0.2209|± |0.0326|
129
+ | - moral_disputes | 1|none | 5|acc |↑ | 0.2457|± |0.0232|
130
+ | - moral_scenarios | 1|none | 5|acc |↑ | 0.2369|± |0.0142|
131
+ | - philosophy | 1|none | 5|acc |↑ | 0.1865|± |0.0221|
132
+ | - prehistory | 1|none | 5|acc |↑ | 0.1975|± |0.0222|
133
+ | - professional_law | 1|none | 5|acc |↑ | 0.2432|± |0.0110|
134
+ | - world_religions | 1|none | 5|acc |↑ | 0.3099|± |0.0355|
135
+ | - other | 2|none | |acc |↑ | 0.2375|± |0.0076|
136
+ | - business_ethics | 1|none | 5|acc |↑ | 0.3200|± |0.0469|
137
+ | - clinical_knowledge | 1|none | 5|acc |↑ | 0.2226|± |0.0256|
138
+ | - college_medicine | 1|none | 5|acc |↑ | 0.1965|± |0.0303|
139
+ | - global_facts | 1|none | 5|acc |↑ | 0.1800|± |0.0386|
140
+ | - human_aging | 1|none | 5|acc |↑ | 0.3004|± |0.0308|
141
+ | - management | 1|none | 5|acc |↑ | 0.1942|± |0.0392|
142
+ | - marketing | 1|none | 5|acc |↑ | 0.2735|± |0.0292|
143
+ | - medical_genetics | 1|none | 5|acc |↑ | 0.3000|± |0.0461|
144
+ | - miscellaneous | 1|none | 5|acc |↑ | 0.2478|± |0.0154|
145
+ | - nutrition | 1|none | 5|acc |↑ | 0.2222|± |0.0238|
146
+ | - professional_accounting | 1|none | 5|acc |↑ | 0.2021|± |0.0240|
147
+ | - professional_medicine | 1|none | 5|acc |↑ | 0.1912|± |0.0239|
148
+ | - virology | 1|none | 5|acc |↑ | 0.2590|± |0.0341|
149
+ | - social sciences | 2|none | |acc |↑ | 0.2203|± |0.0075|
150
+ | - econometrics | 1|none | 5|acc |↑ | 0.2368|± |0.0400|
151
+ | - high_school_geography | 1|none | 5|acc |↑ | 0.2020|± |0.0286|
152
+ | - high_school_government_and_politics| 1|none | 5|acc |↑ | 0.1865|± |0.0281|
153
+ | - high_school_macroeconomics | 1|none | 5|acc |↑ | 0.2205|± |0.0210|
154
+ | - high_school_microeconomics | 1|none | 5|acc |↑ | 0.2143|± |0.0267|
155
+ | - high_school_psychology | 1|none | 5|acc |↑ | 0.1908|± |0.0168|
156
+ | - human_sexuality | 1|none | 5|acc |↑ | 0.2672|± |0.0388|
157
+ | - professional_psychology | 1|none | 5|acc |↑ | 0.2386|± |0.0172|
158
+ | - public_relations | 1|none | 5|acc |↑ | 0.1727|± |0.0362|
159
+ | - security_studies | 1|none | 5|acc |↑ | 0.2367|± |0.0272|
160
+ | - sociology | 1|none | 5|acc |↑ | 0.2488|± |0.0306|
161
+ | - us_foreign_policy | 1|none | 5|acc |↑ | 0.2600|± |0.0441|
162
+ | - stem | 2|none | |acc |↑ | 0.2157|± |0.0073|
163
+ | - abstract_algebra | 1|none | 5|acc |↑ | 0.2200|± |0.0416|
164
+ | - anatomy | 1|none | 5|acc |↑ | 0.1778|± |0.0330|
165
+ | - astronomy | 1|none | 5|acc |↑ | 0.1908|± |0.0320|
166
+ | - college_biology | 1|none | 5|acc |↑ | 0.2778|± |0.0375|
167
+ | - college_chemistry | 1|none | 5|acc |↑ | 0.2200|± |0.0416|
168
+ | - college_computer_science | 1|none | 5|acc |↑ | 0.2100|± |0.0409|
169
+ | - college_mathematics | 1|none | 5|acc |↑ | 0.2100|± |0.0409|
170
+ | - college_physics | 1|none | 5|acc |↑ | 0.2157|± |0.0409|
171
+ | - computer_security | 1|none | 5|acc |↑ | 0.2700|± |0.0446|
172
+ | - conceptual_physics | 1|none | 5|acc |↑ | 0.2638|± |0.0288|
173
+ | - electrical_engineering | 1|none | 5|acc |↑ | 0.2483|± |0.0360|
174
+ | - elementary_mathematics | 1|none | 5|acc |↑ | 0.2037|± |0.0207|
175
+ | - high_school_biology | 1|none | 5|acc |↑ | 0.1774|± |0.0217|
176
+ | - high_school_chemistry | 1|none | 5|acc |↑ | 0.2020|± |0.0282|
177
+ | - high_school_computer_science | 1|none | 5|acc |↑ | 0.2500|± |0.0435|
178
+ | - high_school_mathematics | 1|none | 5|acc |↑ | 0.2148|± |0.0250|
179
+ | - high_school_physics | 1|none | 5|acc |↑ | 0.2053|± |0.0330|
180
+ | - high_school_statistics | 1|none | 5|acc |↑ | 0.1481|± |0.0242|
181
+ | - machine_learning | 1|none | 5|acc |↑ | 0.3125|± |0.0440|
182
+ | - truthfulqa_gen | 3|none | 0|bleu_acc |↑ | 0.2362|± |0.0149|
183
+ | | |none | 0|bleu_diff |↑ |-1.0138|± |0.2569|
184
+ | | |none | 0|bleu_max |↑ | 7.9522|± |0.4088|
185
+ | | |none | 0|rouge1_acc |↑ | 0.2595|± |0.0153|
186
+ | | |none | 0|rouge1_diff|↑ |-1.9129|± |0.4349|
187
+ | | |none | 0|rouge1_max |↑ |21.7885|± |0.7307|
188
+ | | |none | 0|rouge2_acc |↑ | 0.1200|± |0.0114|
189
+ | | |none | 0|rouge2_diff|↑ |-1.9771|± |0.3475|
190
+ | | |none | 0|rouge2_max |↑ | 9.0199|± |0.5842|
191
+ | | |none | 0|rougeL_acc |↑ | 0.2570|± |0.0153|
192
+ | | |none | 0|rougeL_diff|↑ |-1.8812|± |0.4185|
193
+ | | |none | 0|rougeL_max |↑ |19.6284|± |0.6850|
194
+ | - truthfulqa_mc1 | 2|none | 0|acc |↑ | 0.1983|± |0.0140|
195
+ | - truthfulqa_mc2 | 2|none | 0|acc |↑ | 0.3861|± |0.0147|
196
+ | - winogrande | 1|none | 5|acc |↑ | 0.4972|± |0.0141|
197
+
198
+ | Groups |Version|Filter|n-shot|Metric| |Value | |Stderr|
199
+ |-------------------|------:|------|------|------|---|-----:|---|-----:|
200
+ | - mmlu | 2|none | |acc |↑ |0.2290|± |0.0035|
201
+ | - humanities | 2|none | |acc |↑ |0.2380|± |0.0062|
202
+ | - other | 2|none | |acc |↑ |0.2375|± |0.0076|
203
+ | - social sciences| 2|none | |acc |↑ |0.2203|± |0.0075|
204
+ | - stem | 2|none | |acc |↑ |0.2157|± |0.0073|
205
+
206
+ | Tasks |Version|Filter|n-shot| Metric | |Value | |Stderr|
207
+ |---------------------------------|------:|------|-----:|--------|---|-----:|---|-----:|
208
+ |agieval_nous | 0|none | |acc_norm|↑ |0.2133|± |0.0081|
209
+ | - agieval_aqua_rat | 1|none | 0|acc |↑ |0.2047|± |0.0254|
210
+ | | |none | 0|acc_norm|↑ |0.1969|± |0.0250|
211
+ | - agieval_logiqa_en | 1|none | 0|acc |↑ |0.2043|± |0.0158|
212
+ | | |none | 0|acc_norm|↑ |0.2304|± |0.0165|
213
+ | - agieval_lsat_ar | 1|none | 0|acc |↑ |0.1739|± |0.0250|
214
+ | | |none | 0|acc_norm|↑ |0.1957|± |0.0262|
215
+ | - agieval_lsat_lr | 1|none | 0|acc |↑ |0.1549|± |0.0160|
216
+ | | |none | 0|acc_norm|↑ |0.1608|± |0.0163|
217
+ | - agieval_lsat_rc | 1|none | 0|acc |↑ |0.1636|± |0.0226|
218
+ | | |none | 0|acc_norm|↑ |0.2119|± |0.0250|
219
+ | - agieval_sat_en | 1|none | 0|acc |↑ |0.2670|± |0.0309|
220
+ | | |none | 0|acc_norm|↑ |0.2621|± |0.0307|
221
+ | - agieval_sat_en_without_passage| 1|none | 0|acc |↑ |0.2670|± |0.0309|
222
+ | | |none | 0|acc_norm|↑ |0.2621|± |0.0307|
223
+ | - agieval_sat_math | 1|none | 0|acc |↑ |0.2182|± |0.0279|
224
+ | | |none | 0|acc_norm|↑ |0.2318|± |0.0285|
225
+ |arc_challenge | 1|none | 0|acc |↑ |0.1945|± |0.0116|
226
+ | | |none | 0|acc_norm|↑ |0.2372|± |0.0124|
227
+ |truthfulqa_mc2 | 2|none | 0|acc |↑ |0.3861|± |0.0147|
228
+
229
+ | Groups |Version|Filter|n-shot| Metric | |Value | |Stderr|
230
+ |------------|------:|------|------|--------|---|-----:|---|-----:|
231
+ |agieval_nous| 0|none | |acc_norm|↑ |0.2133|± |0.0081|
232
+ # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
233
+ Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_M4-ai__TinyMistral-248M-v3)
234
+
235
+ | Metric |Value|
236
+ |-------------------|----:|
237
+ |Avg. | 4.13|
238
+ |IFEval (0-Shot) |16.39|
239
+ |BBH (3-Shot) | 1.78|
240
+ |MATH Lvl 5 (4-Shot)| 0.00|
241
+ |GPQA (0-shot) | 0.00|
242
+ |MuSR (0-shot) | 5.15|
243
+ |MMLU-PRO (5-shot) | 1.47|
244
+
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "M4-ai/TinyMistral-248M-v3",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 32,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "max_position_embeddings": 32768,
15
+ "model_type": "mistral",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 12,
18
+ "num_key_value_heads": 8,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_theta": 10000.0,
21
+ "sliding_window": 32,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.45.2",
25
+ "use_cache": true,
26
+ "vocab_size": 32005
27
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.45.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9432ee6e0681473a9ed513e43362d9911832f9a5c7faded76f46ec66c55a9d3b
3
+ size 496060688
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|ASSISTANT|>",
4
+ "<|USER|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|bos|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "[PAD]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
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": "<|bos|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<|endoftext|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "[PAD]",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|ASSISTANT|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|USER|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ }
70
+ },
71
+ "additional_special_tokens": [
72
+ "<|ASSISTANT|>",
73
+ "<|USER|>"
74
+ ],
75
+ "bos_token": "<|bos|>",
76
+ "chat_template": "{%- set ns = namespace(found=false) -%}{%- for message in messages -%}{%- if message['role'] == 'system' -%}{%- set ns.found = true -%}{%- endif -%}{%- endfor -%}{%- for message in messages %}{%- if message['role'] == 'system' -%}{{- '<|im_start|>system\n' + message['content'].rstrip() + '<|im_end|>\n' -}}{%- else -%}{%- if message['role'] == 'user' -%}{{-'<|im_start|>user\n' + message['content'].rstrip() + '<|im_end|>\n'-}}{%- else -%}{{-'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' -}}{%- endif -%}{%- endif -%}{%- endfor -%}{%- if add_generation_prompt -%}{{-'<|im_start|>assistant\n'-}}{%- endif -%}",
77
+ "clean_up_tokenization_spaces": false,
78
+ "eos_token": "<|endoftext|>",
79
+ "legacy": true,
80
+ "max_length": 1536,
81
+ "model_max_length": 1000000000000000019884624838656,
82
+ "pad_token": "[PAD]",
83
+ "sp_model_kwargs": {},
84
+ "spaces_between_special_tokens": false,
85
+ "stride": 0,
86
+ "tokenizer_class": "LlamaTokenizer",
87
+ "truncation_side": "right",
88
+ "truncation_strategy": "longest_first",
89
+ "unk_token": "<unk>",
90
+ "use_default_system_prompt": true
91
+ }