Upload folder using huggingface_hub
Browse files- README.md +258 -0
- config.json +50 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- special_tokens_map.json +35 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +49 -0
README.md
ADDED
@@ -0,0 +1,258 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: cc-by-nc-4.0
|
5 |
+
tags:
|
6 |
+
- merge
|
7 |
+
- lazymergekit
|
8 |
+
- dpo
|
9 |
+
- rlhf
|
10 |
+
- autoquant
|
11 |
+
- gptq
|
12 |
+
dataset:
|
13 |
+
- mlabonne/truthy-dpo-v0.1
|
14 |
+
- mlabonne/distilabel-intel-orca-dpo-pairs
|
15 |
+
- mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha
|
16 |
+
base_model:
|
17 |
+
- mlabonne/NeuralMonarch-7B
|
18 |
+
model-index:
|
19 |
+
- name: AlphaMonarch-7B
|
20 |
+
results:
|
21 |
+
- task:
|
22 |
+
type: text-generation
|
23 |
+
name: Text Generation
|
24 |
+
dataset:
|
25 |
+
name: AI2 Reasoning Challenge (25-Shot)
|
26 |
+
type: ai2_arc
|
27 |
+
config: ARC-Challenge
|
28 |
+
split: test
|
29 |
+
args:
|
30 |
+
num_few_shot: 25
|
31 |
+
metrics:
|
32 |
+
- type: acc_norm
|
33 |
+
value: 73.04
|
34 |
+
name: normalized accuracy
|
35 |
+
source:
|
36 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/AlphaMonarch-7B
|
37 |
+
name: Open LLM Leaderboard
|
38 |
+
- task:
|
39 |
+
type: text-generation
|
40 |
+
name: Text Generation
|
41 |
+
dataset:
|
42 |
+
name: HellaSwag (10-Shot)
|
43 |
+
type: hellaswag
|
44 |
+
split: validation
|
45 |
+
args:
|
46 |
+
num_few_shot: 10
|
47 |
+
metrics:
|
48 |
+
- type: acc_norm
|
49 |
+
value: 89.18
|
50 |
+
name: normalized accuracy
|
51 |
+
source:
|
52 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/AlphaMonarch-7B
|
53 |
+
name: Open LLM Leaderboard
|
54 |
+
- task:
|
55 |
+
type: text-generation
|
56 |
+
name: Text Generation
|
57 |
+
dataset:
|
58 |
+
name: MMLU (5-Shot)
|
59 |
+
type: cais/mmlu
|
60 |
+
config: all
|
61 |
+
split: test
|
62 |
+
args:
|
63 |
+
num_few_shot: 5
|
64 |
+
metrics:
|
65 |
+
- type: acc
|
66 |
+
value: 64.4
|
67 |
+
name: accuracy
|
68 |
+
source:
|
69 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/AlphaMonarch-7B
|
70 |
+
name: Open LLM Leaderboard
|
71 |
+
- task:
|
72 |
+
type: text-generation
|
73 |
+
name: Text Generation
|
74 |
+
dataset:
|
75 |
+
name: TruthfulQA (0-shot)
|
76 |
+
type: truthful_qa
|
77 |
+
config: multiple_choice
|
78 |
+
split: validation
|
79 |
+
args:
|
80 |
+
num_few_shot: 0
|
81 |
+
metrics:
|
82 |
+
- type: mc2
|
83 |
+
value: 77.91
|
84 |
+
source:
|
85 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/AlphaMonarch-7B
|
86 |
+
name: Open LLM Leaderboard
|
87 |
+
- task:
|
88 |
+
type: text-generation
|
89 |
+
name: Text Generation
|
90 |
+
dataset:
|
91 |
+
name: Winogrande (5-shot)
|
92 |
+
type: winogrande
|
93 |
+
config: winogrande_xl
|
94 |
+
split: validation
|
95 |
+
args:
|
96 |
+
num_few_shot: 5
|
97 |
+
metrics:
|
98 |
+
- type: acc
|
99 |
+
value: 84.69
|
100 |
+
name: accuracy
|
101 |
+
source:
|
102 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/AlphaMonarch-7B
|
103 |
+
name: Open LLM Leaderboard
|
104 |
+
- task:
|
105 |
+
type: text-generation
|
106 |
+
name: Text Generation
|
107 |
+
dataset:
|
108 |
+
name: GSM8k (5-shot)
|
109 |
+
type: gsm8k
|
110 |
+
config: main
|
111 |
+
split: test
|
112 |
+
args:
|
113 |
+
num_few_shot: 5
|
114 |
+
metrics:
|
115 |
+
- type: acc
|
116 |
+
value: 66.72
|
117 |
+
name: accuracy
|
118 |
+
source:
|
119 |
+
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlabonne/AlphaMonarch-7B
|
120 |
+
name: Open LLM Leaderboard
|
121 |
+
---
|
122 |
+
|
123 |
+
![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/TI7C8F2gk43gmI9U2L0uk.jpeg)
|
124 |
+
|
125 |
+
# 👑 AlphaMonarch-7B
|
126 |
+
|
127 |
+
**tl;dr: AlphaMonarch-7B is a new DPO merge that retains all the reasoning abilities of the very best merges and significantly improves its conversational abilities. Kind of the best of both worlds in a 7B model. 🎉**
|
128 |
+
|
129 |
+
AlphaMonarch-7B is a DPO fine-tuned of [mlabonne/NeuralMonarch-7B](https://huggingface.co/mlabonne/NeuralMonarch-7B/) using the [argilla/OpenHermes2.5-dpo-binarized-alpha](https://huggingface.co/datasets/argilla/OpenHermes2.5-dpo-binarized-alpha) preference dataset.
|
130 |
+
|
131 |
+
It is based on a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
132 |
+
* [mlabonne/OmniTruthyBeagle-7B-v0](https://huggingface.co/mlabonne/OmniTruthyBeagle-7B-v0)
|
133 |
+
* [mlabonne/NeuBeagle-7B](https://huggingface.co/mlabonne/NeuBeagle-7B)
|
134 |
+
* [mlabonne/NeuralOmniBeagle-7B](https://huggingface.co/mlabonne/NeuralOmniBeagle-7B)
|
135 |
+
|
136 |
+
Special thanks to [Jon Durbin](https://huggingface.co/jondurbin), [Intel](https://huggingface.co/Intel), [Argilla](https://huggingface.co/argilla), and [Teknium](https://huggingface.co/teknium) for the preference datasets.
|
137 |
+
|
138 |
+
**Try the demo**: https://huggingface.co/spaces/mlabonne/AlphaMonarch-7B-GGUF-Chat
|
139 |
+
|
140 |
+
## 🔍 Applications
|
141 |
+
|
142 |
+
This model uses a context window of 8k. I recommend using it with the Mistral Instruct chat template (works perfectly with LM Studio).
|
143 |
+
|
144 |
+
If you use SillyTavern, you might want to tweak the inference parameters. Here's what LM Studio uses as a reference: `temp` 0.8, `top_k` 40, `top_p` 0.95, `min_p` 0.05, `repeat_penalty` 1.1.
|
145 |
+
|
146 |
+
It is one of the very best 7B models in terms of instructing following and reasoning abilities and can be used for conversations, RP, and storytelling. Note that it tends to have a quite formal and sophisticated style, but it can be changed by modifying the prompt.
|
147 |
+
|
148 |
+
## ⚡ Quantized models
|
149 |
+
|
150 |
+
Thanks to [LoneStriker](https://huggingface.co/LoneStriker) for the GPTQ, AWQ, and EXL2 quants.
|
151 |
+
|
152 |
+
* **GGUF**: https://huggingface.co/mlabonne/AlphaMonarch-7B-GGUF
|
153 |
+
* **GPTQ**: https://huggingface.co/LoneStriker/AlphaMonarch-7B-GPTQ
|
154 |
+
* **AWQ**: https://huggingface.co/LoneStriker/AlphaMonarch-7B-AWQ
|
155 |
+
* **mlx**: https://huggingface.co/mlx-community/AlphaMonarch-7B-mlx
|
156 |
+
* **EXL2**:
|
157 |
+
* https://huggingface.co/LoneStriker/AlphaMonarch-7B-3.0bpw-h6-exl2
|
158 |
+
* https://huggingface.co/LoneStriker/AlphaMonarch-7B-4.0bpw-h6-exl2
|
159 |
+
* https://huggingface.co/LoneStriker/AlphaMonarch-7B-5.0bpw-h6-exl2
|
160 |
+
* https://huggingface.co/LoneStriker/AlphaMonarch-7B-6.0bpw-h6-exl2
|
161 |
+
* https://huggingface.co/LoneStriker/AlphaMonarch-7B-8.0bpw-h6-exl2
|
162 |
+
|
163 |
+
## 🏆 Evaluation
|
164 |
+
|
165 |
+
### Nous
|
166 |
+
|
167 |
+
AlphaMonarch-7B is the best-performing 7B model on Nous' benchmark suite (evaluation performed using [LLM AutoEval](https://github.com/mlabonne/llm-autoeval)). See the entire leaderboard [here](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard).
|
168 |
+
|
169 |
+
| Model | Average | AGIEval | GPT4All | TruthfulQA | Bigbench |
|
170 |
+
|---|---:|---:|---:|---:|---:|
|
171 |
+
| [**AlphaMonarch-7B**](https://huggingface.co/mlabonne/AlphaMonarch-7B) [📄](https://gist.github.com/mlabonne/1d33c86824b3a11d2308e36db1ba41c1) | **62.74** | **45.37** | **77.01** | **78.39** | **50.2** |
|
172 |
+
| [NeuralMonarch-7B](https://huggingface.co/mlabonne/NeuralMonarch-7B) [📄](https://gist.github.com/mlabonne/64050c96c6aa261a8f5b403190c8dee4) | 62.73 | 45.31 | 76.99 | 78.35 | 50.28 |
|
173 |
+
| [Monarch-7B](https://huggingface.co/mlabonne/Monarch-7B) [📄](https://gist.github.com/mlabonne/0b8d057c5ece41e0290580a108c7a093) | 62.68 | 45.48 | 77.07 | 78.04 | 50.14 |
|
174 |
+
| [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) [📄](https://gist.github.com/mlabonne/88b21dd9698ffed75d6163ebdc2f6cc8) | 52.42 | 42.75 | 72.99 | 52.99 | 40.94 |
|
175 |
+
| [mlabonne/NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B) [📄](https://gist.github.com/mlabonne/14687f1eb3425b166db511f31f8e66f6) | 53.51 | 43.67 | 73.24 | 55.37 | 41.76 |
|
176 |
+
| [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B) [📄](https://gist.github.com/mlabonne/ad0c665bbe581c8420136c3b52b3c15c) | 60.25 | 46.06 | 76.77 | 70.32 | 47.86 |
|
177 |
+
| [mlabonne/NeuralOmniBeagle-7B](https://huggingface.co/mlabonne/NeuralOmniBeagle-7B) [📄](https://gist.github.com/mlabonne/0e49d591787185fa5ae92ca5d9d4a1fd) | 62.3 | 45.85 | 77.26 | 76.06 | 50.03 |
|
178 |
+
| [eren23/dpo-binarized-NeuralTrix-7B](https://huggingface.co/eren23/dpo-binarized-NeuralTrix-7B) [📄](https://gist.github.com/CultriX-Github/dbdde67ead233df0c7c56f1b091f728c) | 62.5 | 44.57 | 76.34 | 79.81 | 49.27 |
|
179 |
+
| [CultriX/NeuralTrix-7B-dpo](https://huggingface.co/CultriX/NeuralTrix-7B-dpo) [📄](https://gist.github.com/CultriX-Github/df0502599867d4043b45d9dafb5976e8) | 62.5 | 44.61 | 76.33 | 79.8 | 49.24 |
|
180 |
+
|
181 |
+
### EQ-bench
|
182 |
+
|
183 |
+
AlphaMonarch-7B is also outperforming 70B and 120B parameter models on [EQ-bench](https://eqbench.com/) by [Samuel J. Paech](https://twitter.com/sam_paech), who kindly ran the evaluations.
|
184 |
+
|
185 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/dnCFxieqLiAC3Ll6CfdZW.png)
|
186 |
+
|
187 |
+
### MT-Bench
|
188 |
+
|
189 |
+
```
|
190 |
+
########## First turn ##########
|
191 |
+
score
|
192 |
+
model turn
|
193 |
+
gpt-4 1 8.95625
|
194 |
+
OmniBeagle-7B 1 8.31250
|
195 |
+
AlphaMonarch-7B 1 8.23750
|
196 |
+
claude-v1 1 8.15000
|
197 |
+
NeuralMonarch-7B 1 8.09375
|
198 |
+
gpt-3.5-turbo 1 8.07500
|
199 |
+
claude-instant-v1 1 7.80000
|
200 |
+
|
201 |
+
########## Second turn ##########
|
202 |
+
score
|
203 |
+
model turn
|
204 |
+
gpt-4 2 9.025000
|
205 |
+
claude-instant-v1 2 8.012658
|
206 |
+
OmniBeagle-7B 2 7.837500
|
207 |
+
gpt-3.5-turbo 2 7.812500
|
208 |
+
claude-v1 2 7.650000
|
209 |
+
AlphaMonarch-7B 2 7.618750
|
210 |
+
NeuralMonarch-7B 2 7.375000
|
211 |
+
|
212 |
+
########## Average ##########
|
213 |
+
score
|
214 |
+
model
|
215 |
+
gpt-4 8.990625
|
216 |
+
OmniBeagle-7B 8.075000
|
217 |
+
gpt-3.5-turbo 7.943750
|
218 |
+
AlphaMonarch-7B 7.928125
|
219 |
+
claude-instant-v1 7.905660
|
220 |
+
claude-v1 7.900000
|
221 |
+
NeuralMonarch-7B 7.734375
|
222 |
+
NeuralBeagle14-7B 7.628125
|
223 |
+
```
|
224 |
+
|
225 |
+
### Open LLM Leaderboard
|
226 |
+
|
227 |
+
AlphaMonarch-7B is one of the best-performing non-merge 7B models on the Open LLM Leaderboard:
|
228 |
+
|
229 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/njHxX_ERQaBssHqp17fMy.png)
|
230 |
+
|
231 |
+
## 🌳 Model Family Tree
|
232 |
+
|
233 |
+
![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/IMAE6DpzkUN6YaEhOX2wA.png)
|
234 |
+
|
235 |
+
## 💻 Usage
|
236 |
+
|
237 |
+
```python
|
238 |
+
!pip install -qU transformers accelerate
|
239 |
+
|
240 |
+
from transformers import AutoTokenizer
|
241 |
+
import transformers
|
242 |
+
import torch
|
243 |
+
|
244 |
+
model = "mlabonne/AlphaMonarch-7B"
|
245 |
+
messages = [{"role": "user", "content": "What is a large language model?"}]
|
246 |
+
|
247 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
248 |
+
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
249 |
+
pipeline = transformers.pipeline(
|
250 |
+
"text-generation",
|
251 |
+
model=model,
|
252 |
+
torch_dtype=torch.float16,
|
253 |
+
device_map="auto",
|
254 |
+
)
|
255 |
+
|
256 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
257 |
+
print(outputs[0]["generated_text"])
|
258 |
+
```
|
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mlabonne/AlphaMonarch-7B",
|
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 |
+
"batch_size": 1,
|
20 |
+
"bits": 4,
|
21 |
+
"block_name_to_quantize": null,
|
22 |
+
"cache_block_outputs": true,
|
23 |
+
"damp_percent": 0.1,
|
24 |
+
"dataset": "c4",
|
25 |
+
"desc_act": false,
|
26 |
+
"exllama_config": {
|
27 |
+
"version": 1
|
28 |
+
},
|
29 |
+
"group_size": 128,
|
30 |
+
"max_input_length": null,
|
31 |
+
"model_seqlen": null,
|
32 |
+
"module_name_preceding_first_block": null,
|
33 |
+
"modules_in_block_to_quantize": null,
|
34 |
+
"pad_token_id": null,
|
35 |
+
"quant_method": "gptq",
|
36 |
+
"sym": true,
|
37 |
+
"tokenizer": null,
|
38 |
+
"true_sequential": true,
|
39 |
+
"use_cuda_fp16": false,
|
40 |
+
"use_exllama": true
|
41 |
+
},
|
42 |
+
"rms_norm_eps": 1e-05,
|
43 |
+
"rope_theta": 10000.0,
|
44 |
+
"sliding_window": 4096,
|
45 |
+
"tie_word_embeddings": false,
|
46 |
+
"torch_dtype": "float16",
|
47 |
+
"transformers_version": "4.38.2",
|
48 |
+
"use_cache": true,
|
49 |
+
"vocab_size": 32000
|
50 |
+
}
|
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": "4.38.2"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c3b38dd11a9b2abf3c251ec87f75fb27a178a5629827d2e6e7eba708fe06d6f
|
3 |
+
size 4158662096
|
special_tokens_map.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"unk_token": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
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 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<unk>",
|
32 |
+
"<s>",
|
33 |
+
"</s>"
|
34 |
+
],
|
35 |
+
"bos_token": "<s>",
|
36 |
+
"chat_template": "{% for message in messages %}{{bos_token + message['role'] + '\n' + message['content'] + eos_token + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ bos_token + 'assistant\n' }}{% endif %}",
|
37 |
+
"clean_up_tokenization_spaces": false,
|
38 |
+
"eos_token": "</s>",
|
39 |
+
"legacy": true,
|
40 |
+
"model_max_length": 8192,
|
41 |
+
"pad_token": "</s>",
|
42 |
+
"padding_side": "left",
|
43 |
+
"sp_model_kwargs": {},
|
44 |
+
"spaces_between_special_tokens": false,
|
45 |
+
"split_special_tokens": false,
|
46 |
+
"tokenizer_class": "LlamaTokenizer",
|
47 |
+
"unk_token": "<unk>",
|
48 |
+
"use_default_system_prompt": true
|
49 |
+
}
|