Hugging Face's logo

baichuan-inc
/
Baichuan-7B

Text Generation
Transformers
PyTorch
Chinese
English
baichuan
custom_code
text-generation-inference
Inference Endpoints
Model card Files Community
29
GradientGuru commited on
Commit
046f944
·
1 Parent(s): c87a927

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +30 -31
README.md CHANGED
@@ -145,15 +145,15 @@ For specific training settings, please refer to [baichuan-7B](https://github.com
145
  | Claude-v1.3 | 54.2 | 39.0 | 51.9 | 61.7 | 52.1 | 53.7 |
146
  | Claude-instant-v1.0 | 45.9 | 35.5 | 43.1 | 53.8 | 44.2 | 45.4 |
147
  | moss-moon-003-base (16b) | 27.4 | 24.5 | 27.0 | 29.1 | 27.2 | 26.9 |
148
- | Ziya-LLaMA-13B-Pretrain | 30.2 | 22.7 | 27.7 | 34.4 | 32.0 | 28.9 |
149
- | llama-7b-hf | 27.1 | 25.9 | 27.1 | 26.8 | 27.9 | 26.3 |
150
- | chatGLM-6b | 34.5 | 23.1 | 30.4 | 39.6 | 37.4 | 34.5 |
151
- | falcon-7b | 25.8 | 24.3 | 25.8 | 26.0 | 25.8 | 25.6 |
152
- | Open-Llama-V2-pretrain (7b) | 24.0 | 22.5 | 23.1 | 25.3 | 25.2 | 23.2 |
153
- | tigerbot-7b-base | 25.7 | 27.0 | 27.3 | 24.7 | 23.4 | 26.1 |
154
  | Aquila-7b<sup>*</sup> | 25.5 | 25.2 | 25.6 | 24.6 | 25.2 | 26.6 |
155
- | bloom-7b | 22.8 | 20.2 | 21.8 | 23.3 | 23.9 | 23.3 |
156
- | bloomz-7b | 35.7 | 25.8 | 31.3 | 43.5 | 36.6 | 35.6 |
157
  | **baichuan-7B** | 42.8 | 31.5 | 38.2 | 52.0 | 46.2 | 39.3 |
158
 
159
 
@@ -165,15 +165,15 @@ For specific training settings, please refer to [baichuan-7B](https://github.com
165
 
166
  | Model | Average |
167
  |-------------------------|-----------------|
168
- | Open-Llama-V2-pretrain | 21.41 |
169
- | Ziya-LLaMA-13B-Pretrain | 23.17 |
170
- | falcon-7b | 23.98 |
171
- | tigerbot-7b-base | 25.94 |
172
- | LLAMA-7B | 27.81 |
173
- | chatGLM-6b | 21.41 |
174
- | bloom-7b | 26.96 |
175
- | bloomz-7b | 28.72 |
176
- | Aquila-7b<sup>*</sup> | 24.39 |
177
  | **baichuan-7B** | **36.24** |
178
 
179
 
@@ -183,15 +183,15 @@ For specific training settings, please refer to [baichuan-7B](https://github.com
183
 
184
  | Model | Average |
185
  |-------------------------|-----------------|
186
- | Open-Llama-V2-pretrain | 23.49 |
187
- | Ziya-LLaMA-13B-Pretrain | 27.64 |
188
- | falcon-7b | 27.18 |
189
- | tigerbot-7b-base | 25.19 |
190
- | LLAMA-7B | 28.17 |
191
- | chatGLM-6b | 23.49 |
192
- | bloom-7b | 26.55 |
193
- | bloomz-7b | 30.27 |
194
- | Aquila-7b<sup>*</sup> | 25.58 |
195
  | **baichuan-7B** | **34.44** |
196
 
197
  <sup>*</sup>其中Aquila模型来源于[智源官方网站](https://model.baai.ac.cn/model-detail/100098)，仅做参考
@@ -208,12 +208,11 @@ We adopted the [open-source]((https://github.com/hendrycks/test)) evaluation sch
208
  | Model | Humanities | Social Sciences | STEM | Other | Average |
209
  |----------------------------------------|-----------:|:---------------:|:----:|:-----:|:-------:|
210
  | LLaMA-7B<sup>2</sup> | 34.0 | 38.3 | 30.5 | 38.1 | 35.1 |
211
- | falcon-7B<sup>1</sup> | - | - | - | - | 35.0 |
212
  | mpt-7B<sup>1</sup> | - | - | - | - | 35.6 |
213
- | chatGLM-6B<sup>0</sup> | 35.4 | 41.0 | 31.3 | 40.5 | 36.9 |
214
- | BLOOM 176B<sup>2</sup> | 34.1 | 41.5 | 36.8 | 46.5 | 39.1 |
215
- | BLOOM 7B1<sup>0</sup> | 25.0 | 24.4 | 26.5 | 26.4 | 25.5 |
216
- | BLOOMZ 7B1<sup>0</sup> | 31.3 | 42.1 | 34.4 | 39.0 | 36.1 |
217
  | moss-moon-003-base (16B)<sup>0</sup> | 24.2 | 22.8 | 22.4 | 24.4 | 23.6 |
218
  | moss-moon-003-sft (16B)<sup>0</sup> | 30.5 | 33.8 | 29.3 | 34.4 | 31.9 |
219
  | **baichuan-7B<sup>0</sup>** | 38.4 | 48.9 | 35.6 | 48.1 | 42.3 |
 
145
  | Claude-v1.3 | 54.2 | 39.0 | 51.9 | 61.7 | 52.1 | 53.7 |
146
  | Claude-instant-v1.0 | 45.9 | 35.5 | 43.1 | 53.8 | 44.2 | 45.4 |
147
  | moss-moon-003-base (16b) | 27.4 | 24.5 | 27.0 | 29.1 | 27.2 | 26.9 |
148
+ | Ziya-LLaMA-13B-pretrain | 30.2 | 22.7 | 27.7 | 34.4 | 32.0 | 28.9 |
149
+ | LLaMA-7B-hf | 27.1 | 25.9 | 27.1 | 26.8 | 27.9 | 26.3 |
150
+ | ChatGLM-6B | 34.5 | 23.1 | 30.4 | 39.6 | 37.4 | 34.5 |
151
+ | Falcon-7B | 25.8 | 24.3 | 25.8 | 26.0 | 25.8 | 25.6 |
152
+ | Open-LLaMA-v2-pretrain (7B) | 24.0 | 22.5 | 23.1 | 25.3 | 25.2 | 23.2 |
153
+ | TigerBot-7B-base | 25.7 | 27.0 | 27.3 | 24.7 | 23.4 | 26.1 |
154
  | Aquila-7b<sup>*</sup> | 25.5 | 25.2 | 25.6 | 24.6 | 25.2 | 26.6 |
155
+ | BLOOM-7B | 22.8 | 20.2 | 21.8 | 23.3 | 23.9 | 23.3 |
156
+ | BLOOMZ-7B | 35.7 | 25.8 | 31.3 | 43.5 | 36.6 | 35.6 |
157
  | **baichuan-7B** | 42.8 | 31.5 | 38.2 | 52.0 | 46.2 | 39.3 |
158
 
159
 
 
165
 
166
  | Model | Average |
167
  |-------------------------|-----------------|
168
+ | Open-LLaMA-v2-pretrain | 21.41 |
169
+ | Ziya-LLaMA-13B-pretrain | 23.17 |
170
+ | Falcon-7B | 23.98 |
171
+ | TigerBot-7B-base | 25.94 |
172
+ | LLaMA-7B | 27.81 |
173
+ | ChatGLM-6B | 21.41 |
174
+ | BLOOM-7B | 26.96 |
175
+ | BLOOMZ-7B | 28.72 |
176
+ | Aquila-7B<sup>*</sup> | 24.39 |
177
  | **baichuan-7B** | **36.24** |
178
 
179
 
 
183
 
184
  | Model | Average |
185
  |-------------------------|-----------------|
186
+ | Open-Llama-v2-pretrain | 23.49 |
187
+ | Ziya-LLaMA-13B-pretrain | 27.64 |
188
+ | Falcon-7b | 27.18 |
189
+ | TigerBot-7B-base | 25.19 |
190
+ | LLaMA-7B | 28.17 |
191
+ | ChatGLM-6B | 23.49 |
192
+ | BLOOM-7B | 26.55 |
193
+ | BLOOMZ-7B | 30.27 |
194
+ | Aquila-7B<sup>*</sup> | 25.58 |
195
  | **baichuan-7B** | **34.44** |
196
 
197
  <sup>*</sup>其中Aquila模型来源于[智源官方网站](https://model.baai.ac.cn/model-detail/100098)，仅做参考
 
208
  | Model | Humanities | Social Sciences | STEM | Other | Average |
209
  |----------------------------------------|-----------:|:---------------:|:----:|:-----:|:-------:|
210
  | LLaMA-7B<sup>2</sup> | 34.0 | 38.3 | 30.5 | 38.1 | 35.1 |
211
+ | Falcon-7B<sup>1</sup> | - | - | - | - | 35.0 |
212
  | mpt-7B<sup>1</sup> | - | - | - | - | 35.6 |
213
+ | ChatGLM-6B<sup>0</sup> | 35.4 | 41.0 | 31.3 | 40.5 | 36.9 |
214
+ | BLOOM 7B<sup>0</sup> | 25.0 | 24.4 | 26.5 | 26.4 | 25.5 |
215
+ | BLOOMZ 7B<sup>0</sup> | 31.3 | 42.1 | 34.4 | 39.0 | 36.1 |
 
216
  | moss-moon-003-base (16B)<sup>0</sup> | 24.2 | 22.8 | 22.4 | 24.4 | 23.6 |
217
  | moss-moon-003-sft (16B)<sup>0</sup> | 30.5 | 33.8 | 29.3 | 34.4 | 31.9 |
218
  | **baichuan-7B<sup>0</sup>** | 38.4 | 48.9 | 35.6 | 48.1 | 42.3 |