Update README.md
Browse files
README.md
CHANGED
|
@@ -75,7 +75,7 @@ and is comparable with Mistral-7B-Instruct-v0.1 on MMLU and MT-Bench in English.
|
|
| 75 |
| | 5 shot | 3 shot | 0 shot | 5 shot | 0 shot |
|
| 76 |
| MediaTek-Research/Breeze-7B-Instruct-v0.1 | | | 5.7 | | |
|
| 77 |
| yentinglin/Taiwan-LLM-7B-v2.1-chat | | | 4.2 | | |
|
| 78 |
-
| yentinglin/Taiwan-LLM-13B-v2.0-chat |
|
| 79 |
| 01-ai/Yi-6B-Chat | | | 5.0 | | |
|
| 80 |
| 01-ai/Yi-34B-Chat | | | 6.9 | | |
|
| 81 |
| Qwen/Qwen-7B-Chat | | | 5.4 | | |
|
|
@@ -83,6 +83,17 @@ and is comparable with Mistral-7B-Instruct-v0.1 on MMLU and MT-Bench in English.
|
|
| 83 |
| gpt-3.5-turbo-1106 | | 76.30 | 7.1 | | |
|
| 84 |
|
| 85 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 86 |
## Use in Transformers
|
| 87 |
|
| 88 |
First install direct dependencies:
|
|
|
|
| 75 |
| | 5 shot | 3 shot | 0 shot | 5 shot | 0 shot |
|
| 76 |
| MediaTek-Research/Breeze-7B-Instruct-v0.1 | | | 5.7 | | |
|
| 77 |
| yentinglin/Taiwan-LLM-7B-v2.1-chat | | | 4.2 | | |
|
| 78 |
+
| yentinglin/Taiwan-LLM-13B-v2.0-chat | 31.92 | | 5.0 | | |
|
| 79 |
| 01-ai/Yi-6B-Chat | | | 5.0 | | |
|
| 80 |
| 01-ai/Yi-34B-Chat | | | 6.9 | | |
|
| 81 |
| Qwen/Qwen-7B-Chat | | | 5.4 | | |
|
|
|
|
| 83 |
| gpt-3.5-turbo-1106 | | 76.30 | 7.1 | | |
|
| 84 |
|
| 85 |
|
| 86 |
+
| Models on 5 shot TMMLU+ | STEM | Social Science | Humanities | Other |
|
| 87 |
+
|-----------------------------------------------------|--------------|----------------|------------|------------|
|
| 88 |
+
| MediaTek-Research/Breeze-7B-Instruct-v0.1 | | | | |
|
| 89 |
+
| yentinglin/Taiwan-LLM-7B-v2.1-chat | | | | |
|
| 90 |
+
| yentinglin/Taiwan-LLM-13B-v2.0-chat | 29.68 | 37.13 | 30.31 | 30.55 |
|
| 91 |
+
| 01-ai/Yi-6B-Chat | | | | |
|
| 92 |
+
| 01-ai/Yi-34B-Chat | | | | |
|
| 93 |
+
| Qwen/Qwen-7B-Chat | | | | |
|
| 94 |
+
| Qwen/Qwen-14B-Chat | | | | |
|
| 95 |
+
| gpt-3.5-turbo-1106 | | | | |
|
| 96 |
+
|
| 97 |
## Use in Transformers
|
| 98 |
|
| 99 |
First install direct dependencies:
|