Update README.md
Browse files
README.md
CHANGED
|
@@ -35,11 +35,11 @@ and is comparable with Mistral-7B-Instruct-v0.1 on MMLU and MT-Bench in English.
|
|
| 35 |
| MediaTek-Research/Breeze-7B-Base-v0.1 | 40.35 | 81.13 | 61.63 |
|
| 36 |
| mistralai/Mistral-7B-v0.1 | 36.93 | 79.27 | 64.89 |
|
| 37 |
| yentinglin/Taiwan-LLM-7B-v2.1-base | | | |
|
| 38 |
-
| yentinglin/Taiwan-LLM-13B-v2.0-base | | | |
|
| 39 |
| 01-ai/Yi-6B | 49.63 | 76.61 | 65.35 |
|
| 40 |
-
| 01-ai/Yi-34B | 63.10 | 84.57 | 77.42 |
|
| 41 |
| Qwen/Qwen-7B | 42.84 | 0.0 * | 61.00 |
|
|
|
|
| 42 |
| Qwen/Qwen-14B | 51.30 | 16.95 * | 68.83 |
|
|
|
|
| 43 |
|
| 44 |
\* Few-shot learning cannot effectively guide the model to generate the proper answer.
|
| 45 |
|
|
@@ -48,11 +48,12 @@ and is comparable with Mistral-7B-Instruct-v0.1 on MMLU and MT-Bench in English.
|
|
| 48 |
| MediaTek-Research/Breeze-7B-Base-v0.1 | 35.74 | 46.08 | 40.29 | 39.27 |
|
| 49 |
| mistralai/Mistral-7B-v0.1 | 33.01 | 42.23 | 35.86 | 37.63 |
|
| 50 |
| yentinglin/Taiwan-LLM-7B-v2.1-base | | | | |
|
| 51 |
-
| yentinglin/Taiwan-LLM-13B-v2.0-base | | | | |
|
| 52 |
| 01-ai/Yi-6B | 41.14 | 57.77 | 50.22 | 49.39 |
|
| 53 |
-
| 01-ai/Yi-34B | 56.03 | 73.06 | 61.12 | 62.19 |
|
| 54 |
| Qwen/Qwen-7B | 28.25 | 47.80 | 43.14 | 42.17 |
|
|
|
|
| 55 |
| Qwen/Qwen-14B | 46.51 | 58.20 | 51.12 | 49.38 |
|
|
|
|
|
|
|
| 56 |
|
| 57 |
## Inference Performance
|
| 58 |
|
|
|
|
| 35 |
| MediaTek-Research/Breeze-7B-Base-v0.1 | 40.35 | 81.13 | 61.63 |
|
| 36 |
| mistralai/Mistral-7B-v0.1 | 36.93 | 79.27 | 64.89 |
|
| 37 |
| yentinglin/Taiwan-LLM-7B-v2.1-base | | | |
|
|
|
|
| 38 |
| 01-ai/Yi-6B | 49.63 | 76.61 | 65.35 |
|
|
|
|
| 39 |
| Qwen/Qwen-7B | 42.84 | 0.0 * | 61.00 |
|
| 40 |
+
| yentinglin/Taiwan-LLM-13B-v2.0-base | | | |
|
| 41 |
| Qwen/Qwen-14B | 51.30 | 16.95 * | 68.83 |
|
| 42 |
+
| 01-ai/Yi-34B | 63.10 | 84.57 | 77.42 |
|
| 43 |
|
| 44 |
\* Few-shot learning cannot effectively guide the model to generate the proper answer.
|
| 45 |
|
|
|
|
| 48 |
| MediaTek-Research/Breeze-7B-Base-v0.1 | 35.74 | 46.08 | 40.29 | 39.27 |
|
| 49 |
| mistralai/Mistral-7B-v0.1 | 33.01 | 42.23 | 35.86 | 37.63 |
|
| 50 |
| yentinglin/Taiwan-LLM-7B-v2.1-base | | | | |
|
|
|
|
| 51 |
| 01-ai/Yi-6B | 41.14 | 57.77 | 50.22 | 49.39 |
|
|
|
|
| 52 |
| Qwen/Qwen-7B | 28.25 | 47.80 | 43.14 | 42.17 |
|
| 53 |
+
| yentinglin/Taiwan-LLM-13B-v2.0-base | | | | |
|
| 54 |
| Qwen/Qwen-14B | 46.51 | 58.20 | 51.12 | 49.38 |
|
| 55 |
+
| 01-ai/Yi-34B | 56.03 | 73.06 | 61.12 | 62.19 |
|
| 56 |
+
|
| 57 |
|
| 58 |
## Inference Performance
|
| 59 |
|