e31210ba00
* Specify the version of pandas in harness evaluation workflow * Specify the version of pandas in harness evaluation workflow * Modify html table style and add fp16.csv in harness * Modify comments
288 B
288 B
| 1 | Index | Model | Precision | Arc | TruthfulQA | Winogrande |
|---|---|---|---|---|---|---|
| 2 | 0 | falcon-7b-instruct-with-patch | fp16 | 46.16 | 44.08 | 67.96 |
| 3 | 1 | Llama2-7b-guanaco-dolphin-500 | fp16 | 56.74 | 46.96 | 74.27 |
| 4 | 2 | Baichuan2-7B-Chat-LLaMAfied | fp16 | 52.47 | 48.04 | 69.14 |
| 5 | 3 | Mistral-7B-v0.1 | fp16 | 59.98 | 42.15 | 78.37 |
| 6 | 4 | mpt-7b-chat | fp16 | 46.50 | 40.16 | 68.43 |