abacusai
/

Fewshot-Metamath-OrcaVicuna-Mistral-10B

Model card Files Files and versions Community

siddartha-abacus commited on Jan 31

Commit

5fc7d7b

•

1 Parent(s): 5320d73

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -47,7 +47,7 @@ To do a proper abalation we compared the performance of 4 models trained for ~1
 Orca, ShareGPT). Here are the results:
 | Model | Trainable Params | Train Loss | Eval Loss | GSM8K | TruthfulQA |
-| :-----| ------: | ---------: | ----- --: | ----: | ---------: |
 | Mistral 7B | 0 | - | - | 0.374 | 0.426 |
 | Mistral 10B | 0 | - | - | 0.290 | 0.407 |
 | Mistral 7B + LoRA r=12 | 31M | 0.412 | 0.366 | 0.514 | 0.499 |

 Orca, ShareGPT). Here are the results:
 | Model | Trainable Params | Train Loss | Eval Loss | GSM8K | TruthfulQA |
+| :-----| ------: | ---------: | -------: | ----: | ---------: |
 | Mistral 7B | 0 | - | - | 0.374 | 0.426 |
 | Mistral 10B | 0 | - | - | 0.290 | 0.407 |
 | Mistral 7B + LoRA r=12 | 31M | 0.412 | 0.366 | 0.514 | 0.499 |