Commit
·
f4bf946
1
Parent(s):
2124cd8
Update README.md
Browse files
README.md
CHANGED
|
@@ -30,22 +30,10 @@ We used the SOTA(State Of The Art) [Language Model Evaluation Harness](https://g
|
|
| 30 |
|
| 31 |
The following is the performance under 0-shot testing, mostly better than acrastt/Marx-3B-V2
|
| 32 |
|
| 33 |
-
| **Task/Metric** | CobraMamba/mamba-gpt-3b-v4 | acrastt/Marx-3B-V2 |
|
| 34 |
-
| ---------------------- | -------- | ------------ |
|
| 35 |
-
| anli_r1/acc | **0.33** | 0.31 |
|
| 36 |
-
| anli_r2/acc | 0.342 | **0.345** |
|
| 37 |
-
| anli_r3/acc | 0.35 | 0.36 |
|
| 38 |
-
| arc_challenge/acc | **0.37** | 0.33 |
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
|
| 42 |
-
|
| 43 |
|
| 44 |
hf-causal (pretrained=CobraMamba/mamba-gpt-3b-v4), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
|
| 45 |
|
| 46 |
|
| 47 |
-
|
| 48 |
-
|
| 49 |
The training code and data will be open sourced later on Github(https://github.com/chi2liu/mamba-gpt-3b).
|
| 50 |
|
| 51 |
|
|
|
|
| 30 |
|
| 31 |
The following is the performance under 0-shot testing, mostly better than acrastt/Marx-3B-V2
|
| 32 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
|
| 34 |
hf-causal (pretrained=CobraMamba/mamba-gpt-3b-v4), limit: None, provide_description: False, num_fewshot: 0, batch_size: None
|
| 35 |
|
| 36 |
|
|
|
|
|
|
|
| 37 |
The training code and data will be open sourced later on Github(https://github.com/chi2liu/mamba-gpt-3b).
|
| 38 |
|
| 39 |
|