Harley-ml
/

LWTDense-6M

Text Generation

lesswrong-transformer

small-language-model

Model card Files Files and versions

Harley-ml commited on Apr 21

Commit

4ac7378

·

verified ·

1 Parent(s): c03c937

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -120,7 +120,7 @@ to Book of the San Francisco and Green, we are in our head to explain what's hap
 | Model | Total Params | Activated Params | Score | Coherent | Mostly Coherent | Partially Coherent | Incoherent |
 |---|---|---|---|---|---|---|---|
 | [gpt2](https://huggingface.co/openai-community/gpt2) | 117M | 117M | 0.4227 | 0 | 51 | 78 | 171 |
-| [LWTMoE-10M-A6M](https://huggingface.co/Harley-ml/LWTMoE-10M-A6M) | 10M | 6M | **0.3520 | 1 | 31 | 49 | 219 |
 | **LWTDense-6M** (this) | 6M | 6M | 0.2962 | 2 | 13 | 32 | 253 |
 | [Pythia-14m-deduped](https://huggingface.co/EleutherAI/pythia-14m-deduped) | 14M | 14M | 0.2846 | 0 | 23 | 24 | 253 |

 | Model | Total Params | Activated Params | Score | Coherent | Mostly Coherent | Partially Coherent | Incoherent |
 |---|---|---|---|---|---|---|---|
 | [gpt2](https://huggingface.co/openai-community/gpt2) | 117M | 117M | 0.4227 | 0 | 51 | 78 | 171 |
+| [LWTMoE-10M-A6M](https://huggingface.co/Harley-ml/LWTMoE-10M-A6M) | 10M | 6M | 0.3520 | 1 | 31 | 49 | 219 |
 | **LWTDense-6M** (this) | 6M | 6M | 0.2962 | 2 | 13 | 32 | 253 |
 | [Pythia-14m-deduped](https://huggingface.co/EleutherAI/pythia-14m-deduped) | 14M | 14M | 0.2846 | 0 | 23 | 24 | 253 |