Update README.md
Browse files
README.md
CHANGED
@@ -8,7 +8,7 @@ language:
|
|
8 |
|
9 |
## Model Details
|
10 |
|
11 |
-
Metharme 1.3B is an instruct model based on EleutherAI's [Pythia 1.4B
|
12 |
|
13 |
This is an experiment to try and get a model that is usable for conversation, roleplaying and storywriting, but which can be guided using natural language like other instruct models. See the [prompting](#prompting) section below for examples.
|
14 |
|
@@ -71,8 +71,8 @@ The model was evaluated using EleutherAI's [lm-evaluation-harness](https://githu
|
|
71 |
```
|
72 |
anli_r1,anli_r2,anli_r3,arc_challenge,arc_easy,boolq,cb,hellaswag,openbookqa,piqa,rte,truthfulqa_mc,wic,winogrande,wsc
|
73 |
```
|
74 |
-
|
75 |
-
![Metharme 1.3B](https://files.catbox.moe/mqemcg.png)
|
76 |
|
77 |
## Limitations and biases
|
78 |
|
|
|
8 |
|
9 |
## Model Details
|
10 |
|
11 |
+
Metharme 1.3B is an instruct model based on EleutherAI's [Pythia 1.4B Deduped](https://huggingface.co/EleutherAI/pythia-1.4b-deduped).
|
12 |
|
13 |
This is an experiment to try and get a model that is usable for conversation, roleplaying and storywriting, but which can be guided using natural language like other instruct models. See the [prompting](#prompting) section below for examples.
|
14 |
|
|
|
71 |
```
|
72 |
anli_r1,anli_r2,anli_r3,arc_challenge,arc_easy,boolq,cb,hellaswag,openbookqa,piqa,rte,truthfulqa_mc,wic,winogrande,wsc
|
73 |
```
|
74 |
+
Comparison of Metharme-1.3B's performance on benchmarks to Pygmalion-6B, Metharme-7B, and [RedPajama-INCITE-Chat-3B-v1](https://huggingface.co/togethercomputer/RedPajama-INCITE-Chat-3B-v1):
|
75 |
+
![Metharme 1.3B Evaluation Results](https://files.catbox.moe/mqemcg.png)
|
76 |
|
77 |
## Limitations and biases
|
78 |
|