Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,10 @@ datasets:
|
|
| 17 |
|
| 18 |
Coma is based on Qwen 2.5 3B, GRPO-fine tuned on the natural reasoning data set from Meta.
|
| 19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
## Testing
|
| 21 |
|
| 22 |
The following system prompt was used in testing of the model:
|
|
|
|
| 17 |
|
| 18 |
Coma is based on Qwen 2.5 3B, GRPO-fine tuned on the natural reasoning data set from Meta.
|
| 19 |
|
| 20 |
+
## GGUF
|
| 21 |
+
|
| 22 |
+
There are quantized versions available at [theprint/Coma-3B-GGUF](https://huggingface.co/theprint/Coma-3B-GGUF) in GGUF format.
|
| 23 |
+
|
| 24 |
## Testing
|
| 25 |
|
| 26 |
The following system prompt was used in testing of the model:
|