Update README.md
Browse files
README.md
CHANGED
|
@@ -23,6 +23,7 @@ pipeline_tag: text-generation
|
|
| 23 |
- ***Q8:*** This model should be used on most high end modern devices like rtx 3080, Responses are very high quality, but its noticeably slower than q4
|
| 24 |
|
| 25 |
This Parm v2 is based on Qwen 2.5 3B which has gotten many extra reasoning training parameters so it would have similar outputs to qwen QwQ / O.1 mini (only much, smaller.), We trained using [this](https://huggingface.co/datasets/gghfez/QwQ-LongCoT-130K-cleaned) dataset, opus dataset and sonnet 3.5 dataset from huggingface.
|
|
|
|
| 26 |
This is a pretty heavy to run model if you want on device ai's for phones I'd recommend using the 0.5B version of this model (coming soon)
|
| 27 |
|
| 28 |
|
|
|
|
| 23 |
- ***Q8:*** This model should be used on most high end modern devices like rtx 3080, Responses are very high quality, but its noticeably slower than q4
|
| 24 |
|
| 25 |
This Parm v2 is based on Qwen 2.5 3B which has gotten many extra reasoning training parameters so it would have similar outputs to qwen QwQ / O.1 mini (only much, smaller.), We trained using [this](https://huggingface.co/datasets/gghfez/QwQ-LongCoT-130K-cleaned) dataset, opus dataset and sonnet 3.5 dataset from huggingface.
|
| 26 |
+
|
| 27 |
This is a pretty heavy to run model if you want on device ai's for phones I'd recommend using the 0.5B version of this model (coming soon)
|
| 28 |
|
| 29 |
|