Fixed spelling issue
Browse files
README.md
CHANGED
|
@@ -26,7 +26,7 @@ We are proud to announce, our new high quality model series - PARM2, Very high q
|
|
| 26 |
- ***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
|
| 27 |
|
| 28 |
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've trained it using the datasets [here](https://huggingface.co/collections/Pinkstackorg/pram-v2-67612d3c542b9121bf15891c)
|
| 29 |
-
if you
|
| 30 |
|
| 31 |
⚠️ it may think it's name is Claude due to the training data, we are sorry for this issue but is shouldn't effect the quality of the responses.
|
| 32 |
|
|
|
|
| 26 |
- ***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
|
| 27 |
|
| 28 |
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've trained it using the datasets [here](https://huggingface.co/collections/Pinkstackorg/pram-v2-67612d3c542b9121bf15891c)
|
| 29 |
+
if you benchmarked this model let me know
|
| 30 |
|
| 31 |
⚠️ it may think it's name is Claude due to the training data, we are sorry for this issue but is shouldn't effect the quality of the responses.
|
| 32 |
|