Update README.md
Browse files
README.md
CHANGED
|
@@ -25,6 +25,8 @@ pipeline_tag: text-generation
|
|
| 25 |
## Things you should be aware of when using PARM models (Pinkstack Accuracy Reasoning Models) 🧀
|
| 26 |
|
| 27 |
This PARM is based on Qwen 2.5 0.5B which has gotten extra training parameters so it would have similar outputs to O.1 Mini, We trained with [this](https://huggingface.co/datasets/gghfez/QwQ-LongCoT-130K-cleaned) dataset.
|
|
|
|
|
|
|
| 28 |
|
| 29 |
To use this model, you must use a service which supports the GGUF file format.
|
| 30 |
Additionaly, this is the Prompt Template, it uses the Phi-3 template.
|
|
|
|
| 25 |
## Things you should be aware of when using PARM models (Pinkstack Accuracy Reasoning Models) 🧀
|
| 26 |
|
| 27 |
This PARM is based on Qwen 2.5 0.5B which has gotten extra training parameters so it would have similar outputs to O.1 Mini, We trained with [this](https://huggingface.co/datasets/gghfez/QwQ-LongCoT-130K-cleaned) dataset.
|
| 28 |
+
it is designed to run on any device, from your phone to high-end PC. that is why we've included a BF16 quant.
|
| 29 |
+
|
| 30 |
|
| 31 |
To use this model, you must use a service which supports the GGUF file format.
|
| 32 |
Additionaly, this is the Prompt Template, it uses the Phi-3 template.
|