Update README.md
Browse files
README.md
CHANGED
|
@@ -5,6 +5,6 @@ base_model:
|
|
| 5 |
- unsloth/Llama-3.2-3B-Instruct
|
| 6 |
license: llama3.2
|
| 7 |
---
|
| 8 |
-
A much further trained version, this time done with full finetuning instead of DoRA.
|
| 9 |
|
| 10 |
Note: This likely has refusals like [PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B](https://huggingface.co/PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B) since no focus was put on removing refusals. I'm working on a KTO DoRA to solve this, and possibly improve roleplay performance.
|
|
|
|
| 5 |
- unsloth/Llama-3.2-3B-Instruct
|
| 6 |
license: llama3.2
|
| 7 |
---
|
| 8 |
+
A much further trained version, this time done with full finetuning instead of DoRA. Similar ~50/50 mix of completion and instruct data.
|
| 9 |
|
| 10 |
Note: This likely has refusals like [PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B](https://huggingface.co/PJMixers-Dev/LLaMa-3.2-Instruct-JankMix-v0.1-SFT-3B) since no focus was put on removing refusals. I'm working on a KTO DoRA to solve this, and possibly improve roleplay performance.
|