Update README.md
Browse files
README.md
CHANGED
|
@@ -13,8 +13,6 @@ SFT fine tune of Meta Llama 3 8B Instruct Abliterated v3 by Failspy using an imp
|
|
| 13 |
Since it is based on the Abliterated version of Llama 3 8B Instruct it should naturally not refuse to answer in the first place and this fine tuning should make it comply even better.
|
| 14 |
|
| 15 |
|
| 16 |
-
We also have it up on our site https://awanllm.com for anyone to try!
|
| 17 |
-
|
| 18 |
Best practices:
|
| 19 |
- Be precise and explain what you want the model to do. It has less base "personality" than the OG model but it will act however you tell it to.
|
| 20 |
- This model works best with system prompts that tells it that it is the character, instead of telling it to act as a character.
|
|
@@ -42,7 +40,7 @@ Llama 3 Instruct format:
|
|
| 42 |
|
| 43 |
Quants:
|
| 44 |
|
| 45 |
-
FP16: https://huggingface.co/
|
| 46 |
|
| 47 |
-
GGUF: https://huggingface.co/
|
| 48 |
|
|
|
|
| 13 |
Since it is based on the Abliterated version of Llama 3 8B Instruct it should naturally not refuse to answer in the first place and this fine tuning should make it comply even better.
|
| 14 |
|
| 15 |
|
|
|
|
|
|
|
| 16 |
Best practices:
|
| 17 |
- Be precise and explain what you want the model to do. It has less base "personality" than the OG model but it will act however you tell it to.
|
| 18 |
- This model works best with system prompts that tells it that it is the character, instead of telling it to act as a character.
|
|
|
|
| 40 |
|
| 41 |
Quants:
|
| 42 |
|
| 43 |
+
FP16: https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Dolfin-v1.0
|
| 44 |
|
| 45 |
+
GGUF: https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Dolfin-v1.0-GGUF
|
| 46 |
|