Update README.md
Browse files
README.md
CHANGED
|
@@ -5,15 +5,9 @@ Based on Meta-Llama-3-8b-Instruct, and is governed by Meta Llama 3 License agree
|
|
| 5 |
https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
|
| 6 |
|
| 7 |
|
| 8 |
-
This v0.3 version is even more uncensored thanks to using https://huggingface.co/AwanLLM/Awanllm-Llama-3-8B-Dolfin-v0.6-Abliterated as the base model.
|
| 9 |
-
|
| 10 |
-
|
| 11 |
In terms of reasoning and intelligence, this model is probably a bit worse than the OG model because of the decensoring. However, this model is better at long back and forth chats and will refuse less.
|
| 12 |
|
| 13 |
|
| 14 |
-
We have it up on our site https://awanllm.com for anyone to try.
|
| 15 |
-
|
| 16 |
-
|
| 17 |
OpenLLM Benchmark:
|
| 18 |
|
| 19 |
|
|
@@ -38,7 +32,7 @@ Instruct format:
|
|
| 38 |
|
| 39 |
Quants:
|
| 40 |
|
| 41 |
-
FP16: https://huggingface.co/
|
| 42 |
|
| 43 |
-
GGUF: https://huggingface.co/
|
| 44 |
|
|
|
|
| 5 |
https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
|
| 6 |
|
| 7 |
|
|
|
|
|
|
|
|
|
|
| 8 |
In terms of reasoning and intelligence, this model is probably a bit worse than the OG model because of the decensoring. However, this model is better at long back and forth chats and will refuse less.
|
| 9 |
|
| 10 |
|
|
|
|
|
|
|
|
|
|
| 11 |
OpenLLM Benchmark:
|
| 12 |
|
| 13 |
|
|
|
|
| 32 |
|
| 33 |
Quants:
|
| 34 |
|
| 35 |
+
FP16: https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.3
|
| 36 |
|
| 37 |
+
GGUF: https://huggingface.co/OwenArli/ArliAI-Llama-3-8B-Cumulus-v0.3-GGUF
|
| 38 |
|