Awan LLM
commited on
Commit
•
21f40fc
1
Parent(s):
b4b6ac9
Update README.md
Browse files
README.md
CHANGED
|
@@ -4,6 +4,8 @@ license: apache-2.0
|
|
| 4 |
Based on Meta-Llama-3-8b-Instruct, and is governed by Meta Llama 3 License agreement:
|
| 5 |
https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
|
| 6 |
|
|
|
|
|
|
|
| 7 |
|
| 8 |
We don't know how good this model is exactly in benchmarks since we have not benched this yet, but we think real prompts and usage is more telling anyways.
|
| 9 |
|
|
|
|
| 4 |
Based on Meta-Llama-3-8b-Instruct, and is governed by Meta Llama 3 License agreement:
|
| 5 |
https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct
|
| 6 |
|
| 7 |
+
WARNING: There have been reports that GGUF made using llama.cpp might have tokenization issues and more prone to making mistakes. Until this is fixed we recommend using the AWQ model instead if you need a quantized version.
|
| 8 |
+
|
| 9 |
|
| 10 |
We don't know how good this model is exactly in benchmarks since we have not benched this yet, but we think real prompts and usage is more telling anyways.
|
| 11 |
|