Commit
•
8115011
1
Parent(s):
cb76929
Update README.md
Browse files
README.md
CHANGED
|
@@ -25,8 +25,9 @@ tags:
|
|
| 25 |
<!-- ### vocab_type: -->
|
| 26 |
static quants of https://huggingface.co/aaditya/OpenBioLLM-Llama3-8B
|
| 27 |
|
|
|
|
|
|
|
| 28 |
<!-- provided-files -->
|
| 29 |
-
weighted/imatrix quants are available at https://huggingface.co/mradermacher/OpenBioLLM-Llama3-8B-i1-GGUF
|
| 30 |
## Usage
|
| 31 |
|
| 32 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
|
| 25 |
<!-- ### vocab_type: -->
|
| 26 |
static quants of https://huggingface.co/aaditya/OpenBioLLM-Llama3-8B
|
| 27 |
|
| 28 |
+
You should use `--override-kv tokenizer.ggml.pre=str:llama3` and a current llama.cpp version to work around a bug in llama.cpp that made these quants.
|
| 29 |
+
|
| 30 |
<!-- provided-files -->
|
|
|
|
| 31 |
## Usage
|
| 32 |
|
| 33 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|