Commit
•
c73f16d
1
Parent(s):
06bf66b
Update README.md
Browse files
README.md
CHANGED
|
@@ -23,8 +23,7 @@ license: apache-2.0
|
|
| 23 |
# Mistral-Nemo-Instruct-12B-iMat-GGUF
|
| 24 |
|
| 25 |
> [!WARNING]
|
| 26 |
-
><b>Important Note:</b> Inferencing in llama.cpp has now been merged in [PR #8604](https://github.com/ggerganov/llama.cpp/pull/8604). Please ensure you are on release [b3438](https://github.com/ggerganov/llama.cpp/releases/tag/b3438) or newer.
|
| 27 |
-
>Other front-ends such as the main branch of kobold.cpp and text-generation-web-ui may not work as intended</b>
|
| 28 |
|
| 29 |
Quantized from Mistral-Nemo-Instruct-2407 fp16
|
| 30 |
* Weighted quantizations were creating using fp16 GGUF and groups_merged.txt in 92 chunks and n_ctx=512
|
|
|
|
| 23 |
# Mistral-Nemo-Instruct-12B-iMat-GGUF
|
| 24 |
|
| 25 |
> [!WARNING]
|
| 26 |
+
><b>Important Note:</b> Inferencing in llama.cpp has now been merged in [PR #8604](https://github.com/ggerganov/llama.cpp/pull/8604). Please ensure you are on release [b3438](https://github.com/ggerganov/llama.cpp/releases/tag/b3438) or newer. Text-generation-web-ui (Ooba) is also working as of 7/23. Official support for Kobold.cpp is still [pending](https://github.com/LostRuins/koboldcpp/issues/1011). </b>
|
|
|
|
| 27 |
|
| 28 |
Quantized from Mistral-Nemo-Instruct-2407 fp16
|
| 29 |
* Weighted quantizations were creating using fp16 GGUF and groups_merged.txt in 92 chunks and n_ctx=512
|