Update README.md
Browse files
README.md
CHANGED
|
@@ -35,6 +35,8 @@ inference: false
|
|
| 35 |
|
| 36 |
## Llamacpp imatrix Quantizations of Mistral-Small-3.1-24B-Instruct-2503 by mistralai
|
| 37 |
|
|
|
|
|
|
|
| 38 |
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4914">b4914</a> for quantization.
|
| 39 |
|
| 40 |
Original model: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503
|
|
|
|
| 35 |
|
| 36 |
## Llamacpp imatrix Quantizations of Mistral-Small-3.1-24B-Instruct-2503 by mistralai
|
| 37 |
|
| 38 |
+
*Text only conversion, vision isn't supported yet in llama.cpp*
|
| 39 |
+
|
| 40 |
Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4914">b4914</a> for quantization.
|
| 41 |
|
| 42 |
Original model: https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503
|