Update README.md
Browse files
README.md
CHANGED
|
@@ -2,12 +2,43 @@
|
|
| 2 |
base_model: mistralai/Mistral-Small-3.2-24B-Instruct-2506
|
| 3 |
base_model_relation: quantized
|
| 4 |
quantized_by: ArtusDev
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
## EXL3 Quants of mistralai/Mistral-Small-3.2-24B-Instruct-2506
|
| 8 |
|
| 9 |
EXL3 quants of [mistralai/Mistral-Small-3.2-24B-Instruct-2506](https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506) using <a href="https://github.com/turboderp-org/exllamav3/">exllamav3</a> for quantization.
|
| 10 |
|
|
|
|
|
|
|
| 11 |
### Quants
|
| 12 |
| Quant(Revision) | Bits per Weight | Head Bits |
|
| 13 |
| -------- | ---------- | --------- |
|
|
@@ -36,4 +67,4 @@ Download quant by targeting the specific quant revision (branch):
|
|
| 36 |
```
|
| 37 |
huggingface-cli download ArtusDev/mistralai_Mistral-Small-3.2-24B-Instruct-2506-EXL3 --revision "5.0bpw_H6" --local-dir ./
|
| 38 |
```
|
| 39 |
-
</details>
|
|
|
|
| 2 |
base_model: mistralai/Mistral-Small-3.2-24B-Instruct-2506
|
| 3 |
base_model_relation: quantized
|
| 4 |
quantized_by: ArtusDev
|
| 5 |
+
language:
|
| 6 |
+
- en
|
| 7 |
+
- fr
|
| 8 |
+
- de
|
| 9 |
+
- es
|
| 10 |
+
- pt
|
| 11 |
+
- it
|
| 12 |
+
- ja
|
| 13 |
+
- ko
|
| 14 |
+
- ru
|
| 15 |
+
- zh
|
| 16 |
+
- ar
|
| 17 |
+
- fa
|
| 18 |
+
- id
|
| 19 |
+
- ms
|
| 20 |
+
- ne
|
| 21 |
+
- pl
|
| 22 |
+
- ro
|
| 23 |
+
- sr
|
| 24 |
+
- sv
|
| 25 |
+
- tr
|
| 26 |
+
- uk
|
| 27 |
+
- vi
|
| 28 |
+
- hi
|
| 29 |
+
- bn
|
| 30 |
+
license: apache-2.0
|
| 31 |
+
pipeline_tag: image-text-to-text
|
| 32 |
+
tags:
|
| 33 |
+
- exl3
|
| 34 |
---
|
| 35 |
|
| 36 |
## EXL3 Quants of mistralai/Mistral-Small-3.2-24B-Instruct-2506
|
| 37 |
|
| 38 |
EXL3 quants of [mistralai/Mistral-Small-3.2-24B-Instruct-2506](https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506) using <a href="https://github.com/turboderp-org/exllamav3/">exllamav3</a> for quantization.
|
| 39 |
|
| 40 |
+
Based on the HF conversion of the base 3.2 model by unsloth: [unsloth/Mistral-Small-3.2-24B-Instruct-2506](https://huggingface.co/unsloth/Mistral-Small-3.2-24B-Instruct-2506)
|
| 41 |
+
|
| 42 |
### Quants
|
| 43 |
| Quant(Revision) | Bits per Weight | Head Bits |
|
| 44 |
| -------- | ---------- | --------- |
|
|
|
|
| 67 |
```
|
| 68 |
huggingface-cli download ArtusDev/mistralai_Mistral-Small-3.2-24B-Instruct-2506-EXL3 --revision "5.0bpw_H6" --local-dir ./
|
| 69 |
```
|
| 70 |
+
</details>
|