Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- mistralai/Mistral-Small-3.1-24B-Instruct-2503
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
Text-Only EXL2 Quant of [mistralai/Mistral-Small-3.1-24B-Instruct-2503](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503)
|
| 7 |
+
|
| 8 |
+
The following changes were made:
|
| 9 |
+
|
| 10 |
+
1. Vision encoder removed
|
| 11 |
+
2. Architecture changed to that of [mistralai/Mistral-Small-24B-Instruct-2501](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501)
|
| 12 |
+
3. Chat template in tokenizer_config.json was modified (see below).
|
| 13 |
+
|
| 14 |
+
I was having trouble with the timestamp at the beginning of the system prompt and removed it from tokenizer_config.json.
|
| 15 |
+
|
| 16 |
+
**NOTE** Tensor Parallel is not implemented in exllamav2 for both [mistralai/Mistral-Small-3.1-24B-Instruct-2503](https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503) and [mistralai/Mistral-Small-24B-Instruct-2501](https://huggingface.co/mistralai/Mistral-Small-24B-Instruct-2501).
|