Update README.md
Browse files
README.md
CHANGED
|
@@ -30,6 +30,7 @@ tags:
|
|
| 30 |
</div>
|
| 31 |
|
| 32 |
These quants include our Unsloth chat template fixes, specifically for llama.cpp supported backends.
|
|
|
|
| 33 |
- Set the temperature **~0.6** (recommended) and Top_P value of **0.95** (recommended)
|
| 34 |
- UD-Q2_K_XL (247GB) is recommended
|
| 35 |
- For complete detailed instructions, see our guide: [unsloth.ai/blog/deepseek-v3.1](https://docs.unsloth.ai/basics/deepseek-v3.1)
|
|
|
|
| 30 |
</div>
|
| 31 |
|
| 32 |
These quants include our Unsloth chat template fixes, specifically for llama.cpp supported backends.
|
| 33 |
+
- You must use --jinja for llama.cpp quants
|
| 34 |
- Set the temperature **~0.6** (recommended) and Top_P value of **0.95** (recommended)
|
| 35 |
- UD-Q2_K_XL (247GB) is recommended
|
| 36 |
- For complete detailed instructions, see our guide: [unsloth.ai/blog/deepseek-v3.1](https://docs.unsloth.ai/basics/deepseek-v3.1)
|