Update README.md
#2
by matt-here - opened
README.md
CHANGED
|
@@ -23,6 +23,8 @@ A **6-bit MLX** quantization of [Jackrong/Qwopus3.5-27B-v3](https://huggingface.
|
|
| 23 |
|
| 24 |
Supports `{%- set enable_thinking = false %}` Jinja variable.
|
| 25 |
|
|
|
|
|
|
|
| 26 |
---
|
| 27 |
## Quantization Details
|
| 28 |
|
|
|
|
| 23 |
|
| 24 |
Supports `{%- set enable_thinking = false %}` Jinja variable.
|
| 25 |
|
| 26 |
+
> Update [2026-04-12]: Refined the chat template to further improve stability for long-running tasks and tool use; mitigated an issue where incorrect think tag formatting could leak from a distillation dataset.
|
| 27 |
+
|
| 28 |
---
|
| 29 |
## Quantization Details
|
| 30 |
|