Remove duplication footprints
Browse files
README.md
CHANGED
|
@@ -39,10 +39,8 @@ Additionally, to enforce model thinking, the default chat template automatically
|
|
| 39 |
|
| 40 |
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/).
|
| 41 |
|
| 42 |
-
|
| 43 |
## Performance
|
| 44 |
|
| 45 |
-
|
| 46 |
| | Qwen3-30B-A3B Thinking | Qwen3-4B Thinking | Qwen3-4B-Thinking-2507 |
|
| 47 |
|--- | --- | --- | --- |
|
| 48 |
| **Knowledge** | | |
|
|
@@ -216,7 +214,6 @@ To achieve optimal performance, we recommend the following settings:
|
|
| 216 |
|
| 217 |
4. **No Thinking Content in History**: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.
|
| 218 |
|
| 219 |
-
|
| 220 |
### Citation
|
| 221 |
|
| 222 |
If you find our work helpful, feel free to give us a cite.
|
|
|
|
| 39 |
|
| 40 |
For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/).
|
| 41 |
|
|
|
|
| 42 |
## Performance
|
| 43 |
|
|
|
|
| 44 |
| | Qwen3-30B-A3B Thinking | Qwen3-4B Thinking | Qwen3-4B-Thinking-2507 |
|
| 45 |
|--- | --- | --- | --- |
|
| 46 |
| **Knowledge** | | |
|
|
|
|
| 214 |
|
| 215 |
4. **No Thinking Content in History**: In multi-turn conversations, the historical model output should only include the final output part and does not need to include the thinking content. It is implemented in the provided chat template in Jinja2. However, for frameworks that do not directly use the Jinja2 chat template, it is up to the developers to ensure that the best practice is followed.
|
| 216 |
|
|
|
|
| 217 |
### Citation
|
| 218 |
|
| 219 |
If you find our work helpful, feel free to give us a cite.
|