Instructions to use Qwen/Qwen3-Omni-30B-A3B-Thinking with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/Qwen3-Omni-30B-A3B-Thinking with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Qwen/Qwen3-Omni-30B-A3B-Thinking") model = AutoModelForMultimodalLM.from_pretrained("Qwen/Qwen3-Omni-30B-A3B-Thinking", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add the missing `do_sample: true` to generation_config.json
#12
by NotaMG - opened
- generation_config.json +1 -0
generation_config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"max_new_tokens": 32768,
|
| 3 |
"repetition_penalty": 1.0,
|
| 4 |
"temperature": 0.6,
|
|
|
|
| 1 |
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
"max_new_tokens": 32768,
|
| 4 |
"repetition_penalty": 1.0,
|
| 5 |
"temperature": 0.6,
|