SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

[qwen-omni] fix training (#37517)

Browse Source 
* fix

* add text config

* fixup

* fix docs
This commit is contained in:
Raushan Turganbay
2025-04-22 12:36:07 +02:00
committed by GitHub
parent 9167fadab9
commit dcf6df5b0d
4 changed files with 39 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs/source/en/quantization/torchao.md
View File

@@ -112,8 +112,6 @@ input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")
output = quantized_model.generate(**input_ids, max_new_tokens=10, cache_implementation="static")
print(tokenizer.decode(output[0], skip_special_tokens=True))
```
</hfoption>
</hfoption>
<hfoption id="int4-weight-only">
@@ -332,6 +330,7 @@ quantized_model.push_to_hub(f"{USER_ID}/llama3-8b-int4wo-128", safe_serializatio
tokenizer.push_to_hub(f"{USER_ID}/llama3-8b-int4wo-128")
```
</hfoption>
</hfoptions>
## Loading quantized models