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

Fix auto-round hfoption (#37759)

Browse Source 
fix
This commit is contained in:
Mohamed Mekkouri
2025-04-24 18:19:38 +02:00
committed by GitHub
parent acdbe627e3
commit b2d70e9c49
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
docs/source/en/quantization/auto_round.md
View File

@@ -184,7 +184,7 @@ inputs = tokenizer(text, return_tensors="pt").to(model.device)
print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50, do_sample=False)[0])) print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50, do_sample=False)[0]))
``` ```
<hfoption> </hfoption>
<hfoption id="inference xpu"> <hfoption id="inference xpu">
@@ -203,7 +203,7 @@ inputs = tokenizer(text, return_tensors="pt").to(model.device)
print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50, do_sample=False)[0])) print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50, do_sample=False)[0]))
``` ```
<hfoption> </hfoption>
<hfoption id="inference cuda"> <hfoption id="inference cuda">
@@ -222,7 +222,7 @@ inputs = tokenizer(text, return_tensors="pt").to(model.device)
print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50, do_sample=False)[0])) print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50, do_sample=False)[0]))
``` ```
<hfoption> </hfoption>
<hfoption id="inference backend"> <hfoption id="inference backend">
@@ -245,7 +245,7 @@ inputs = tokenizer(text, return_tensors="pt").to(model.device)
print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50, do_sample=False)[0])) print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50, do_sample=False)[0]))
``` ```
<hfoption> </hfoption>
<hfoption id="format convert"> <hfoption id="format convert">
@@ -266,9 +266,9 @@ inputs = tokenizer(text, return_tensors="pt").to(model.device)
print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50, do_sample=False)[0])) print(tokenizer.decode(model.generate(**inputs, max_new_tokens=50, do_sample=False)[0]))
``` ```
<hfoption> </hfoption>
<hfoptions> </hfoptions>
## Issues ## Issues