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

[docs] Fix image link (#36869)

Browse Source 
* fix image link

* fix

* update

* fix
This commit is contained in:
Steven Liu
2025-03-25 11:34:21 -07:00
committed by GitHub
parent d68a91aebf
commit a844297088
4 changed files with 62 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
docs/source/en/processors.md
View File

@@ -29,8 +29,8 @@ import requests
processor = AutoProcessor.from_pretrained("google/paligemma-3b-pt-224")
prompt = "answer en Where is the cow standing?"
url = "https://huggingface.co/gv-hf/PaliGemma-test-224px-hf/resolve/main/cow_beach_1.png"
prompt = "answer en Where is the cat standing?"
url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"
image = Image.open(requests.get(url, stream=True).raw)
inputs = processor(text=prompt, images=image, return_tensors="pt")

37
src/transformers/models/gemma3/modeling_gemma3.py
View File

@@ -1272,20 +1272,37 @@ class Gemma3ForConditionalGeneration(Gemma3PreTrainedModel, GenerationMixin):
>>> import requests
>>> from transformers import AutoProcessor, Gemma3ForConditionalGeneration
>>> model = Gemma3ForConditionalGeneration.from_pretrained("google/Gemma3-test-224px-hf")
>>> processor = AutoProcessor.from_pretrained("google/Gemma3-test-224px-hf")
>>> model = Gemma3ForConditionalGeneration.from_pretrained("google/gemma-3-4b-it")
>>> processor = AutoProcessor.from_pretrained("google/gemma-3-4b-it")
>>> prompt = "answer en Where is the cow standing?"
>>> url = "https://huggingface.co/gv-hf/Gemma3-test-224px-hf/resolve/main/cow_beach_1.png"
>>> image = Image.open(requests.get(url, stream=True).raw)
>>> inputs = processor(images=image, text=prompt, return_tensors="pt")
>>> messages = [
... {
... "role": "system",
... "content": [
... {"type": "text", "text": "You are a helpful assistant."}
... ]
... },
... {
... "role": "user", "content": [
... {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
... {"type": "text", "text": "Where is the cat standing?"},
... ]
... },
... ]
>>> inputs = processor.apply_chat_template(
... messages,
... tokenizer=True,
... return_dict=True,
... return_tensors="pt",
... add_generation_prompt=True
... )
>>> # Generate
>>> generate_ids = model.generate(**inputs, max_length=30)
>>> generate_ids = model.generate(**inputs)
>>> processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
"answer en Where is the cow standing?\nbeach"
```"""
"user\nYou are a helpful assistant.\n\n\n\n\n\nWhere is the cat standing?\nmodel\nBased on the image, the cat is standing in a snowy area, likely outdoors. It appears to"
```
"""
if (input_ids is None) ^ (inputs_embeds is not None):
raise ValueError("You must specify exactly one of input_ids or inputs_embeds")

37
src/transformers/models/gemma3/modular_gemma3.py
View File

@@ -883,20 +883,37 @@ class Gemma3ForConditionalGeneration(PaliGemmaForConditionalGeneration):
>>> import requests
>>> from transformers import AutoProcessor, Gemma3ForConditionalGeneration
>>> model = Gemma3ForConditionalGeneration.from_pretrained("google/Gemma3-test-224px-hf")
>>> processor = AutoProcessor.from_pretrained("google/Gemma3-test-224px-hf")
>>> model = Gemma3ForConditionalGeneration.from_pretrained("google/gemma-3-4b-it")
>>> processor = AutoProcessor.from_pretrained("google/gemma-3-4b-it")
>>> prompt = "answer en Where is the cow standing?"
>>> url = "https://huggingface.co/gv-hf/Gemma3-test-224px-hf/resolve/main/cow_beach_1.png"
>>> image = Image.open(requests.get(url, stream=True).raw)
>>> inputs = processor(images=image, text=prompt, return_tensors="pt")
>>> messages = [
... {
... "role": "system",
... "content": [
... {"type": "text", "text": "You are a helpful assistant."}
... ]
... },
... {
... "role": "user", "content": [
... {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"},
... {"type": "text", "text": "Where is the cat standing?"},
... ]
... },
... ]
>>> inputs = processor.apply_chat_template(
... messages,
... tokenizer=True,
... return_dict=True,
... return_tensors="pt",
... add_generation_prompt=True
... )
>>> # Generate
>>> generate_ids = model.generate(**inputs, max_length=30)
>>> generate_ids = model.generate(**inputs)
>>> processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
"answer en Where is the cow standing?\nbeach"
```"""
"user\nYou are a helpful assistant.\n\n\n\n\n\nWhere is the cat standing?\nmodel\nBased on the image, the cat is standing in a snowy area, likely outdoors. It appears to"
```
"""
if (input_ids is None) ^ (inputs_embeds is not None):
raise ValueError("You must specify exactly one of input_ids or inputs_embeds")

12
src/transformers/models/paligemma/modeling_paligemma.py
View File

@@ -464,19 +464,19 @@ class PaliGemmaForConditionalGeneration(PaliGemmaPreTrainedModel, GenerationMixi
>>> import requests
>>> from transformers import AutoProcessor, PaliGemmaForConditionalGeneration
>>> model = PaliGemmaForConditionalGeneration.from_pretrained("google/PaliGemma-test-224px-hf")
>>> processor = AutoProcessor.from_pretrained("google/PaliGemma-test-224px-hf")
>>> model = PaliGemmaForConditionalGeneration.from_pretrained("google/paligemma2-3b-mix-224")
>>> processor = AutoProcessor.from_pretrained("google/paligemma2-3b-mix-224")
>>> prompt = "answer en Where is the cow standing?"
>>> url = "https://huggingface.co/gv-hf/PaliGemma-test-224px-hf/resolve/main/cow_beach_1.png"
>>> prompt = "Where is the cat standing?"
>>> url = "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/pipeline-cat-chonk.jpeg"
>>> image = Image.open(requests.get(url, stream=True).raw)
>>> inputs = processor(images=image, text=prompt, return_tensors="pt")
>>> # Generate
>>> generate_ids = model.generate(**inputs, max_length=30)
>>> generate_ids = model.generate(**inputs,)
>>> processor.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
"answer en Where is the cow standing?\nbeach"
"Where is the cat standing?\nsnow"
```"""
if (input_ids is None) ^ (inputs_embeds is not None):