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

Chat template docs (#36163)

Browse Source 
* decompose chat template docs

* add docs

* update model docs

* qwen2-5

* pixtral

* remove old chat template

* also video as list frames supported

* Update docs/source/en/chat_template_multimodal.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/chat_template_multimodal.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/chat_template_multimodal.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/chat_template_multimodal.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/chat_template_multimodal.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/chat_template_multimodal.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/chat_template_multimodal.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/chat_template_multimodal.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/chat_template_multimodal.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/chat_template_multimodal.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/chat_template_multimodal.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/chat_template_multimodal.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* Update docs/source/en/chat_template_multimodal.md

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>

* remove audio for now

---------

Co-authored-by: Steven Liu <59462357+stevhliu@users.noreply.github.com>
This commit is contained in:
Raushan Turganbay
2025-02-14 10:32:14 +01:00
committed by GitHub
parent 3bf02cf440
commit 1931a35140
14 changed files with 1725 additions and 1470 deletions
Download Patch File Download Diff File Expand all files Collapse all files

158
docs/source/en/model_doc/llava.md
View File

@@ -47,9 +47,19 @@ Adding these attributes means that LLaVA will try to infer the number of image t
The attributes can be obtained from model config, as `model.config.vision_config.patch_size` or `model.config.vision_feature_select_strategy`. The `num_additional_image_tokens` should be `1` if the vision backbone adds a CLS token or `0` if nothing extra is added to the vision patches.
### Single image inference
### Formatting Prompts with Chat Templates
Each **checkpoint** is trained with a specific prompt format, depending on the underlying large language model backbone. To ensure correct formatting, use the processor’s `apply_chat_template` method.
**Important:**
- You must construct a conversation history — passing a plain string won't work.
- Each message should be a dictionary with `"role"` and `"content"` keys.
- The `"content"` should be a list of dictionaries for different modalities like `"text"` and `"image"`.
Here’s an example of how to structure your input.
We will use [llava-hf/llava-1.5-7b-hf](https://huggingface.co/llava-hf/llava-1.5-7b-hf) and a conversation history of text and image. Each content field has to be a list of dicts, as follows:
For best results, we recommend users to use the processor's `apply_chat_template()` method to format your prompt correctly. For that you need to construct a conversation history, passing in a plain string will not format your prompt. Each message in the conversation history for chat templates is a dictionary with keys "role" and "content". The "content" should be a list of dictionaries, for "text" and "image" modalities, as follows:
```python
from transformers import AutoProcessor
@@ -84,60 +94,6 @@ print(text_prompt)
>>> "USER: <image>\n<What’s shown in this image? ASSISTANT: This image shows a red stop sign.</s>USER: Describe the image in more details. ASSISTANT:"
```
### Batched inference
LLaVa also supports batched inference. Here is how you can do it:
```python
import requests
from PIL import Image
import torch
from transformers import AutoProcessor, LlavaForConditionalGeneration
# Load the model in half-precision
model = LlavaForConditionalGeneration.from_pretrained("llava-hf/llava-1.5-7b-hf", torch_dtype=torch.float16, device_map="auto")
processor = AutoProcessor.from_pretrained("llava-hf/llava-1.5-7b-hf")
# Get two different images
url = "https://www.ilankelman.org/stopsigns/australia.jpg"
image_stop = Image.open(requests.get(url, stream=True).raw)
url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image_cats = Image.open(requests.get(url, stream=True).raw)
# Prepare a batch of two prompts
conversation_1 = [
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "What is shown in this image?"},
],
},
]
conversation_2 = [
{
"role": "user",
"content": [
{"type": "image"},
{"type": "text", "text": "What is shown in this image?"},
],
},
]
prompt_1 = processor.apply_chat_template(conversation_1, add_generation_prompt=True)
prompt_2 = processor.apply_chat_template(conversation_2, add_generation_prompt=True)
prompts = [prompt_1, prompt_2]
# We can simply feed images in the order they have to be used in the text prompt
inputs = processor(images=[image_stop, image_cats], text=prompts, padding=True, return_tensors="pt").to(model.device, torch.float16)
# Generate
generate_ids = model.generate(**inputs, max_new_tokens=30)
processor.batch_decode(generate_ids, skip_special_tokens=True)
```
- If you want to construct a chat prompt yourself, below is a list of prompt formats accepted by each llava checkpoint:
[llava-interleave models](https://huggingface.co/collections/llava-hf/llava-interleave-668e19a97da0036aad4a2f19) requires the following format:
@@ -162,6 +118,96 @@ For multiple turns conversation:
"USER: <image>\n<prompt1> ASSISTANT: <answer1></s>USER: <prompt2> ASSISTANT: <answer2></s>USER: <prompt3> ASSISTANT:"
```
🚀 **Bonus:** If you're using `transformers>=4.49.0`, you can also get a vectorized output from `apply_chat_template`. See the **Usage Examples** below for more details on how to use it.
## Usage examples
### Single input inference
```python
import torch
from transformers import AutoProcessor, LlavaForConditionalGeneration
# Load the model in half-precision
model = LlavaForConditionalGeneration.from_pretrained("llava-hf/llava-1.5-7b-hf", torch_dtype=torch.float16, device_map="auto")
processor = AutoProcessor.from_pretrained("llava-hf/llava-1.5-7b-hf")
conversation = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://www.ilankelman.org/stopsigns/australia.jpg"},
{"type": "text", "text": "What is shown in this image?"},
],
},
]
inputs = processor.apply_chat_template(
conversation,
add_generation_prompt=True,
tokenize=True,
return_dict=True,
return_tensors="pt"
).to(model.device, torch.float16)
# Generate
generate_ids = model.generate(**inputs, max_new_tokens=30)
processor.batch_decode(generate_ids, skip_special_tokens=True)
```
### Batched inference
LLaVa also supports batched inference. Here is how you can do it:
```python
import torch
from transformers import AutoProcessor, LlavaForConditionalGeneration
# Load the model in half-precision
model = LlavaForConditionalGeneration.from_pretrained("llava-hf/llava-1.5-7b-hf", torch_dtype=torch.float16, device_map="auto")
processor = AutoProcessor.from_pretrained("llava-hf/llava-1.5-7b-hf")
# Prepare a batch of two prompts
conversation_1 = [
{
"role": "user",
"content": [
{"type": "image", "url": "https://www.ilankelman.org/stopsigns/australia.jpg"},
{"type": "text", "text": "What is shown in this image?"},
],
},
]
conversation_2 = [
{
"role": "user",
"content": [
{"type": "image", "url": "http://images.cocodataset.org/val2017/000000039769.jpg"},
{"type": "text", "text": "What is shown in this image?"},
],
},
]
inputs = processor.apply_chat_template(
[conversation_1, conversation_2],
add_generation_prompt=True,
tokenize=True,
return_dict=True,
padding=True,
return_tensors="pt"
).to(model.device, torch.float16)
# Generate
generate_ids = model.generate(**inputs, max_new_tokens=30)
processor.batch_decode(generate_ids, skip_special_tokens=True)
```
## Note regarding reproducing original implementation
In order to match the logits of the [original implementation](https://github.com/haotian-liu/LLaVA/tree/main), one needs to additionally specify `do_pad=True` when instantiating `LLavaImageProcessor`: