Instructions to use IFM/CrystalChat-7B-Web2Code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IFM/CrystalChat-7B-Web2Code with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="IFM/CrystalChat-7B-Web2Code", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("IFM/CrystalChat-7B-Web2Code", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use IFM/CrystalChat-7B-Web2Code with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IFM/CrystalChat-7B-Web2Code"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IFM/CrystalChat-7B-Web2Code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/IFM/CrystalChat-7B-Web2Code

SGLang

How to use IFM/CrystalChat-7B-Web2Code with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "IFM/CrystalChat-7B-Web2Code" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IFM/CrystalChat-7B-Web2Code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "IFM/CrystalChat-7B-Web2Code" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IFM/CrystalChat-7B-Web2Code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use IFM/CrystalChat-7B-Web2Code with Docker Model Runner:
```
docker model run hf.co/IFM/CrystalChat-7B-Web2Code
```

victormiller commited on Oct 17, 2024

Commit

670d19f

verified ·

1 Parent(s): 56cb2bd

Update README.md

Browse files

Files changed (1) hide show

README.md +15 -2

README.md CHANGED Viewed

@@ -16,8 +16,21 @@ datasets:
 ## Model Description
-CrystalChat-7B based multi-modal large language model (MLLM) mimics the training recipe used for Vicuna-7B based [LLaVa-v1.5](https://huggingface.co/docs/transformers/main/model_doc/llava). CrystalChat-7B based MLLMs models are entirely transparent, having open-sourced all materials, including code, data, model checkpoint, intermediate results, and more at [TODO: Add paper link](). CrystalChat-7B-Web2Code MLLM is specialized in webpage images-to-html code generation.
 ## Evaluations

 ## Model Description
+CrystalChat-7B based multi-modal large language model (MLLM) mimics the training recipe used for Vicuna-7B based [LLaVa-v1.5](https://huggingface.co/docs/transformers/main/model_doc/llava). CrystalChat-7B based MLLMs models are entirely transparent, having open-sourced all materials, including code, data, model checkpoint, intermediate results, and more at [Web2Code: A Large-scale Webpage-to-Code Dataset
+and Evaluation Framework for Multimodal LLMs](https://arxiv.org/pdf/2406.20098). CrystalChat-7B-Web2Code MLLM is specialized in webpage images-to-html code generation.
+## Web2Code Dataset
+Our Web2Code instruction tuning dataset construction and instruction generation process
+involves four key components:
+1.  Creation of new webpage image-code pair data: We generated
+high-quality HTML webpage-code pairs following the CodeAlpaca prompt [6] using GPT-3.5 and
+convert them into instruction-following data. (2) Refinement of existing webpage code generation
+data: We transform existing datasets including WebSight [ 22 ] and Pix2Code [ 4] into an instruction-
+following data format similar to LLaVA data [33 ], so they can be used as instruction-following data
+to train MLLMs. (3) Creation of a new text question-answer pair data: We generated a new question-
+answer pair dataset utilizing our new GPT-3.5 generated data from (1) for webpage understanding.
+(4) Refinement of existing webpage understanding data: We refine the WebSRC [ 10] question-answer
+data to improve its quality using the GPT-4.
 ## Evaluations