Instructions to use redactable-llm/redactable-dolphin-mixtral with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use redactable-llm/redactable-dolphin-mixtral with Transformers:

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

pipe = pipeline("text-generation", model="redactable-llm/redactable-dolphin-mixtral")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("redactable-llm/redactable-dolphin-mixtral")
model = AutoModelForCausalLM.from_pretrained("redactable-llm/redactable-dolphin-mixtral", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use redactable-llm/redactable-dolphin-mixtral with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "redactable-llm/redactable-dolphin-mixtral"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redactable-llm/redactable-dolphin-mixtral",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/redactable-llm/redactable-dolphin-mixtral

SGLang

How to use redactable-llm/redactable-dolphin-mixtral 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 "redactable-llm/redactable-dolphin-mixtral" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redactable-llm/redactable-dolphin-mixtral",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "redactable-llm/redactable-dolphin-mixtral" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "redactable-llm/redactable-dolphin-mixtral",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use redactable-llm/redactable-dolphin-mixtral with Docker Model Runner:
```
docker model run hf.co/redactable-llm/redactable-dolphin-mixtral
```

redactable-dolphin-mixtral / README.md

d-delaurier

Update README.md

3031a79 over 2 years ago

preview code

Raw

History Blame Contribute Delete

3.24 kB

	---
	datasets:
	- cognitivecomputations/dolphin
	- cognitivecomputations/dolphin-coder
	- Open-Orca/OpenOrca
	language:
	- en
	library_name: transformers
	tags:
	- legal
	---
	# Redactable-LLM
	The high-level overview for integrating multiple Open Source Large Language Models within the AutoGen Framework is as follows:

	### Development of Custom Agents
	- Agent Design: Tasks include NLP/NER/PII identification, interpreting natural language commands, executing document redaction, and final verification.
	- Customization: Custom agents trained on specific tasks related to each aspect of the redaction process.
	- Human Interaction: Implement features to facilitate seamless human-agent interaction, allowing users to input commands and queries naturally (Optional)

	### LLM & VLLM AutoGen Integration

	- Model Selection: Automatic, task-dependent agent selection.
	- Enhanced Inference: Enhanced LLM inference features for optimal performance, including tuning, caching, error handling, and templating.
	- Quality Control: Vision agents analyze redacted documents using Set-of-Mark (SoM) prompting. Rejected documents are reprocessed and reviewed.
	-
	![AutoGen Agents](https://i.imgur.com/aFgV7yd.png)

	### System Optimization
	- Workflow Automation: Automate the redaction workflow using a blend of LLMs, custom agents, and human inputs for efficient detection and redaction of sensitive information.
	- Performance Maximization: Optimize the system for both efficiency and accuracy, utilizing AutoGen's complex workflow management features.

	### User Interface Development
	- Interface Design: Develop a user-friendly interface that enables non-technical users to interact with the system via natural language prompts.
	- Feedback Integration: Implement a feedback loop to continuously refine the system's accuracy and user-friendliness based on user inputs.
	- User Knowledgebase: (Optional) User account, profile, and domain knowledge will be accessible by the `Research` agent, for personalized interaction and results.

	### Training, Testing and Validation
	- Model Training: Develop new datasets, focused on document understanding related to redaction.
	- Unit Testing: Conduct extensive unit tests to ensure individual system components function correctly.
	- System Testing: Perform comprehensive end-to-end testing to validate the entire redaction process, from user input to output.
	- User Trials: Facilitate user trials to gather feedback and make necessary system adjustments.
	---

	- #### Mistral AI (LLM)
	[Paper](https://mistral.ai/news/mixtral-of-experts/) \| [Model](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)

	- #### QwenLM (VLLM)
	[Paper](https://arxiv.org/abs/2308.12966) \| [Code](https://github.com/QwenLM/Qwen-VL?tab=readme-ov-file) \| [Paper: Set-of-Mark Prompting](https://arxiv.org/abs/2310.11441)

	- #### AutoGen
	[Paper](https://arxiv.org/abs/2308.08155) \| [Code](https://github.com/microsoft/autogen/tree/main)

	- #### Gretel AI (Synthetic Dataset Generation)
	[Model Page](https://gretel.ai/solutions/public-sector) \| [Code](https://github.com/gretelai) \| [Paper: Textbooks Are All You Need II](https://arxiv.org/abs/2309.05463)