Instructions to use IDEA-FinAI/TouchstoneGPT-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IDEA-FinAI/TouchstoneGPT-7B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="IDEA-FinAI/TouchstoneGPT-7B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("IDEA-FinAI/TouchstoneGPT-7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("IDEA-FinAI/TouchstoneGPT-7B-Instruct")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use IDEA-FinAI/TouchstoneGPT-7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IDEA-FinAI/TouchstoneGPT-7B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IDEA-FinAI/TouchstoneGPT-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IDEA-FinAI/TouchstoneGPT-7B-Instruct

SGLang

How to use IDEA-FinAI/TouchstoneGPT-7B-Instruct 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 "IDEA-FinAI/TouchstoneGPT-7B-Instruct" \
    --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": "IDEA-FinAI/TouchstoneGPT-7B-Instruct",
		"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 "IDEA-FinAI/TouchstoneGPT-7B-Instruct" \
        --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": "IDEA-FinAI/TouchstoneGPT-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IDEA-FinAI/TouchstoneGPT-7B-Instruct with Docker Model Runner:
```
docker model run hf.co/IDEA-FinAI/TouchstoneGPT-7B-Instruct
```

Update model card for Think-on-Graph 3.0 framework (RAG-Factory)

by nielsr HF Staff - opened Sep 30, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+68

-36

nielsr

Sep 30, 2025

This PR updates the model card for IDEA-FinAI/TouchstoneGPT-7B-Instruct to accurately reflect its association with the paper "Think-on-Graph 3.0: Efficient and Adaptive LLM Reasoning on Heterogeneous Graphs via Multi-Agent Dual-Evolving Context Retrieval" and the corresponding RAG-Factory GitHub repository.

The update includes:

Clarifying that this repository hosts a Qwen2-7B-Instruct based model that can be used within the Think-on-Graph 3.0 framework.
Incorporating the abstract of the Think-on-Graph 3.0 paper.
Adding links to the paper and the RAG-Factory GitHub repository.
Integrating features, installation steps, and general usage examples from the RAG-Factory GitHub README to provide context for the framework.
Retaining the existing transformers sample usage for TouchstoneGPT-7B-Instruct, explicitly stating how to use this specific model.
Updating metadata with relevant tags such as retrieval-augmented-generation, rag, graph-neural-networks, and llm-reasoning, while preserving existing finance and text-generation-inference tags relevant to the model itself.
Updating images and badges to link to the RAG-Factory project and the Think-on-Graph 3.0 paper.

Please review and merge this PR to ensure the model card comprehensively describes the model and its relation to the Think-on-Graph 3.0 framework.

Update model card for Think-on-Graph 3.0 framework (RAG-Factory)c258334e

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment