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
```

wuxiaojun commited on Nov 15, 2024

Commit

e49c216

verified ·

1 Parent(s): bb69298

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -19,7 +19,7 @@ datasets:
 <!-- markdownlint-disable no-duplicate-header -->
 <div align="center">
-  <img src="https://github.com/IDEA-FinAI/Golden-Touchstone/blob/main/Touchstone-GPT-logo.png?raw=true" width="15%" alt="Golden-Touchstone" />
   <h1 style="display: inline-block; vertical-align: middle; margin-left: 10px; font-size: 2em; font-weight: bold;">Golden-Touchstone Benchmark</h1>
 </div>
@@ -48,15 +48,15 @@ Golden Touchstone is a simple, effective, and systematic benchmark for bilingual
 The paper shows the evaluation of the diversity, systematicness and LLM adaptability of each open source benchmark.
-![benchmark_info](https://github.com/IDEA-FinAI/Golden-Touchstone/blob/main/benchmark_info.png?raw=true)
 By collecting and selecting representative task datasets, we built our own Chinese-English bilingual Touchstone Benchmark, which includes 22 datasets
-![golden_touchstone_info](https://github.com/IDEA-FinAI/Golden-Touchstone/blob/main/golden_touchstone_info.png?raw=true)
 We extensively evaluated GPT-4o, llama3, qwen2, fingpt and our own trained Touchstone-GPT, analyzed the advantages and disadvantages of these models, and provided direction for subsequent research on financial large language models
-![evaluation](https://github.com/IDEA-FinAI/Golden-Touchstone/blob/main/evaluation.png?raw=true)
 ## Evaluation of Touchstone Benchmark

 <!-- markdownlint-disable no-duplicate-header -->
 <div align="center">
+  <img src="https://github.com/IDEA-FinAI/Golden-Touchstone/blob/main/assets/Touchstone-GPT-logo.png?raw=true" width="15%" alt="Golden-Touchstone" />
   <h1 style="display: inline-block; vertical-align: middle; margin-left: 10px; font-size: 2em; font-weight: bold;">Golden-Touchstone Benchmark</h1>
 </div>
 The paper shows the evaluation of the diversity, systematicness and LLM adaptability of each open source benchmark.
+![benchmark_info](https://github.com/IDEA-FinAI/Golden-Touchstone/blob/main/assets/benchmark_info.png?raw=true)
 By collecting and selecting representative task datasets, we built our own Chinese-English bilingual Touchstone Benchmark, which includes 22 datasets
+![golden_touchstone_info](https://github.com/IDEA-FinAI/Golden-Touchstone/blob/main/assets/golden_touchstone_info.png?raw=true)
 We extensively evaluated GPT-4o, llama3, qwen2, fingpt and our own trained Touchstone-GPT, analyzed the advantages and disadvantages of these models, and provided direction for subsequent research on financial large language models
+![evaluation](https://github.com/IDEA-FinAI/Golden-Touchstone/blob/main/assets/evaluation.png?raw=true)
 ## Evaluation of Touchstone Benchmark