Instructions to use HINT-lab/mistral-7b-ppo-m-hermes with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HINT-lab/mistral-7b-ppo-m-hermes with Transformers:

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

pipe = pipeline("text-generation", model="HINT-lab/mistral-7b-ppo-m-hermes")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HINT-lab/mistral-7b-ppo-m-hermes")
model = AutoModelForCausalLM.from_pretrained("HINT-lab/mistral-7b-ppo-m-hermes")
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

vLLM

How to use HINT-lab/mistral-7b-ppo-m-hermes with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/HINT-lab/mistral-7b-ppo-m-hermes

SGLang

How to use HINT-lab/mistral-7b-ppo-m-hermes 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 "HINT-lab/mistral-7b-ppo-m-hermes" \
    --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": "HINT-lab/mistral-7b-ppo-m-hermes",
		"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 "HINT-lab/mistral-7b-ppo-m-hermes" \
        --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": "HINT-lab/mistral-7b-ppo-m-hermes",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HINT-lab/mistral-7b-ppo-m-hermes with Docker Model Runner:
```
docker model run hf.co/HINT-lab/mistral-7b-ppo-m-hermes
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Model ID

PPO-M (PPO with Calibrated Reward Modeling) is an RLHF algorithm to mitigate verbalized overconfidence in RLHF-trained Large Language Models. PPO-M calibrates the reward modeling process by augmenting the binary pairwise ranking dataset with explicit confidence scores, and encourages the reward model to align confidence levels with response quality. Please refer to our preprint (Taming Overconfidence in LLMs: Reward Calibration in RLHF) and repo for more details.