Instructions to use Unbabel/M-Prometheus-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Unbabel/M-Prometheus-7B with Transformers:

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

pipe = pipeline("text-generation", model="Unbabel/M-Prometheus-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Unbabel/M-Prometheus-7B")
model = AutoModelForCausalLM.from_pretrained("Unbabel/M-Prometheus-7B")
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 Unbabel/M-Prometheus-7B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Unbabel/M-Prometheus-7B

SGLang

How to use Unbabel/M-Prometheus-7B 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 "Unbabel/M-Prometheus-7B" \
    --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": "Unbabel/M-Prometheus-7B",
		"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 "Unbabel/M-Prometheus-7B" \
        --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": "Unbabel/M-Prometheus-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Unbabel/M-Prometheus-7B with Docker Model Runner:
```
docker model run hf.co/Unbabel/M-Prometheus-7B
```

Evaluation reproducibility issue and temperature setting

by Tae-Gyun - opened Aug 22, 2025

Discussion

Tae-Gyun

Aug 22, 2025

Hello, thank you for your great work.

I'm using the "Unbabel/M-Prometheus-7B" model to evaluate LLM responses via PrometheusEval.absolute_grade(). In order to improve evaluation reproducibility, I set the temperature parameter to a lower value (e.g., between 0 and 0.9). However, when doing so, I frequently encounter the following issue: Retrying failed batches

This seems to happen more often when the temperature is low, and in some cases the evaluation fails entirely.

Could you clarify:

Whether low temperature values are supported for inference-time deterministic scoring, and if this issue is expected or avoidable.
Whether there are recommended inference settings (e.g., temperature, top_p, etc.) for stable and reproducible scoring using the model?

Additionally, I noticed that the retry logic for failed batches is capped at a maximum of 10 attempts. When evaluating around 9K Korean samples, 10 retries were not sufficient to complete all requests successfully. As a workaround, I modified the retry loop to allow unlimited retries, for example:

# Retry logic with progress bar
retries = 0
while to_retry_inputs:
    retries += 1
    print(f"Retrying failed batches: Attempt {retries}")
...

I have two follow-up questions here:

Is there a specific reason why the maximum retry count is limited to 10?
Would it be safe to use a higher or unlimited retry threshold like above, or could it lead to unintended issues (e.g., hanging processes, resource leaks)?

Thanks again for your support and for providing such a useful evaluation framework!

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

Tap or paste here to upload images

· Sign up or log in to comment