Instructions to use Unbabel/M-Prometheus-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Unbabel/M-Prometheus-3B with Transformers:

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

pipe = pipeline("text-generation", model="Unbabel/M-Prometheus-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Unbabel/M-Prometheus-3B")
model = AutoModelForCausalLM.from_pretrained("Unbabel/M-Prometheus-3B")
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-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Unbabel/M-Prometheus-3B"
# 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-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Unbabel/M-Prometheus-3B

SGLang

How to use Unbabel/M-Prometheus-3B 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-3B" \
    --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-3B",
		"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-3B" \
        --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-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Unbabel/M-Prometheus-3B with Docker Model Runner:
```
docker model run hf.co/Unbabel/M-Prometheus-3B
```

jmprcp commited on Apr 7, 2025

Commit

ed06696

verified ·

1 Parent(s): 03f5e9a

Update README.md

Browse files

Files changed (1) hide show

README.md +8 -53

README.md CHANGED Viewed

@@ -2,64 +2,19 @@
 library_name: transformers
 license: other
 base_model: Qwen/Qwen2.5-3B-Instruct
-tags:
-- alignment-handbook
-- generated_from_trainer
-model-index:
-- name: trained_prometheus
-  results: []
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
-# trained_prometheus
-This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: nan
-## Model description
-More information needed
-## Intended uses & limitations
-More information needed
-## Training and evaluation data
-More information needed
-## Training procedure
-### Training hyperparameters
-The following hyperparameters were used during training:
-- learning_rate: 1e-06
-- train_batch_size: 2
-- eval_batch_size: 1
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 8
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 32
-- total_eval_batch_size: 8
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 1.0
-### Training results
-| Training Loss | Epoch  | Step  | Validation Loss |
-|:-------------:|:------:|:-----:|:---------------:|
-| 1.9997        | 1.0000 | 14840 | nan             |
-### Framework versions
-- Transformers 4.46.0
-- Pytorch 2.1.2+cu121
-- Datasets 3.3.1
-- Tokenizers 0.20.3

 library_name: transformers
 license: other
 base_model: Qwen/Qwen2.5-3B-Instruct
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
+# M-Prometheus
+M-Prometheus is a suite of open LLM judges that can natively evaluate multilingual outputs. They were trained on 480k instances of multilingual direct assessment and pairwise comparison data wiht long-form feedback.
+They can be prompted in the same way as [Prometheus-2](https://huggingface.co/prometheus-eval/prometheus-7b-v2.0/tree/main).
+Check out our [paper](wip) for more details.
+## Citation
+```bibtex
+wip
+```