Instructions to use ai-forever/Pollux-4B-Judge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ai-forever/Pollux-4B-Judge with Transformers:

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

pipe = pipeline("text-generation", model="ai-forever/Pollux-4B-Judge")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ai-forever/Pollux-4B-Judge")
model = AutoModelForCausalLM.from_pretrained("ai-forever/Pollux-4B-Judge")
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 ai-forever/Pollux-4B-Judge with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ai-forever/Pollux-4B-Judge"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ai-forever/Pollux-4B-Judge",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ai-forever/Pollux-4B-Judge

SGLang

How to use ai-forever/Pollux-4B-Judge 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 "ai-forever/Pollux-4B-Judge" \
    --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": "ai-forever/Pollux-4B-Judge",
		"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 "ai-forever/Pollux-4B-Judge" \
        --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": "ai-forever/Pollux-4B-Judge",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ai-forever/Pollux-4B-Judge with Docker Model Runner:
```
docker model run hf.co/ai-forever/Pollux-4B-Judge
```

ai-forever commited on 11 days ago

Commit

336d1d9

verified ·

1 Parent(s): 7140a43

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ metrics:
 <!-- Provide a quick summary of what the model is/does. -->
-![banner](images/logo_pollux_horiz_short_WHITEBG.png)
 Pollux-4B-Judge is a 4-billion parameter generative language model specifically designed to evaluate the quality of other language models' responses in Russian.
 The model assesses answer quality given input instruction, specific criteria and rubrics, providing automated LLM performance evaluation for Russian-language tasks.

 <!-- Provide a quick summary of what the model is/does. -->
+![banner](logo_pollux_horiz_short_WHITEBG.png)
 Pollux-4B-Judge is a 4-billion parameter generative language model specifically designed to evaluate the quality of other language models' responses in Russian.
 The model assesses answer quality given input instruction, specific criteria and rubrics, providing automated LLM performance evaluation for Russian-language tasks.