Instructions to use speakleash/Bielik-11B-v2.2-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use speakleash/Bielik-11B-v2.2-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="speakleash/Bielik-11B-v2.2-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("speakleash/Bielik-11B-v2.2-Instruct")
model = AutoModelForCausalLM.from_pretrained("speakleash/Bielik-11B-v2.2-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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use speakleash/Bielik-11B-v2.2-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "speakleash/Bielik-11B-v2.2-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": "speakleash/Bielik-11B-v2.2-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/speakleash/Bielik-11B-v2.2-Instruct

SGLang

How to use speakleash/Bielik-11B-v2.2-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 "speakleash/Bielik-11B-v2.2-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": "speakleash/Bielik-11B-v2.2-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 "speakleash/Bielik-11B-v2.2-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": "speakleash/Bielik-11B-v2.2-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use speakleash/Bielik-11B-v2.2-Instruct with Docker Model Runner:
```
docker model run hf.co/speakleash/Bielik-11B-v2.2-Instruct
```

Sugestia co do ustawień.

by Danioken - opened Jan 29, 2025

Discussion

Danioken

Jan 29, 2025

•

edited Jan 29, 2025

Witam.

Początkowo używałem zalecanych przez was ustawień, to znaczy temperatury bardzo niskiej około 0.2-03. Ale ekperymentując trafiłem na coś ciekawego.

Ustawienia:

Temperatura: 1.0
Top K: 40 (to być może jest zbędne)
Min P: 0.2 (ważne)
Smoothing Factor: 0.9 (podstawa tego ustawienia)
Smoothing Curve: 1 (czyli domyślne)

Efekt - dużo bardziej naturalny język i niezwykle mało literówek i dziwnych odmian. Dodatkową zaletą jest to że jest znacznie mniej powtórzeń. Zauważyłem że często jest kilka ciekawych opcji na następne słowo, ale temperatura 0.2 je eliminowała. Smoothing Factor znacząco poprawia tą sytuację, jednocześnie trzyma wysoki poziom wypowiedzi.

Danioken changed discussion status to closed Jan 30, 2025

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