Instructions to use beyoru/BronCode-Thinker-8B-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use beyoru/BronCode-Thinker-8B-medium with Transformers:

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

pipe = pipeline("text-generation", model="beyoru/BronCode-Thinker-8B-medium")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("beyoru/BronCode-Thinker-8B-medium")
model = AutoModelForCausalLM.from_pretrained("beyoru/BronCode-Thinker-8B-medium")
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 beyoru/BronCode-Thinker-8B-medium with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "beyoru/BronCode-Thinker-8B-medium"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "beyoru/BronCode-Thinker-8B-medium",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/beyoru/BronCode-Thinker-8B-medium

SGLang

How to use beyoru/BronCode-Thinker-8B-medium 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 "beyoru/BronCode-Thinker-8B-medium" \
    --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": "beyoru/BronCode-Thinker-8B-medium",
		"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 "beyoru/BronCode-Thinker-8B-medium" \
        --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": "beyoru/BronCode-Thinker-8B-medium",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use beyoru/BronCode-Thinker-8B-medium with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for beyoru/BronCode-Thinker-8B-medium to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for beyoru/BronCode-Thinker-8B-medium to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for beyoru/BronCode-Thinker-8B-medium to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="beyoru/BronCode-Thinker-8B-medium",
    max_seq_length=2048,
)

Docker Model Runner
How to use beyoru/BronCode-Thinker-8B-medium with Docker Model Runner:
```
docker model run hf.co/beyoru/BronCode-Thinker-8B-medium
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Overview

This model is optimized for concise and structured reasoning, delivering high-quality outputs with minimal verbosity. By prioritizing efficient internal reasoning over long, explicit explanations, the model provides more practical and focused responses.

This approach results in:

Improved response quality
Faster inference
Lower token usage
Better suitability for real-world and production use cases

Key Differences from Base Model

Token generation has been reduced compared to the base model, leading to more concise outputs while maintaining reasoning quality.

Intended Use

This model is well-suited for applications that require:

Clear and direct answers
Efficient reasoning without excessive verbosity
Lower inference costs and faster response times

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16