Instructions to use BurnyCoder/Qwen2.5-0.5B-Capybara with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BurnyCoder/Qwen2.5-0.5B-Capybara with Transformers:

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

pipe = pipeline("text-generation", model="BurnyCoder/Qwen2.5-0.5B-Capybara")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BurnyCoder/Qwen2.5-0.5B-Capybara")
model = AutoModelForCausalLM.from_pretrained("BurnyCoder/Qwen2.5-0.5B-Capybara")
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 BurnyCoder/Qwen2.5-0.5B-Capybara with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BurnyCoder/Qwen2.5-0.5B-Capybara"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BurnyCoder/Qwen2.5-0.5B-Capybara",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BurnyCoder/Qwen2.5-0.5B-Capybara

SGLang

How to use BurnyCoder/Qwen2.5-0.5B-Capybara 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 "BurnyCoder/Qwen2.5-0.5B-Capybara" \
    --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": "BurnyCoder/Qwen2.5-0.5B-Capybara",
		"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 "BurnyCoder/Qwen2.5-0.5B-Capybara" \
        --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": "BurnyCoder/Qwen2.5-0.5B-Capybara",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BurnyCoder/Qwen2.5-0.5B-Capybara with Docker Model Runner:
```
docker model run hf.co/BurnyCoder/Qwen2.5-0.5B-Capybara
```

Qwen2.5-0.5B-Capybara

This model is a fine-tuned version of Qwen/Qwen2.5-0.5B on the trl-lib/Capybara dataset using Supervised Fine-Tuning (SFT).

Model Description

Qwen2.5-0.5B-Capybara is trained on the Capybara dataset, which is a high-quality multi-turn conversational dataset emphasizing:

Reasoning and Logic: Strong focus on extrapolation and logical thinking
Information Diversity: Wide range of domains including STEM, pop-culture, and general knowledge
Multi-turn Conversations: Average of 3+ turns per conversation with 1,000+ tokens context
Natural Prose: Maintains conversational flow while exploring complex topics

The Capybara dataset was created using the Amplify-Instruct synthesis method, combining techniques from Airoboros, Evol-Instruct (WizardLM), Orca, and other high-performing datasets.

Training Details

Training Configuration

Parameter	Value
Base Model	Qwen/Qwen2.5-0.5B
Training Method	Supervised Fine-Tuning (SFT)
Dataset	trl-lib/Capybara (15,806 samples)
Epochs	3
Batch Size	8
Gradient Accumulation	4
Effective Batch Size	32
Learning Rate	2e-5
LR Scheduler	Linear
Precision	BF16
Max Sequence Length	1024
Optimizer	AdamW (fused)

Memory Optimizations

Liger Kernel: Enabled for ~60% VRAM reduction
Gradient Checkpointing: Enabled
BF16 Mixed Precision: Enabled

Training Infrastructure

Framework: TRL (Transformer Reinforcement Learning)
Hardware: Single GPU (8GB VRAM)
Training Time: ~5 minutes per step

Training Progress

Note: This is checkpoint at step 42 of 1,482 total steps (~3% of training). This is an early checkpoint from an ongoing training run.

Metric	Value
Steps Completed	42 / 1,482
Training Progress	~3%
Final Loss (step 42)	1.3058
Initial Loss (step 1)	1.9030

Dataset Information

The trl-lib/Capybara dataset contains:

15,806 training samples of multi-turn conversations
Sources: GPT4LLM, GOAT, EverythingLM, Know-Logic, SuperCOT, Airoboros, Dove, TheoremQA, TaskSource, General-Instruct
Format: Conversation messages with user/assistant roles
Quality: Aggressively filtered to remove alignment artifacts and common undesirable behaviors

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("BurnyCoder/Qwen2.5-0.5B-Capybara")
tokenizer = AutoTokenizer.from_pretrained("BurnyCoder/Qwen2.5-0.5B-Capybara")

messages = [
    {"role": "user", "content": "Explain the concept of recursion in programming."}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Limitations

This is an early checkpoint (~3% trained) and may not reflect full model capabilities
Model size is 494M parameters - suitable for edge deployment but limited compared to larger models
Training was conducted on a single GPU with memory optimizations

Citation

If you use this model, please cite:

@misc{qwen2.5-0.5b-capybara,
  author = {BurnyCoder},
  title = {Qwen2.5-0.5B-Capybara: Multi-turn Conversational Fine-tuning},
  year = {2026},
  publisher = {Hugging Face},
  url = {https://huggingface.co/BurnyCoder/Qwen2.5-0.5B-Capybara}
}

Acknowledgments

Qwen Team for the base model
TRL Library for the training framework
Capybara Dataset creators

Downloads last month: 10

Safetensors

Model size

0.5B params

Tensor type

F32

Model tree for BurnyCoder/Qwen2.5-0.5B-Capybara

Base model

Qwen/Qwen2.5-0.5B

Finetuned

(609)

this model

BurnyCoder
/

Qwen2.5-0.5B-Capybara