Instructions to use Cbgcbg/limo-qwen3-8b-math-full-precision_v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Cbgcbg/limo-qwen3-8b-math-full-precision_v3 with Transformers:

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

pipe = pipeline("text-generation", model="Cbgcbg/limo-qwen3-8b-math-full-precision_v3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Cbgcbg/limo-qwen3-8b-math-full-precision_v3")
model = AutoModelForCausalLM.from_pretrained("Cbgcbg/limo-qwen3-8b-math-full-precision_v3")
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 Cbgcbg/limo-qwen3-8b-math-full-precision_v3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Cbgcbg/limo-qwen3-8b-math-full-precision_v3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Cbgcbg/limo-qwen3-8b-math-full-precision_v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Cbgcbg/limo-qwen3-8b-math-full-precision_v3

SGLang

How to use Cbgcbg/limo-qwen3-8b-math-full-precision_v3 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 "Cbgcbg/limo-qwen3-8b-math-full-precision_v3" \
    --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": "Cbgcbg/limo-qwen3-8b-math-full-precision_v3",
		"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 "Cbgcbg/limo-qwen3-8b-math-full-precision_v3" \
        --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": "Cbgcbg/limo-qwen3-8b-math-full-precision_v3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Cbgcbg/limo-qwen3-8b-math-full-precision_v3 with Docker Model Runner:
```
docker model run hf.co/Cbgcbg/limo-qwen3-8b-math-full-precision_v3
```

LIMO-Qwen3-8B-Math-Full-Precision-v2

Full-precision (bfloat16) merged model trained with LIMO methodology for mathematical reasoning.

Model Details

Base Model: Qwen/Qwen3-8B (full precision)
Training Method: LIMO (Less is More for Reasoning)
Dataset: GAIR/LIMO (817 high-quality samples)
Training Approach: LoRA fine-tuning → Full merge
Model Size: ~16GB (full precision)
Precision: bfloat16

Training Configuration

LoRA Rank: 8 (conservative)
Learning Rate: 5e-6 (conservative)
Epochs: 1 (prevents overfitting)
Batch Size: 2 (memory optimized)
Gradient Accumulation: 4

Expected Performance

Elementary Math: +2-4% improvement over base Qwen3-8B
High School Math: +2-4% improvement over base Qwen3-8B
Reasoning Quality: Enhanced step-by-step mathematical reasoning

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load model
model = AutoModelForCausalLM.from_pretrained(
    "Cbgcbg/limo-qwen3-8b-math-full-precision_v3",
    torch_dtype=torch.bfloat16,
    device_map="auto",
    trust_remote_code=True
)

tokenizer = AutoTokenizer.from_pretrained(
    "Cbgcbg/limo-qwen3-8b-math-full-precision_v3",
    trust_remote_code=True
)

# Example usage
messages = [
    {"role": "user", "content": "Solve: 2x + 3 = 11"}
]

text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)

with torch.no_grad():
    outputs = model.generate(
        **inputs,
        max_new_tokens=512,
        temperature=0.7,
        do_sample=True
    )

response = tokenizer.decode(outputs[0][len(inputs.input_ids[0]):], skip_special_tokens=True)
print(response)

Model Comparison

Model	Size	Precision	Performance
Original Gasing-8B	15.26 GB	Full	✅ Baseline
Previous LIMO (quantized)	5.55 GB	4-bit	❌ Degraded
This LIMO (full precision)	~16 GB	bfloat16	✅ Expected +2-4%

Training Details

This model was trained using the LIMO methodology, which demonstrates that high-quality mathematical reasoning can be achieved with minimal but carefully curated training data (817 samples vs typical 100k+ datasets).

Key improvements:

✅ Perfect format alignment with evaluation benchmarks
✅ Conservative training parameters to prevent overfitting
✅ Full precision training and inference
✅ High-quality reasoning chains from GAIR/LIMO dataset

Citation

If you use this model, please cite the LIMO paper:

@misc{ye2025limo,
    title={LIMO: Less is More for Reasoning},
    author={Yixin Ye and Zhen Huang and Yang Xiao and Ethan Chern and Shijie Xia and Pengfei Liu},
    year={2025},
    eprint={2502.03387},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}