Instructions to use tensorhydra/qwen3-8b-aimo3-tir with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tensorhydra/qwen3-8b-aimo3-tir with Transformers:

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

pipe = pipeline("text-generation", model="tensorhydra/qwen3-8b-aimo3-tir")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("tensorhydra/qwen3-8b-aimo3-tir")
model = AutoModelForMultimodalLM.from_pretrained("tensorhydra/qwen3-8b-aimo3-tir")
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 Settings

vLLM

How to use tensorhydra/qwen3-8b-aimo3-tir with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tensorhydra/qwen3-8b-aimo3-tir"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tensorhydra/qwen3-8b-aimo3-tir",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tensorhydra/qwen3-8b-aimo3-tir

SGLang

How to use tensorhydra/qwen3-8b-aimo3-tir 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 "tensorhydra/qwen3-8b-aimo3-tir" \
    --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": "tensorhydra/qwen3-8b-aimo3-tir",
		"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 "tensorhydra/qwen3-8b-aimo3-tir" \
        --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": "tensorhydra/qwen3-8b-aimo3-tir",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tensorhydra/qwen3-8b-aimo3-tir with Docker Model Runner:
```
docker model run hf.co/tensorhydra/qwen3-8b-aimo3-tir
```

Qwen3-8B AIMO3 Tool-Integrated Reasoning

Model Summary

A LoRA fine-tuned version of Qwen-8B trained for tool-integrated reasoning on the AIMO3 competition dataset (generated by GPT-OSS-120B). The LoRA adapters have been merged into the base model and saved in SafeTensors format for straightforward deployment.

Property	Details
Base Model	Qwen-8B
Fine-tuning Method	LoRA (merged)
Format	SafeTensors (BF16)
Parameters	~8B
Disk Size	~16GB
Max Context	8192 tokens

Model Details

LoRA Configuration

Hyperparameter	Value
Rank (r)	16
Alpha	32
Dropout	0.05
Bias	none
Target Modules	`q_proj`, `k_proj`, `v_proj`, `o_proj`, `gate_proj`, `up_proj`, `down_proj`

Training Hyperparameters

Hyperparameter	Value
Precision	BFloat16 (no quantization)
Epochs	2
Steps	8750 (~1 epoch)
Per-device Batch Size	2
Gradient Accumulation Steps	8 (effective batch: 16)
Learning Rate	2e-4
LR Scheduler	Cosine with warmup
Warmup Ratio	0.03
Weight Decay	0.01
Max Gradient Norm	1.0
Max Sequence Length	8192
Optimizer	AdamW (Fused)

Hardware & Infrastructure

Platform: Kaggle
GPU: Single NVIDIA H100 (80GB)
Attention: Flash Attention 2
Optimizations: Gradient checkpointing, TF32, fused optimizer

Training Data

Dataset: AIMO3 Tool-Integrated Reasoning Dataset (synthesized by GPT-OSS-120B)
Split: 97.5% train / 2.5% validation
Format: CSV with problem–solution pairs

Supported column names:

Input: problem, question, input, prompt
Output: solution, answer, output, response, completion

Instruction Format

Training uses a ChatML-style format:

<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
{response}<|im_end|>

Training Loss

The model is trained for 8750 steps (~ 1 epoch) before stopping. Below are the train and validation loss curves for the entire training session.

Usage

Load the Model

Since the LoRA adapters are already merged, PEFT is not required:

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "tensorhydra/qwen-8b-aimo3-reasoning",
    trust_remote_code=True,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

tokenizer = AutoTokenizer.from_pretrained(
    "tensorhydra/qwen-8b-aimo3-reasoning",
    trust_remote_code=True
)

Inference

prompt = "Solve this problem: What is 2 + 2?"

formatted_prompt = f"user\n{prompt}\nassistant\n"

inputs = tokenizer(formatted_prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=512,
    temperature=0.7,
    top_p=0.9,
    do_sample=True
)

response = tokenizer.decode(outputs[0], skip_special_tokens=False)
print(response)

Batch Inference

prompts = [
    "Solve: 15 + 27 = ?",
    "What is the derivative of x^2?",
    "Calculate the area of a circle with radius 5"
]

formatted_prompts = [
    f"user\n{p}\nassistant\n"
    for p in prompts
]

inputs = tokenizer(formatted_prompts, return_tensors="pt", padding=True).to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True)

for response in tokenizer.batch_decode(outputs, skip_special_tokens=False):
    print(response)
    print("-" * 80)

Quantized Inference (Lower VRAM)

# 8-bit (~8GB VRAM)
model = AutoModelForCausalLM.from_pretrained(
    "tensorhydra/qwen-8b-aimo3-reasoning",
    load_in_8bit=True,
    device_map="auto"
)

# 4-bit (~4GB VRAM)
model = AutoModelForCausalLM.from_pretrained(
    "tensorhydra/qwen-8b-aimo3-reasoning",
    load_in_4bit=True,
    device_map="auto"
)

Memory Requirements

Mode	VRAM
BF16 (full)	~16GB
8-bit quantized	~8GB
4-bit quantized	~4GB

Repository Structure

model/
├── config.json
├── generation_config.json
├── model.safetensors.index.json
├── model-00001-of-0000X.safetensors
├── ...
├── tokenizer_config.json
├── tokenizer.json
└── special_tokens_map.json

Intended Use

Mathematical reasoning and problem solving
Tool-integrated step-by-step reasoning
Educational and research applications
Production deployment (merged model, no PEFT dependency)

Limitations

Fine-tuned on a narrow reasoning domain; may not generalize well to other tasks
Hard context limit of 8192 tokens
Performance is bounded by the quality and distribution of the synthetic training data
Full merged model requires ~16GB storage (vs. ~100–200MB for LoRA adapters alone)

Citation

@misc{qwen-lora-aimo3,
  title   = {Qwen-8B LoRA Fine-tuned for Tool-Integrated Reasoning},
  author  = {tensorhydra},
  year    = {2025},
  howpublished = {Kaggle Model Hub},
  note    = {Merged LoRA model in SafeTensors format}
}

Acknowledgements

Base model: Qwen-8B by Alibaba Cloud
Training frameworks: Hugging Face Transformers & PEFT
Dataset synthesis: GPT-OSS-120B
Serialization: SafeTensors
Training platform: Kaggle (H100 GPU)

License

This model inherits the license of the base Qwen-8B model. Please refer to the Qwen license terms before use.

Downloads last month: 5

Safetensors

Model size

8B params

Tensor type

BF16

tensorhydra
/

qwen3-8b-aimo3-tir