Instructions to use huihui-ai/MicroThinker-3B-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use huihui-ai/MicroThinker-3B-Preview with Transformers:

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

pipe = pipeline("text-generation", model="huihui-ai/MicroThinker-3B-Preview")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("huihui-ai/MicroThinker-3B-Preview")
model = AutoModelForCausalLM.from_pretrained("huihui-ai/MicroThinker-3B-Preview")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use huihui-ai/MicroThinker-3B-Preview with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "huihui-ai/MicroThinker-3B-Preview"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "huihui-ai/MicroThinker-3B-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/huihui-ai/MicroThinker-3B-Preview

SGLang

How to use huihui-ai/MicroThinker-3B-Preview 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 "huihui-ai/MicroThinker-3B-Preview" \
    --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": "huihui-ai/MicroThinker-3B-Preview",
		"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 "huihui-ai/MicroThinker-3B-Preview" \
        --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": "huihui-ai/MicroThinker-3B-Preview",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use huihui-ai/MicroThinker-3B-Preview with Docker Model Runner:
```
docker model run hf.co/huihui-ai/MicroThinker-3B-Preview
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MicroThinker-3B-Preview

MicroThinker-3B-Preview, a new model fine-tuned from the huihui-ai/Llama-3.2-3B-Instruct-abliterated model, focused on advancing AI reasoning capabilities.

Use with ollama

You can use huihui_ai/microthinker directly

ollama run huihui_ai/microthinker:3b

Training Details

This is just a test, but the performance is quite good.

Now, I'll introduce the test environment.

The model was trained using 1 RTX 4090 GPU(24GB) .

The fine-tuning process used 142k from the FineQwQ-142k dataset, max_length(tokens) 21710, quant_bits 4.

The SFT (Supervised Fine-Tuning) process is divided into several steps, and no code needs to be written.

Create the environment.

conda create -yn ms-swift python=3.11
conda activate ms-swift

git clone https://github.com/modelscope/ms-swift.git

cd ms-swift
pip install -e .
cd ..

Download the model and dataset.

huggingface-cli download huihui-ai/Llama-3.2-3B-Instruct-abliterated --local-dir ./huihui-ai/Llama-3.2-3B-Instruct-abliterated
huggingface-cli download --repo-type  dataset huihui-ai/FineQwQ-142k --local-dir ./data/FineQwQ-142k

Used only the huihui-ai/FineQwQ-142k, Trained for 1 epoch:

swift sft --model huihui-ai/Llama-3.2-3B-Instruct-abliterated --model_type llama3_2 --train_type lora --dataset "data/FineQwQ-142k/FineQwQ-142k.jsonl" --num_train_epochs 1 --per_device_train_batch_size 1 --per_device_eval_batch_size 1 --max_length 21710 --quant_bits 4 --bnb_4bit_compute_dtype bfloat16 --bnb_4bit_quant_storage bfloat16 --lora_rank 8 --lora_alpha 32 --gradient_checkpointing true --weight_decay 0.1 --learning_rate 1e-4 --gradient_accumulation_steps 16 --eval_steps 100 --save_steps 100 --logging_steps 20 --system "You are a helpful assistant. You should think step-by-step." --output_dir output/MicroThinker-3B-Preview/lora/sft --model_author "huihui-ai" --model_name "MicroThinker-3B-Preview"

Save the final fine-tuned model. After you're done, input exit to exit. Replace the directories below with specific ones.

swift infer --model huihui-ai/Llama-3.2-3B-Instruct-abliterated --adapters output/Llama-3.2-3B-Instruct-abliterated/lora/sft/v0-20250106-193759/checkpoint-8786 --stream true --merge_lora true

This should create a new model directory: checkpoint-8786-merged, Rename the directory to MicroThinker-3B-Preview, Copy or move this directory to the huihui directory.

Perform inference on the final fine-tuned model.

swift infer --model huihui/MicroThinker-3B-Preview --stream true --infer_backend pt --max_new_tokens 8192

Test examples.

How many 'r' characters are there in the word "strawberry"?

Downloads last month: 15

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for huihui-ai/MicroThinker-3B-Preview

Base model

meta-llama/Llama-3.2-3B-Instruct

Finetuned

huihui-ai/Llama-3.2-3B-Instruct-abliterated

Finetuned

(22)

this model

Finetunes

1 model

Quantizations

4 models

Dataset used to train huihui-ai/MicroThinker-3B-Preview

Collection including huihui-ai/MicroThinker-3B-Preview

MicroThinker

Collection

4 items • Updated Jan 14, 2025 • 1