Qwen3-4B-SFT-Claude-Opus-Reasoning-Unsloth

This model is a fine-tuned version of Qwen3-4B (Unsloth 4-bit) optimized for reasoning distillation (chain-of-thought) using Unsloth for 2x faster training and 60% less VRAM.

Trained on the claude-reasoning-distillation dataset, which contains 10,477 samples of Claude's reasoning traces with <think> blocks for chain-of-thought learning.

Overview

Training Configuration

SFT + LoRA Settings

LoRA Configuration

Dataset

Hardware

Training Outcome

Usage

Quick Start (Transformers)

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "ermiaazarkhalili/Qwen3-4B-SFT-Claude-Opus-Reasoning-Unsloth"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {"role": "user", "content": "Solve step by step: What is the sum of the first 10 prime numbers?"}
]

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

outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True)
response = tokenizer.decode(outputs[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
print(response)

Using with Unsloth (Fastest)

from unsloth import FastLanguageModel

model, tokenizer = FastLanguageModel.from_pretrained(
    "ermiaazarkhalili/Qwen3-4B-SFT-Claude-Opus-Reasoning-Unsloth",
    max_seq_length=2048,
    load_in_4bit=True,
)

4-bit Quantized Inference

from transformers import AutoModelForCausalLM, BitsAndBytesConfig
import torch

quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.bfloat16,
    bnb_4bit_use_double_quant=True,
    bnb_4bit_quant_type="nf4",
)

model = AutoModelForCausalLM.from_pretrained(
    "ermiaazarkhalili/Qwen3-4B-SFT-Claude-Opus-Reasoning-Unsloth",
    quantization_config=quantization_config,
    device_map="auto",
)

GGUF Versions

Quantized GGUF versions for CPU and edge inference are available at: Qwen3-4B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF

Using with Ollama

ollama pull hf.co/ermiaazarkhalili/Qwen3-4B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF:Q4_K_M
ollama run hf.co/ermiaazarkhalili/Qwen3-4B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF:Q4_K_M "Solve step by step: What is the sum of the first 10 prime numbers?"

Using with llama.cpp

./llama-cli -m Qwen3-4B-SFT-Claude-Opus-Reasoning-Unsloth-Q4_K_M.gguf -p "Solve step by step: What is the sum of the first 10 prime numbers?" -n 512

Limitations

• Language: Primarily trained on English data
• Knowledge Cutoff: Limited to base model's training data cutoff
• Hallucinations: May generate plausible-sounding but incorrect information
• Context Length: Fine-tuned with 2,048 token context window
• Safety: Not extensively safety-tuned; use with appropriate guardrails

Training Framework Versions

Citation

@misc{ermiaazarkhalili_qwen3_4b_sft_claude_opus_reasoning_unsloth,
    author = {ermiaazarkhalili},
    title = {Qwen3-4B-SFT-Claude-Opus-Reasoning-Unsloth: Fine-tuned Qwen3-4B (Unsloth 4-bit) with Unsloth},
    year = {2026},
    publisher = {Hugging Face},
    howpublished = {\url{https://huggingface.co/ermiaazarkhalili/Qwen3-4B-SFT-Claude-Opus-Reasoning-Unsloth}}
}

Acknowledgments

• Unsloth for 2x faster fine-tuning
• Base model developers (unsloth)
• Hugging Face TRL Team for the training library
• Claude Reasoning Distillation dataset
• Compute Canada / DRAC for HPC resources