qwen3-8b-lora-Opus4.6-resoning

Qwen3-8B LoRA Opus4.6 Reasoning

Merged model (base + LoRA) fine-tuned for reasoning tasks using Opus-4.6-Reasoning-3000x-filtered dataset.

Model Details

• Base Model: unsloth/Qwen3-8B
• Training Method: SFT (Supervised Fine-Tuning)
• Framework: Unsloth + TRL

Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "cylnx/qwen3-8b-lora-Opus4.6-resoning",
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("cylnx/qwen3-8b-lora-Opus4.6-resoning", trust_remote_code=True)

messages = [{"role": "user", "content": "Your question here"}]
inputs = tokenizer.apply_chat_template(messages, tokenize=True, return_tensors="pt").to(model.device)
outputs = model.generate(inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0]))