hassanshka/Biomni-R0-32B-LoRA-Rank256

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

# Load base model
base_model = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen3-32B",
    device_map="auto",
    torch_dtype="auto",
    trust_remote_code=True
)

# Load LoRA adapter
model = PeftModel.from_pretrained(base_model, "hassanshka/Biomni-R0-32B-LoRA-Rank256")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-32B")

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

from vllm import LLM, SamplingParams

llm = LLM(
    model="Qwen/Qwen3-32B",
    enable_lora=True,
    max_lora_rank=256
)

# Load LoRA at runtime
output = llm.generate(
    prompts,
    lora_request=LoRARequest("biomni", 1, "hassanshka/Biomni-R0-32B-LoRA-Rank256")
)

mergekit-extract-lora \
    --model "biomni/Biomni-R0-32B-Preview" \
    --base-model "Qwen/Qwen3-32B" \
    --out-path "./lora_output" \
    --max-rank 256 \
    --device cuda