Qwen-3-4B-finetuned-PathoPreter-Rohit

from unsloth import FastLanguageModel

# 1. Load the model
model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "YADAV0206/Qwen-3-4B-finetuned-PathoPreter-Rohit",
    max_seq_length = 2048,
    load_in_4bit = True,
)
FastLanguageModel.for_inference(model)

# 2. Define the input prompt
prompt = """
Variant: NM_000059.4(BRCA2):c.8499G>A (p.Lys2833=)
Associated conditions: Hereditary breast ovarian cancer syndrome
### Response:
"""

# 3. Inference
inputs = tokenizer([prompt], return_tensors = "pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens = 12)
print(tokenizer.batch_decode(outputs))