PathoPreter-4B-SNV-Pathogen-ClinVar-gnomAD

!pip install transformers accelerate peft bitsandbytes #bitsandbytes-0.49.1
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
from peft import PeftModel

base_model = "unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit"   # same base your adapter was trained on
adapter_repo = "YADAV0206/PathoPreter-4B-SNV-Pathogen-ClinVar-gnomAD"

# Load tokenizer from your repo (it contains added tokens + merges)
tok = AutoTokenizer.from_pretrained(adapter_repo)

# Load base model in 4-bit to save RAM
model = AutoModelForCausalLM.from_pretrained(
    base_model,
    load_in_4bit=True,
    device_map="auto"
)

# Load LoRA adapter weights
model = PeftModel.from_pretrained(model, adapter_repo)

pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tok,
    device_map="auto"
)

#THIS SAMPLE SHOULD OUTPUT PATHOGENIC 
sample = {
"text":"Below is a biological context regarding a genetic variant. Determine if it is Pathogenic or Benign.\n\n### Input:\nGene: CDK8\nVariant: NM_001260.3(CDK8):c.563C>G (p.Ala188Gly)\nLocation: chr13:26385259 C>G\ngnomAD Frequency: 0.000000\n\n### Response:",
"variant_id":"NM_001260.3(CDK8):c.563C>G (p.Ala188Gly)",
"join_key":"NM_001260.3(CDK8):c.563C>G (p.Ala188Gly)",
"Name":"NM_001260.3(CDK8):c.563C>G (p.Ala188Gly)",
"Assembly":"GRCh38",
"chrom":"13",
"pos":"26385259",
"ref":"C",
"alt":"G",
"gnomad_af":0
}

prompt = sample["text"]
print(prompt)

#EXPECTED OUTPUT PATHOGENIC

out = pipe(
    prompt,
    max_new_tokens=50,
    do_sample=True,
    temperature=0.2,
)[0]["generated_text"]

print("\n------ OUTPUT ------")
print(out)