zewial/job-description-generator-llama3-8b

from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
from peft import PeftModel
import torch

# Configuration
model_id = "zewail/job-description-generator-llama3-8b"
base_model = "meta-llama/Meta-Llama-3-8B-Instruct"

# Load with 4-bit quantization
bnb_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_compute_dtype=torch.bfloat16
)

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    base_model,
    quantization_config=bnb_config,
    device_map="auto"
)
model = PeftModel.from_pretrained(model, model_id)

# Generate
prompt = """<|begin_of_text|><|start_header_id|>system<|end_header_id|>

You are an expert HR professional.<|eot_id|><|start_header_id|>user<|end_header_id|>

Generate a job description for Senior Data Scientist in San Francisco, CA.<|eot_id|><|start_header_id|>assistant<|end_header_id|>

"""

inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=400, temperature=0.7, top_p=0.95)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))