Pongo-70B

only for FFmpeg

Direct Use

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

model_name = "meta-llama/Llama-2-70b-chat-hf"
adapters_name = 'wj2003/Pongo-70B'

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    load_in_4bit=True,
    torch_dtype=torch.bfloat16,
    device_map="auto",
    max_memory={i: '48000MB' for i in range(torch.cuda.device_count())},
    quantization_config=BitsAndBytesConfig(
        load_in_4bit=True,
        bnb_4bit_compute_dtype=torch.bfloat16,
        bnb_4bit_use_double_quant=True,
        bnb_4bit_quant_type='nf4'
    ),
)
model = PeftModel.from_pretrained(model, adapters_name)
tokenizer = AutoTokenizer.from_pretrained(adapters_name)
prompt = "find potential security issues in the following code. If it has vulnerability, " \
         "output: Vulnerabilities " \
         "Detected: type of vulnerability. otherwise output<no vulnerability detected>.Here is the complete code: "

# Provide your code
code=""
formatted_prompt = (
        f"{prompt + code}"
    )
inputs = tokenizer(formatted_prompt,return_tensors="pt").to("cuda:0")
outputs = model.generate(inputs=inputs.input_ids, max_new_tokens=1024)