metadata
base_model: meta-llama/Meta-Llama-3.1-8B
language:
- ko
license: apache-2.0
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
base_model = 'bigdefence/Llama-3.1-8B-Ko-bigdefence'
device = 'cuda' if torch.cuda.is_available() else 'cpu'
tokenizer = AutoTokenizer.from_pretrained(base_model)
model = AutoModelForCausalLM.from_pretrained(base_model, torch_dtype=torch.float16, device_map="auto")
model.eval()
def generate_response(prompt, model, tokenizer, text_streamer,max_new_tokens=256):
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=True)
inputs = inputs.to(model.device)
with torch.no_grad():
outputs = model.generate(
**inputs,
streamer=text_streamer,
max_new_tokens=max_new_tokens,
do_sample=True,
pad_token_id=tokenizer.eos_token_id
)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
return response.replace(prompt, '').strip()
key = "์๋
?"
prompt = f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
### Instruction:
{key}
### Response:
"""
text_streamer = TextStreamer(tokenizer)
response = generate_response(prompt, model, tokenizer,text_streamer)
print(response)
Uploaded model
- Developed by: Bigdefence
- License: apache-2.0
- Finetuned from model : meta-llama/Meta-Llama-3.1-8B
- Dataset : MarkrAI/KoCommercial-Dataset
Thanks
- ํ๊ตญ์ด LLM ์คํ์ํ๊ณ์ ๋ง์ ๊ณตํ์ ํด์ฃผ์ , Beomi ๋๊ณผ maywell ๋, MarkrAI๋ ๊ฐ์ฌ์ ์ธ์ฌ ๋๋ฆฝ๋๋ค.
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.