|
Download README.md from tklohj/windyfllm2.2: direct link, hf CLI and curl.
- Browser
- Download file 621 Bytes
-
https://huggingface.co/tklohj/windyfllm2.2/resolve/main/README.md
- Command line
-
hf download hf://tklohj/windyfllm2.2/README.md
-
curl -L -o README.md https://huggingface.co/tklohj/windyfllm2.2/resolve/main/README.md
621 Bytes
metadata
license: mit
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
tags:
- llama
- mmlu
- fine-tuned
- windyfllm
datasets:
- cais/mmlu
WindyFLLM 2.2 ๐ช๏ธ
MMLU ๋ฐ์ดํฐ์ ์ผ๋ก ํ์ธํ๋๋ meta-llama/Meta-Llama-3.1-8B-Instruct ๋ชจ๋ธ์ ๋๋ค.
์ฌ์ฉ๋ฒ
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")
model = PeftModel.from_pretrained(base_model, "tklohj/windyfllm2.2")
tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct")