Downloads · 30 days
0
iishiken/gemma2-27bit_lora
gemma2-27bit_lora is a machine learning model from iishiken. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
- Developed by: iishiken - License: apache-2.0 - Finetuned from model : unsloth/gemma-2-27b-bnb-4bit
Downloads · 30 days
0
Access
Public
Updated Dec 8, 2024
Repo size
952 MB
Likes
0
Public
Click a slice to open those files.
.safetensors914 MB · 96%
From the Hugging Face model README
This gemma2 model was trained 2x faster with Unsloth and Huggingface's TRL library.
#sample use
%%capture !pip install unsloth !pip uninstall unsloth -y && pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git" !pip install -U torch !pip install -U peft
from unsloth import FastLanguageModel from peft import PeftModel import torch import json from tqdm import tqdm import re
model_id = "google/gemma-2-27b" adapter_id = "iishiken/gemma2-27bit_lora"
HF_TOKEN = "your_token"
dtype = None # Noneにしておけば自動で設定 load_in_4bit = True # 今回は13Bモデルを扱うためTrue
model, tokenizer = FastLanguageModel.from_pretrained( model_name=model_id, dtype=dtype, load_in_4bit=load_in_4bit, trust_remote_code=True,
model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)
datasets = [] with open("/home/user/LLM勉強コード/LLM2024_最終課題/elyza-tasks-100-TV_0.jsonl", "r") as f: item = "" for line in f: line = line.strip() item += line if item.endswith("}"): datasets.append(json.loads(item)) item = ""
FastLanguageModel.for_inference(model)
results = [] for dt in tqdm(datasets): input = dt["input"]
prompt = f"""### 指示\n{input}\n### 回答\n"""
inputs = tokenizer([prompt], return_tensors = "pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens = 512, use_cache = True, do_sample=False, repetition_penalty=1.2) prediction = tokenizer.decode(outputs[0], skip_special_tokens=True).split('\n### 回答')[-1]
results.append({"task_id": dt["task_id"], "input": input, "output": prediction})
with open("gemmaBIT_output.jsonl", 'w', encoding='utf-8') as f: for result in results: json.dump(result, f, ensure_ascii=False) f.write('\n')