Downloads · 30 days
17
22% of all-time downloads
mou0110/llm-jp-3-13b-1206-finetune2
llm-jp-3-13b-1206-finetune2 is a text generation model from mou0110. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
- Developed by: mou0110 - License: apache-2.0 - Finetuned from model : llm-jp/llm-jp-3-13b
Downloads · 30 days
17
22% of all-time downloads
All-time downloads
76
Public
Repo size
27.9 GB
Likes
0
Public
Click a slice to open those files.
.bin27.4 GB · 98%
From the Hugging Face model README
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
Sample Use
推論用コード 本コードはunslothで学習したqLoRAのアダプタを用いてELYZA-tasks-100-TVの出力を得るためのコードです。 Hugging Faceにアダプタをアップロードしてあることが前提となります。 このコードはunslothライブラリを用いてモデルを読み込み、推論するためのコードとなります。 このコードで生成されたjsonlファイルは課題の成果として提出可能なフォーマットになっております。
※本コードはGoogle Colabでの動作を想定
%%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 = "llm-jp/llm-jp-3-13b" adapter_id = "mou0110/llm-jp-3-13b-1206-finetune2"
HF_TOKEN = "HF_TOKEN" #@param {type:"string"}
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("./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 let's think step by step \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})
json_file_id = re.sub(".*/", "", adapter_id) #with open(f"/content/{json_file_id}_output3.jsonl", 'w', encoding='utf-8') as f: with open(f"{json_file_id}_output3.jsonl", 'w', encoding='utf-8') as f: for result in results: json.dump(result, f, ensure_ascii=False) f.write('\n')