Downloads · 30 days
0
kensir0u/llm-jp-3-13b-it-2_lora
llm-jp-3-13b-it-2_lora is a machine learning model from kensir0u. 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.
- Developed by: kensir0u - License: apache-2.0 - Finetuned from model : llm-jp/llm-jp-3-13b
Downloads · 30 days
0
Access
Public
Updated Dec 24, 2024
Repo size
501 MB
Likes
0
Public
Click a slice to open those files.
.safetensors501 MB · 99%
From the Hugging Face model README
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
Hugging Faceにアップロードしたモデルを用いてELYZA-tasks-100-TVの出力を得るためのコードです。
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。
# Commented out IPython magic to ensure Python compatibility.
# %%capture
# !pip install unsloth
# !pip uninstall unsloth -y && pip install --upgrade --no-cache-dir "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
from unsloth import FastLanguageModel
import torch
import json
model_name = "llm-jp-3-13b-it-2_lora"
model_path = "kensir0u/llm-jp-3-13b-it-2_lora"
HF_TOKEN = ""
max_seq_length = 1024
dtype = None
load_in_4bit = True
model, tokenizer = FastLanguageModel.from_pretrained(
model_name = model_path,
max_seq_length = max_seq_length,
dtype = dtype,
load_in_4bit = load_in_4bit,
token = HF_TOKEN,#"HF token",
)
FastLanguageModel.for_inference(model)
# データセットの読み込み。
# omnicampusの開発環境では、左にタスクのjsonlをドラッグアンドドロップしてから実行。
datasets = []
with open("/content/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 = ""
# 学習したモデルを用いてタスクを実行
from tqdm import tqdm
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 = 1024, 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(f"/content/{model_name}_output.jsonl", 'w', encoding='utf-8') as f:
for result in results:
json.dump(result, f, ensure_ascii=False)
f.write('\n')