Downloads · 30 days
0
ishikawakazuhiko/llm-jp-3-13b-it_20241208_lora
llm-jp-3-13b-it_20241208_lora is a machine learning model from ishikawakazuhiko. 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: ishikawakazuhiko - License: apache-2.0 - Finetuned from model : llm-jp/llm-jp-3-13b
Downloads · 30 days
0
Access
Public
Updated Dec 8, 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.
# ELYZA-tasks-100-TVの読み込み。事前にファイルをアップロードしてください
# 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。
import json
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
# 推論するためにモデルのモードを変更
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})
# jsonlで保存
with open(f"{new_model_id}_output.jsonl", 'w', encoding='utf-8') as f:
for result in results:
json.dump(result, f, ensure_ascii=False)
f.write('\n')
# LoRAアダプタだけ保存
model.push_to_hub_merged(
new_model_id+"_lora",
tokenizer=tokenizer,
save_method="lora",
token=HF_TOKEN,
private=True
)