Uploaded model

  • Developed by: kochan13
  • License: apache-2.0
  • Finetuned from model : kochan13/llm-jp-3-13b-8

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

以下コードにて推論・出力

推論用コード

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。

# ライブラリのンストール
%%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

!pip install httpx==0.27.2

# model,tokenizerの読み込み。
model_name = "kochan13/llm-jp-3-13b-19_lora" 

max_seq_length = 2048
dtype = None
load_in_4bit = True

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = model_name,
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
    token = "my_HF_token", #"HF token",
)
FastLanguageModel.for_inference(model)

# データセットの読み込み。
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 = ""

from tqdm import tqdm

# 推論
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})

import os

# 結果をjsonlで保存
filename = f"{model_name.split('/')[-1]}_output.jsonl"  # モデル名の末尾部分だけを使用
filepath = os.path.join("/content", filename)  # Join the directory and filename

# 保存処理
with open(filepath, 'w', encoding='utf-8') as f:
    for result in results:
        json.dump(result, f, ensure_ascii=False)
        f.write('\n')

print(f"Results saved to: {filepath}")
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.

Model tree for kochan13/llm-jp-3-13b-19_lora

Finetuned
(3)
this model