Uploaded model

  • Developed by: zhulei777
  • License: apache-2.0
  • Finetuned from model : llm-jp/llm-jp-3-13b

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

USE MODEL

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。 """

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 = "zhulei777/llm-jp-3-13b-finetune-zhu6"

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 = "your 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("./elyza-tasks-100-TV_0.jsonl", "r") as f: item = "" for line in f: line = line.strip() item += line if item.endswith("}"): try: datasets.append(json.loads(item)) item = "" except json.JSONDecodeError as e: print(f"Error decoding JSON on line: {line}") print(f"Error message: {e}")

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})

with open(f"./llm-jp-3-13b-finetune-zhu6_output.jsonl", 'w', encoding='utf-8') as f: for result in results: json.dump(result, f, ensure_ascii=False) f.write('\n')

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 zhulei777/llm-jp-3-13b-finetune-zhu6

Finetuned
(1120)
this model