File size: 3,240 Bytes
e2f4fe9 7395838 2ac851a 7395838 2ac851a 7395838 ca2919b 2ac851a 7395838 2ac851a 7395838 2ac851a 7395838 fa9625e 7395838 ca2919b 7395838 fa9625e b09ac23 2ac851a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 |
---
base_model: llm-jp/llm-jp-3-13b
tags:
- text-generation-inference
- transformers
- unsloth
- llama
- trl
license: apache-2.0
language:
- en
---
# Uploaded model
- **Developed by:** onewan
- **License:** apache-2.0
- **Finetuned from model :** llm-jp/llm-jp-3-13b
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
# Sample Use
Jupyter notebook、特にGoogle Colaboratoryで動作させることを想定しています
まずは以下のとおりインストールを実行してください
```Python
!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 --upgrade torch
!pip install --upgrade xformers
!pip install ipywidgets --upgrade
```
- 以下のコードを実行する前に、
- コードの中の「--Input your own Hugging Face Token--」の部分にご自身のHugging FaceのTokenを入力してください
- Access Tokens > Create new tokenで、Token typeは「Finegrained」として、Read, Writeをチェックして、取得するとよいでしょう
- "elyza-tasks-100-TV_0.jsonl"を同じフォルダに入れてください
- Colaboratoryの場合は、左のフォルダマークを押して、直下にファイルをドラッグ＆ドロップしてください
```Python
import torch
if torch.cuda.get_device_capability()[0] >= 8:
!pip install --no-deps packaging ninja einops "flash-attn>=2.6.3"
from unsloth import FastLanguageModel
import json
from tqdm import tqdm
import datetime
import pytz
model_name = "onewan/llm-jp-3-13b-finetune-2"
new_model_id = "llm-jp-3-13b-finetune-2"
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 = "--Input your own Hugging Face Token--",
)
FastLanguageModel.for_inference(model)
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{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})
now = datetime.datetime.now(pytz.timezone('Asia/Tokyo')).strftime("%Y%m%d-%H%M%S")
with open(f"{new_model_id}_output_{now}.jsonl", 'w', encoding='utf-8') as f:
for result in results:
json.dump(result, f, ensure_ascii=False)
f.write('\n')
``` |