File size: 2,924 Bytes
afda711 6c3ecdb |
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 99 100 101 102 103 |
---
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:** holy0516
- **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)
# 出力までの流れ
- 1. 必要なライブラリのインストール・インポート
2. ベースモデルの読み込みとLoRAアダプタの指定
3. Hugging Face Tokenの指定
4. 元モデルのロード
5. LoRAアダプタの結合
6. タスクの読み込み
7. 推論
8. 出力
# コード
## 1. 必要なライブラリのインストール・インポート
!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
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
from unsloth import FastLanguageModel
import torch
from tqdm import tqdm
import json
## 2. ベースモデルの読み込みとLoRAアダプタの指定
model_id = "llm-jp/llm-jp-3-13b"
adapter_id = "holy0516/llm-jp-3-13b-it-r1_elyza100-r4"
## 3. Hugging Face Tokenの指定
(略)
## 4. 元モデルのロード
dtype = None # Noneにしておけば自動で設定
load_in_4bit = True # 今回は13Bモデルを扱うためTrue
model, tokenizer = FastLanguageModel.from_pretrained(
model_name=model_id,
dtype=dtype,
load_in_4bit=load_in_4bit,
trust_remote_code=True,
)
# 5. LoRAのアダプタの統合
model = PeftModel.from_pretrained(model, adapter_id, token = HF_TOKEN)
# 6. タスクの読み込み
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 = ""
# 7. 推論
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})
# 8. 出力結果の保存
with open(f"output.jsonl", 'w', encoding='utf-8') as f:
for result in results:
json.dump(result, f, ensure_ascii=False)
f.write('\n') |