70 lines
1.7 KiB
Markdown
70 lines
1.7 KiB
Markdown
|
---
|
|||
|
|
library_name: transformers
|
|||
|
|
license: apache-2.0
|
|||
|
|
language:
|
|||
|
|
- ja
|
|||
|
|
base_model:
|
|||
|
|
- Qwen/Qwen2.5-32B-Instruct
|
|||
|
|
- abeja/ABEJA-Qwen2.5-32b-Japanese-v0.1
|
|||
|
|
pipeline_tag: text-generation
|
|||
|
|
---
|
|||
|
|
## ABEJA-Qwen2.5-32b-Japanese-v1.0
|
|||
|
|
|
|||
|
|
`ABEJA-Qwen2.5-32b-Japanese-v1.0`は`Qwen/Qwen2.5-32B-Instruct`をベースに日本語中心とした継続事前学習を実施したモデル`abeja/ABEJA-Qwen2.5-32b-Japanese-v0.1`に対してSFTとDPOによる事後学習を実施したモデルです。
|
|||
|
|
|
|||
|
|
詳細はABEJAのテックブログを参照してください。
|
|||
|
|
|
|||
|
|
https://tech-blog.abeja.asia/entry/geniac2-qwen25-32b-v1.0
|
|||
|
|
|
|||
|
|
## 使い方
|
|||
|
|
|
|||
|
|
```Python
|
|||
|
|
import torch
|
|||
|
|
from transformers import AutoModelForCausalLM, AutoTokenizer
|
|||
|
|
|
|||
|
|
model_name = "abeja/ABEJA-Qwen2.5-32b-Japanese-v1.0"
|
|||
|
|
|
|||
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|||
|
|
model_name,
|
|||
|
|
torch_dtype="auto",
|
|||
|
|
device_map="auto"
|
|||
|
|
)
|
|||
|
|
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
|||
|
|
|
|||
|
|
prompt = "人とAIが協調するためには？"
|
|||
|
|
messages = [
|
|||
|
|
{"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
|
|||
|
|
{"role": "user", "content": prompt}
|
|||
|
|
]
|
|||
|
|
text = tokenizer.apply_chat_template(
|
|||
|
|
messages,
|
|||
|
|
tokenize=False,
|
|||
|
|
add_generation_prompt=True
|
|||
|
|
)
|
|||
|
|
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
|
|||
|
|
|
|||
|
|
generated_ids = model.generate(
|
|||
|
|
**model_inputs,
|
|||
|
|
max_new_tokens=512
|
|||
|
|
)
|
|||
|
|
generated_ids = [
|
|||
|
|
output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
|
|||
|
|
]
|
|||
|
|
|
|||
|
|
response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
|
|||
|
|
|
|||
|
|
print(response)
|
|||
|
|
```
|
|||
|
|
|
|||
|
|
## 開発者
|
|||
|
|
|
|||
|
|
- Hiroshi Kiyota
|
|||
|
|
- Keisuke Fujimoto
|
|||
|
|
- Kentaro Nakanishi
|
|||
|
|
- Kyo Hattori
|
|||
|
|
- Shinya Otani
|
|||
|
|
- Shogo Muranushi
|
|||
|
|
- Takuma Kume
|
|||
|
|
- Tomoki Manabe
|
|||
|
|
|
|||
|
|
(*)アルファベット順
|