71 lines
1.8 KiB
Markdown
71 lines
1.8 KiB
Markdown
---
|
||
library_name: transformers
|
||
license: apache-2.0
|
||
language:
|
||
- ja
|
||
base_model:
|
||
- Qwen/Qwen2.5-7B-Instruct
|
||
pipeline_tag: text-generation
|
||
---
|
||
## ABEJA-Qwen2.5-7b-Japanese-v0.1
|
||
|
||
ABEJA-Qwen2.5-7b-Japanese-v0.1はQwen/Qwen2.5-7B-Instructをベースに日本語の学習をしたモデルです。
|
||
通常の継続事前学習ではなく、abeja/ABEJA-Qwen2.5-32b-Japanese-v0.1をベースに蒸留学習を実施したモデルです。
|
||
Post-Traningは実施しておらず、ChatVector(Qwen/Qwen2.5-7B-InstructとQwen/Qwen2.5-7B の差分ベクトル)により指示追従性能をあげています。
|
||
|
||
詳細はABEJAのテックブログを参照してください。
|
||
|
||
|
||
|
||
## 使い方
|
||
|
||
```Python
|
||
import torch
|
||
from transformers import AutoModelForCausalLM, AutoTokenizer
|
||
|
||
model_name = "abeja/ABEJA-Qwen2.5-7b-Japanese-v0.1"
|
||
|
||
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 |