Text Generation
Transformers
Safetensors
Japanese
Chinese
English
chatglm
feature-extraction
conversational
custom_code
Instructions to use dummy-foo/ChatGLM3-Japanese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dummy-foo/ChatGLM3-Japanese with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="dummy-foo/ChatGLM3-Japanese", trust_remote_code=True) messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("dummy-foo/ChatGLM3-Japanese", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use dummy-foo/ChatGLM3-Japanese with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "dummy-foo/ChatGLM3-Japanese" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dummy-foo/ChatGLM3-Japanese", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/dummy-foo/ChatGLM3-Japanese
- SGLang
How to use dummy-foo/ChatGLM3-Japanese with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "dummy-foo/ChatGLM3-Japanese" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dummy-foo/ChatGLM3-Japanese", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "dummy-foo/ChatGLM3-Japanese" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dummy-foo/ChatGLM3-Japanese", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use dummy-foo/ChatGLM3-Japanese with Docker Model Runner:
docker model run hf.co/dummy-foo/ChatGLM3-Japanese
How to use from
SGLangUse Docker images
docker run --gpus all \
--shm-size 32g \
-p 30000:30000 \
-v ~/.cache/huggingface:/root/.cache/huggingface \
--env "HF_TOKEN=<secret>" \
--ipc=host \
lmsysorg/sglang:latest \
python3 -m sglang.launch_server \
--model-path "dummy-foo/ChatGLM3-Japanese" \
--host 0.0.0.0 \
--port 30000# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "dummy-foo/ChatGLM3-Japanese",
"messages": [
{
"role": "user",
"content": "What is the capital of France?"
}
]
}'Quick Links
ChatGLM3-6B是一个中英双语大模型,本项目为ChatGLM3-6B加入日文能力。
通过sentencepiece在日文wiki和青空文库上训练BPE的tokenizer,词表扩充14000(64789 -> 78554),相比原生ChatGLM3的日文编码效率提升接近一倍,中文英文编码效率不变。
扩充词表后,在1B tokens上进行增量预训练,然后在22万对话上进行指令微调,得到最终的模型。
共有两个模型:
- ChatGLM3-Japanese-Zero:经过扩词表和resize后的模型,保留了ChatGLM3的中英文能力,尚无日文能力,但因为编码效率高,适合在日文语料上训练。
- ChatGLM3-Japanese:本模型,对ChatGLM3-Japanese-Zero进行日文语料增量预训练和指令微调的模型,可以日文对话。
GitHub上有全流程的代码,包含训练tokenizer和训练模型。
使用样例:
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("dummy-foo/ChatGLM3-Japanese", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("dummy-foo/ChatGLM3-Japanese", trust_remote_code=True, device_map='cuda:0', torch_dtype=torch.float16)
# test Chinese chat
response, _ = model.chat(tokenizer, "你是谁", history=[])
print("\nQ:你是谁,A:", response)
response, _ = model.chat(tokenizer, "你喜欢甜粽子还是咸粽子", history=[])
print("\nQ:你喜欢甜粽子还是咸粽子,A:", response)
# test Japanese chat
response, _ = model.chat(tokenizer, "あなたは誰ですか", history=[])
print("\nQ:あなたは誰ですか,A:", response)
response, _ = model.chat(tokenizer, "すみません、ちょっとお聞きしたいことがあるんですが", history=[])
print("\nQ:すみません、ちょっとお聞きしたいことがあるんですが,A:", response)
# test Japanese tokenizer
print("\ntokens: ", tokenizer.tokenize("恥の多い生涯を送って来ました。自分には、人間の生活というものが、見当つかないのです。"))
- Downloads last month
- 5
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "dummy-foo/ChatGLM3-Japanese" \ --host 0.0.0.0 \ --port 30000# Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "dummy-foo/ChatGLM3-Japanese", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'