Instructions to use dummy-foo/ChatGLM3-Japanese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

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
```

dummy-foo commited on Jun 9, 2024

Commit

0aa9c28

verified ·

1 Parent(s): 3dc9a1c

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -6,7 +6,9 @@ language:
 pipeline_tag: text-generation
 ---
 [ChatGLM3-6B](https://github.com/THUDM/ChatGLM3)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。
 共有两个模型：
 - [ChatGLM3-Japanese-Zero]( https://huggingface.co/dummy-foo/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。

 pipeline_tag: text-generation
 ---
 [ChatGLM3-6B](https://github.com/THUDM/ChatGLM3)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]( https://huggingface.co/dummy-foo/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。