Instructions to use whynlp/tinyllama-zh with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use whynlp/tinyllama-zh with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="whynlp/tinyllama-zh")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("whynlp/tinyllama-zh")
model = AutoModelForCausalLM.from_pretrained("whynlp/tinyllama-zh", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use whynlp/tinyllama-zh with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "whynlp/tinyllama-zh"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "whynlp/tinyllama-zh",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/whynlp/tinyllama-zh

SGLang

How to use whynlp/tinyllama-zh 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 "whynlp/tinyllama-zh" \
    --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": "whynlp/tinyllama-zh",
		"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 "whynlp/tinyllama-zh" \
        --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": "whynlp/tinyllama-zh",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use whynlp/tinyllama-zh with Docker Model Runner:
```
docker model run hf.co/whynlp/tinyllama-zh
```

whynlp commited on Mar 11, 2024

Commit

bb24762

verified ·

1 Parent(s): 9ffb4b7

Update README.md

Browse files

Files changed (1) hide show

README.md +36 -0

README.md CHANGED Viewed

@@ -1,3 +1,39 @@
 ---
 license: mit
 ---

 ---
 license: mit
+datasets:
+- p208p2002/wudao
+language:
+- zh
 ---
+# Chinese TinyLlama
+A demo project that pretrains a tinyllama on Chinese corpora, with minimal modification to the huggingface transformers code. It serves as a use case to demonstrate how to use the huggingface version [TinyLlama](https://github.com/whyNLP/tinyllama) to pretrain a model on a large corpus.
+See the [Github Repo](https://github.com/whyNLP/tinyllama-zh) for more details.
+## Usage
+```python
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("whynlp/tinyllama-zh", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("whynlp/tinyllama-zh")
+```
+## Model Details
+### Model Description
+This model is trained on [WuDaoCorpora Text](https://www.scidb.cn/en/detail?dataSetId=c6a3fe684227415a9db8e21bac4a15ab). The dataset contains about 45B tokens and the model is trained for 2 epochs. The training takes about 6 days on 8 A100 GPUs.
+The model uses the `THUDM/chatglm3-6b` tokenizer from huggingface.
+- **Model type:** Llama
+- **Language(s) (NLP):** Chinese
+- **License:** MIT
+- **Finetuned from model [optional]:** TinyLlama-2.5T checkpoint
+## Uses
+The model does not perform very well (The CMMLU result is slightly above 25). For better performance, one may use a better corpus (e.g. [wanjuan](https://opendatalab.org.cn/OpenDataLab/WanJuan1_dot_0)). Again, this project only serves as a demonstration of how to pretrain a TinyLlama on a large corpus.