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")
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

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
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

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 to pretrain a model on a large corpus.

See the Github Repo for more details.

Usage

# 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. 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). Again, this project only serves as a demonstration of how to pretrain a TinyLlama on a large corpus.

Downloads last month: 10

Safetensors

Model size

1B params

Tensor type

F32

Model tree for whynlp/tinyllama-zh

Quantizations

2 models

whynlp
/

tinyllama-zh