Instructions to use GeneZC/MiniChat-1.5-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GeneZC/MiniChat-1.5-3B with Transformers:

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

pipe = pipeline("text-generation", model="GeneZC/MiniChat-1.5-3B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GeneZC/MiniChat-1.5-3B")
model = AutoModelForCausalLM.from_pretrained("GeneZC/MiniChat-1.5-3B")
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 GeneZC/MiniChat-1.5-3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GeneZC/MiniChat-1.5-3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GeneZC/MiniChat-1.5-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GeneZC/MiniChat-1.5-3B

SGLang

How to use GeneZC/MiniChat-1.5-3B 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 "GeneZC/MiniChat-1.5-3B" \
    --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": "GeneZC/MiniChat-1.5-3B",
		"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 "GeneZC/MiniChat-1.5-3B" \
        --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": "GeneZC/MiniChat-1.5-3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use GeneZC/MiniChat-1.5-3B with Docker Model Runner:
```
docker model run hf.co/GeneZC/MiniChat-1.5-3B
```

GeneZC commited on Nov 26, 2023

Commit

886af96

1 Parent(s): 93935eb

Update README.md

Browse files

Files changed (1) hide show

README.md +6 -3

README.md CHANGED Viewed

@@ -10,7 +10,12 @@ widget:
 ## MiniChat-1.5-3B
-📑 [arXiv](https://arxiv.org/abs/2311.07052) | 👻 [GitHub](https://github.com/GeneZC/MiniMA) | 🤗 [HuggingFace-MiniMA](https://huggingface.co/GeneZC/MiniMA-3B) | 🤗 [HuggingFace-MiniChat](https://huggingface.co/GeneZC/MiniChat-3B) | 🤖 [ModelScope-MiniMA](https://modelscope.cn/models/GeneZC/MiniMA-3B) | 🤖 [ModelScope-MiniChat](https://modelscope.cn/models/GeneZC/MiniChat-3B)
 ❗ Must comply with LICENSE of LLaMA2 since it is derived from LLaMA2.
@@ -18,8 +23,6 @@ A language model distilled and finetuned from an adapted version of LLaMA2-7B fo
 Outperforming a wide range of 3B competitors in GPT4 evaluation and even competing with several 7B chat models.
-**Updates from MiniChat-3B**: 1) better data mixture; 2) use of [NEFTune](https://arxiv.org/abs/2310.05914); 3) use of [DPO](https://arxiv.org/abs/2305.18290)
 <img src="./teaser_b.jpg" alt="teaser_b" width="687" />
 The following is an example code snippet to use MiniChat-3B:

 ## MiniChat-1.5-3B
+📑 [arXiv](https://arxiv.org/abs/2311.07052) | 👻 [GitHub](https://github.com/GeneZC/MiniMA) | 🤗 [HuggingFace-MiniMA](https://huggingface.co/GeneZC/MiniMA-3B) | 🤗 [HuggingFace-MiniChat](https://huggingface.co/GeneZC/MiniChat-3B) | 🤗 [HuggingFace-MiniChat-1.5](https://huggingface.co/GeneZC/MiniChat-1.5-3B) | 🤖 [ModelScope-MiniMA](https://modelscope.cn/models/GeneZC/MiniMA-3B) | 🤖 [ModelScope-MiniChat](https://modelscope.cn/models/GeneZC/MiniChat-3B)
+🆕 **Updates from MiniChat-3B**:
+- better data mixture;
+- use of [NEFTune](https://arxiv.org/abs/2310.05914);
+- use of [DPO](https://arxiv.org/abs/2305.18290).
 ❗ Must comply with LICENSE of LLaMA2 since it is derived from LLaMA2.
 Outperforming a wide range of 3B competitors in GPT4 evaluation and even competing with several 7B chat models.
 <img src="./teaser_b.jpg" alt="teaser_b" width="687" />
 The following is an example code snippet to use MiniChat-3B: