Instructions to use hongyin/informer-0.2b-4k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hongyin/informer-0.2b-4k with Transformers:

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

pipe = pipeline("text-generation", model="hongyin/informer-0.2b-4k")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("hongyin/informer-0.2b-4k")
model = AutoModelForCausalLM.from_pretrained("hongyin/informer-0.2b-4k", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hongyin/informer-0.2b-4k with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hongyin/informer-0.2b-4k"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hongyin/informer-0.2b-4k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/hongyin/informer-0.2b-4k

SGLang

How to use hongyin/informer-0.2b-4k 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 "hongyin/informer-0.2b-4k" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hongyin/informer-0.2b-4k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "hongyin/informer-0.2b-4k" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hongyin/informer-0.2b-4k",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hongyin/informer-0.2b-4k with Docker Model Runner:
```
docker model run hf.co/hongyin/informer-0.2b-4k
```

hongyin/informer-0.2b

I am pleased to introduce to you an English-Chinese bilingual autoregressive language model. This model is trained from scratch and has a unique vocabulary and 20 million parameters based on the LLAMA2 model structure. Our goal is to provide a solution that is computationally cheap and easy to inference. It's important to note that this is a base model, not intended to be used as a chatbot, but rather for alchemy. We look forward to providing you with a practical model product.

To put aside the damn high-sounding words, the name of each model has rich connotations and personal experience, including the previous model, and it is worth reminding us repeatedly.

Bibtex entry and citation info

Please cite if you find it helpful.

@article{zhu2023metaaid,
  title={MetaAID 2.0: An Extensible Framework for Developing Metaverse Applications via Human-controllable Pre-trained Models},
  author={Zhu, Hongyin},
  journal={arXiv preprint arXiv:2302.13173},
  year={2023}
}

license: other

Downloads last month: 9

Paper for hongyin/informer-0.2b-4k

MetaAID 2.0: An Extensible Framework for Developing Metaverse Applications via Human-controllable Pre-trained Models

Paper • 2302.13173 • Published Feb 25, 2023