Instructions to use MBZUAI/LaMini-Neo-125M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MBZUAI/LaMini-Neo-125M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="MBZUAI/LaMini-Neo-125M")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("MBZUAI/LaMini-Neo-125M") model = AutoModelForCausalLM.from_pretrained("MBZUAI/LaMini-Neo-125M") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use MBZUAI/LaMini-Neo-125M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "MBZUAI/LaMini-Neo-125M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "MBZUAI/LaMini-Neo-125M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/MBZUAI/LaMini-Neo-125M
- SGLang
How to use MBZUAI/LaMini-Neo-125M 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 "MBZUAI/LaMini-Neo-125M" \ --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": "MBZUAI/LaMini-Neo-125M", "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 "MBZUAI/LaMini-Neo-125M" \ --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": "MBZUAI/LaMini-Neo-125M", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use MBZUAI/LaMini-Neo-125M with Docker Model Runner:
docker model run hf.co/MBZUAI/LaMini-Neo-125M
Update README.md
Browse files
README.md
CHANGED
|
@@ -141,12 +141,20 @@ More information needed
|
|
| 141 |
# Citation
|
| 142 |
|
| 143 |
```bibtex
|
| 144 |
-
@
|
| 145 |
-
|
| 146 |
-
|
| 147 |
-
|
| 148 |
-
|
| 149 |
-
|
| 150 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 151 |
}
|
|
|
|
| 152 |
```
|
|
|
|
| 141 |
# Citation
|
| 142 |
|
| 143 |
```bibtex
|
| 144 |
+
@article{lamini-lm,
|
| 145 |
+
author = {Minghao Wu and
|
| 146 |
+
Abdul Waheed and
|
| 147 |
+
Chiyu Zhang and
|
| 148 |
+
Muhammad Abdul-Mageed and
|
| 149 |
+
Alham Fikri Aji
|
| 150 |
+
},
|
| 151 |
+
title = {LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions},
|
| 152 |
+
journal = {CoRR},
|
| 153 |
+
volume = {abs/2304.14402},
|
| 154 |
+
year = {2023},
|
| 155 |
+
url = {https://arxiv.org/abs/2304.14402},
|
| 156 |
+
eprinttype = {arXiv},
|
| 157 |
+
eprint = {2304.14402}
|
| 158 |
}
|
| 159 |
+
|
| 160 |
```
|