Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
bloom
Eval Results (legacy)
text-generation-inference
Instructions to use bigscience/bloomz-1b7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigscience/bloomz-1b7 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bigscience/bloomz-1b7")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("bigscience/bloomz-1b7") model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz-1b7") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use bigscience/bloomz-1b7 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bigscience/bloomz-1b7" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bigscience/bloomz-1b7", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bigscience/bloomz-1b7
- SGLang
How to use bigscience/bloomz-1b7 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 "bigscience/bloomz-1b7" \ --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": "bigscience/bloomz-1b7", "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 "bigscience/bloomz-1b7" \ --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": "bigscience/bloomz-1b7", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bigscience/bloomz-1b7 with Docker Model Runner:
docker model run hf.co/bigscience/bloomz-1b7
Commit ·
4ea0141
1
Parent(s): c75f4a9
Update README.md
Browse files
README.md
CHANGED
|
@@ -871,12 +871,10 @@ We refer to Table 7 from our [paper](https://arxiv.org/abs/2211.01786) & [bigsci
|
|
| 871 |
|
| 872 |
# Citation
|
| 873 |
```bibtex
|
| 874 |
-
@
|
| 875 |
-
|
| 876 |
-
|
| 877 |
-
|
| 878 |
-
|
| 879 |
-
archivePrefix={arXiv},
|
| 880 |
-
primaryClass={cs.CL}
|
| 881 |
}
|
| 882 |
```
|
|
|
|
| 871 |
|
| 872 |
# Citation
|
| 873 |
```bibtex
|
| 874 |
+
@article{muennighoff2022crosslingual,
|
| 875 |
+
title={Crosslingual generalization through multitask finetuning},
|
| 876 |
+
author={Muennighoff, Niklas and Wang, Thomas and Sutawika, Lintang and Roberts, Adam and Biderman, Stella and Scao, Teven Le and Bari, M Saiful and Shen, Sheng and Yong, Zheng-Xin and Schoelkopf, Hailey and others},
|
| 877 |
+
journal={arXiv preprint arXiv:2211.01786},
|
| 878 |
+
year={2022}
|
|
|
|
|
|
|
| 879 |
}
|
| 880 |
```
|