Instructions to use FabbriSimo01/Bloom_1b_Quantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FabbriSimo01/Bloom_1b_Quantized with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="FabbriSimo01/Bloom_1b_Quantized")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("FabbriSimo01/Bloom_1b_Quantized") model = AutoModelForCausalLM.from_pretrained("FabbriSimo01/Bloom_1b_Quantized", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use FabbriSimo01/Bloom_1b_Quantized with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "FabbriSimo01/Bloom_1b_Quantized" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "FabbriSimo01/Bloom_1b_Quantized", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/FabbriSimo01/Bloom_1b_Quantized
- SGLang
How to use FabbriSimo01/Bloom_1b_Quantized 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 "FabbriSimo01/Bloom_1b_Quantized" \ --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": "FabbriSimo01/Bloom_1b_Quantized", "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 "FabbriSimo01/Bloom_1b_Quantized" \ --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": "FabbriSimo01/Bloom_1b_Quantized", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use FabbriSimo01/Bloom_1b_Quantized with Docker Model Runner:
docker model run hf.co/FabbriSimo01/Bloom_1b_Quantized
|
Download README.md from FabbriSimo01/Bloom_1b_Quantized: direct link, hf CLI and curl.
- Browser
- Download file 706 Bytes
-
https://huggingface.co/FabbriSimo01/Bloom_1b_Quantized/resolve/refs%2Fpr%2F2/README.md
- Command line
-
hf download hf://FabbriSimo01/Bloom_1b_Quantized@refs/pr/2/README.md
-
curl -L -o README.md https://huggingface.co/FabbriSimo01/Bloom_1b_Quantized/resolve/refs%2Fpr%2F2/README.md
706 Bytes
| license: bigscience-bloom-rail-1.0 | |
| # [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) | |
| Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_FabbriSimo01__Bloom_1b_Quantized) | |
| | Metric | Value | | |
| |-----------------------|---------------------------| | |
| | Avg. | 28.45 | | |
| | ARC (25-shot) | 27.73 | | |
| | HellaSwag (10-shot) | 42.83 | | |
| | MMLU (5-shot) | 26.28 | | |
| | TruthfulQA (0-shot) | 41.82 | | |
| | Winogrande (5-shot) | 55.64 | | |
| | GSM8K (5-shot) | 0.15 | | |
| | DROP (3-shot) | 4.71 | | |