Text Generation
Transformers
PyTorch
TensorBoard
Safetensors
bloom
Eval Results (legacy)
text-generation-inference
Instructions to use bigscience/bloom with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bigscience/bloom with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bigscience/bloom")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("bigscience/bloom") model = AutoModelForCausalLM.from_pretrained("bigscience/bloom") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use bigscience/bloom with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bigscience/bloom" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bigscience/bloom", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/bigscience/bloom
- SGLang
How to use bigscience/bloom 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/bloom" \ --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/bloom", "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/bloom" \ --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/bloom", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use bigscience/bloom with Docker Model Runner:
docker model run hf.co/bigscience/bloom
first proposals of examples for the widget
Browse filesOnce the PR that allows to select a language and an example type is merged, this PR offers several examples in several languages of prompts.
I tried to do my best to be compatible with the yaml format but it's not impossible that some adjustments have to be made for the line breaks and the special characters such as the quotation mark.
README.md
CHANGED
|
@@ -50,6 +50,31 @@ language:
|
|
| 50 |
- zht
|
| 51 |
- zu
|
| 52 |
pipeline_tag: text-generation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
---
|
| 54 |
|
| 55 |
<h1 style='text-align: center '>BLOOM LM</h1>
|
|
|
|
| 50 |
- zht
|
| 51 |
- zu
|
| 52 |
pipeline_tag: text-generation
|
| 53 |
+
widget:
|
| 54 |
+
- text: Language idioms. It's raining
|
| 55 |
+
example_title: Language idioms
|
| 56 |
+
group: en
|
| 57 |
+
- text: Idiomes linguistiques. Il pleut
|
| 58 |
+
example_title: Language idioms
|
| 59 |
+
group: fr
|
| 60 |
+
- text: "A \"whatpu\" is a small, furry animal native to Tanzania. An example of a sentence that uses the word whatpu is: We were traveling in Africa and we saw these very cute whatpus.\nTo do a \"farduddle\" means to jump up and down really fast. An example of a sentence that uses the word farduddle is:"
|
| 61 |
+
example_title: Imaginary word
|
| 62 |
+
group: en
|
| 63 |
+
- text: "Un \"whatpu\" est un petit animal à fourrure originaire de Tanzanie. Un exemple d'une phrase qui utilise le mot whatpu est: Nous étions en Afrique et nous avons vu des whatpus trop mignons.\"Faire un \"farduddle\" veut dire sauter sur place vraiment vite. Un exemple de phrase qui utilise le mot farduddle est:"
|
| 64 |
+
example_title: Imaginary word
|
| 65 |
+
group: fr
|
| 66 |
+
- text: "Un \"whatpu\" es un pequeño animal peludo nativo de Tanzania. Un ejemplo de una oración que usa la palabra whatpu es: Estábamos viajando por África y vimos estos whatpus muy bonitos.\"Hacer un \"farduddle\" significa saltar arriba y abajo muy rápido. Un ejemplo de una oración que usa la palabra farduddle es:"
|
| 67 |
+
example_title: Imaginary word
|
| 68 |
+
group: es
|
| 69 |
+
- text:"ال"واتبو" هو حيوان صغير مكسو بالفراء يعيش في تنزانيا. مثال على جملة تستخدم كلمة واتبو هي: كنا نسافر في افريقيا و رأينا هؤلاء الواتبو اللطفاء. \n للقيام ب"فاردادل" يعني ان تقفز للأعلى و الأسفل بسرعة كبيرة. مثال على جملة تستخدم كلمة فاردادل هي:"
|
| 70 |
+
example_title: Imaginary word
|
| 71 |
+
group: ar
|
| 72 |
+
- text: "\"ワトプー\"はタンザニアに生息する毛むくじゃらの小動物である。ワトプーを使った例文は以下の通りです:\n私たちはアフリカを旅行していて、とてもかわいいワトプーを見た。\n\"ファルドドル\"はとても速く飛び跳ねることを意味します。ファルドドルを使った例文は以下の通りです:"
|
| 73 |
+
example_title: Imaginary word
|
| 74 |
+
group: jp
|
| 75 |
+
- text: "Um \"whatpu\" é um pequeno animal peludo nativo da Tanzânia. Um exemplo de uma frase que usa a palavra whatpu é: Estávamos a viajar por África e vimos uns whatpus muito queridos.\"Fazer um \"farduddle\" significa saltar para cima e para baixo muito rápido. Um exemplo de uma frase que usa a palavra farduddle é:"
|
| 76 |
+
example_title: Imaginary word
|
| 77 |
+
group: pt
|
| 78 |
---
|
| 79 |
|
| 80 |
<h1 style='text-align: center '>BLOOM LM</h1>
|