Text Generation
Transformers
Safetensors
llama
toksuite
tokenization
bloom
multilingual
bpe
robustness
research
text-generation-inference
Instructions to use toksuite/bigscience-bloom with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use toksuite/bigscience-bloom with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="toksuite/bigscience-bloom")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("toksuite/bigscience-bloom", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use toksuite/bigscience-bloom with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "toksuite/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": "toksuite/bigscience-bloom", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/toksuite/bigscience-bloom
- SGLang
How to use toksuite/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 "toksuite/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": "toksuite/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 "toksuite/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": "toksuite/bigscience-bloom", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use toksuite/bigscience-bloom with Docker Model Runner:
docker model run hf.co/toksuite/bigscience-bloom
Upload config
Browse files- config.json +0 -4
config.json
CHANGED
|
@@ -1,7 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"LlamaForCausalLM"
|
| 4 |
-
],
|
| 5 |
"attention_bias": false,
|
| 6 |
"attention_dropout": 0.0,
|
| 7 |
"bos_token_id": 128000,
|
|
@@ -22,7 +19,6 @@
|
|
| 22 |
"rope_scaling": null,
|
| 23 |
"rope_theta": 10000.0,
|
| 24 |
"tie_word_embeddings": false,
|
| 25 |
-
"torch_dtype": "bfloat16",
|
| 26 |
"transformers_version": "4.51.3",
|
| 27 |
"use_cache": true,
|
| 28 |
"vocab_size": 250680
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
| 2 |
"attention_bias": false,
|
| 3 |
"attention_dropout": 0.0,
|
| 4 |
"bos_token_id": 128000,
|
|
|
|
| 19 |
"rope_scaling": null,
|
| 20 |
"rope_theta": 10000.0,
|
| 21 |
"tie_word_embeddings": false,
|
|
|
|
| 22 |
"transformers_version": "4.51.3",
|
| 23 |
"use_cache": true,
|
| 24 |
"vocab_size": 250680
|