Instructions to use CCC-Unito/BAMBINO-0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use CCC-Unito/BAMBINO-0.1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="CCC-Unito/BAMBINO-0.1", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("CCC-Unito/BAMBINO-0.1", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use CCC-Unito/BAMBINO-0.1 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "CCC-Unito/BAMBINO-0.1" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "CCC-Unito/BAMBINO-0.1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/CCC-Unito/BAMBINO-0.1
- SGLang
How to use CCC-Unito/BAMBINO-0.1 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 "CCC-Unito/BAMBINO-0.1" \ --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": "CCC-Unito/BAMBINO-0.1", "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 "CCC-Unito/BAMBINO-0.1" \ --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": "CCC-Unito/BAMBINO-0.1", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use CCC-Unito/BAMBINO-0.1 with Docker Model Runner:
docker model run hf.co/CCC-Unito/BAMBINO-0.1
Esperimento
Eseguire con
import torch
import os
from transformers import AutoModelForCausalLM,AutoTokenizer
os.environ["MATFORMER_ROOT"] = /path/to/matformer
tokenizer=AutoTokenizer.from_pretrained("mrinaldi/Gettone-TEST")
model = AutoModelForCausalLM.from_pretrained("CCC-Unito/BAMBINO-0.1", trust_remote_code=True, dtype=torch.bfloat16,device_map='cuda')
text="In un giorno di Autunno"
encoded=tokenizer(text,return_tensors='pt',add_special_tokens=True)
output=model.generate(encoded['input_ids'].to('cuda'))
print(tokenizer.decode(output[0]))
- Downloads last month
- 4