Madras1/corpus-ptbr-v1
Viewer • Updated • 8.4M • 724 • 3
How to use Madras1/tinygpt-ptbr-v1 with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="Madras1/tinygpt-ptbr-v1", trust_remote_code=True) # Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Madras1/tinygpt-ptbr-v1", trust_remote_code=True, dtype="auto")How to use Madras1/tinygpt-ptbr-v1 with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Madras1/tinygpt-ptbr-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "Madras1/tinygpt-ptbr-v1",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/Madras1/tinygpt-ptbr-v1
How to use Madras1/tinygpt-ptbr-v1 with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "Madras1/tinygpt-ptbr-v1" \
--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": "Madras1/tinygpt-ptbr-v1",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'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 "Madras1/tinygpt-ptbr-v1" \
--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": "Madras1/tinygpt-ptbr-v1",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use Madras1/tinygpt-ptbr-v1 with Docker Model Runner:
docker model run hf.co/Madras1/tinygpt-ptbr-v1
Modelo causal pequeno treinado em JAX/Flax/Orbax e exportado para o Hugging Face com safetensors.
hidden_size: 768num_hidden_layers: 12num_attention_heads: 8intermediate_size: 2048max_position_embeddings: 1024vocab_size: 32000Checkpoint convertido do treino JAX TPU do projeto local. Este repositório usa trust_remote_code=True.
from transformers import AutoTokenizer, AutoModelForCausalLM
repo_id = "Madras1/tinygpt-ptbr-v1"
tokenizer = AutoTokenizer.from_pretrained(repo_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(repo_id, trust_remote_code=True)