Instructions to use g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50 with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("TucanoBR/Tucano-2b4")
model = PeftModel.from_pretrained(base_model, "g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50")

Transformers

How to use g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50

SGLang

How to use g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50 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 "g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50" \
    --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": "g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50",
		"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 "g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50" \
        --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": "g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50 with Docker Model Runner:
```
docker model run hf.co/g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50
```

tucano-2b4-pira-paraphrase-lora-e50

This model is a fine-tuned version of TucanoBR/Tucano-2b4 on the None dataset.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 0.0002
train_batch_size: 2
eval_batch_size: 8
seed: 13
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 50

Training results

Framework versions

PEFT 0.17.1
Transformers 4.57.0
Pytorch 2.5.0+cu124
Datasets 4.2.0
Tokenizers 0.22.1

Downloads last month: 1

Model tree for g-assismoraes/tucano-2b4-pira-paraphrase-lora-e50

Base model

TucanoBR/Tucano-2b4

Adapter

(5)

this model