Instructions to use Felladrin/Minueza-2-96M-Instruct-Variant-02 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Felladrin/Minueza-2-96M-Instruct-Variant-02 with Transformers:

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

pipe = pipeline("text-generation", model="Felladrin/Minueza-2-96M-Instruct-Variant-02")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Felladrin/Minueza-2-96M-Instruct-Variant-02")
model = AutoModelForCausalLM.from_pretrained("Felladrin/Minueza-2-96M-Instruct-Variant-02")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Felladrin/Minueza-2-96M-Instruct-Variant-02 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Felladrin/Minueza-2-96M-Instruct-Variant-02"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Felladrin/Minueza-2-96M-Instruct-Variant-02",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Felladrin/Minueza-2-96M-Instruct-Variant-02

SGLang

How to use Felladrin/Minueza-2-96M-Instruct-Variant-02 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 "Felladrin/Minueza-2-96M-Instruct-Variant-02" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Felladrin/Minueza-2-96M-Instruct-Variant-02",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Felladrin/Minueza-2-96M-Instruct-Variant-02" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Felladrin/Minueza-2-96M-Instruct-Variant-02",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Felladrin/Minueza-2-96M-Instruct-Variant-02 with Docker Model Runner:
```
docker model run hf.co/Felladrin/Minueza-2-96M-Instruct-Variant-02
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Minueza-2-96M-Instruct (Variant 02)

This model is a fine-tuned version of Felladrin/Minueza-2-96M on the Portuguese recogna-nlp/ultra-alpaca-ptbr dataset.

Usage

pip install transformers==4.50.0 torch==2.6.0

from transformers import pipeline, TextStreamer
import torch

generate_text = pipeline(
    "text-generation",
    model="Felladrin/Minueza-2-96M-Instruct-Variant-02",
    device=torch.device("cuda" if torch.cuda.is_available() else "cpu"),
)

messages = [
    {
        "role": "system",
        "content": "Você é um assistente com vasta experiência em abertura de empresas.",
    },
    {
        "role": "user",
        "content": "Olá!",
    },
    {
        "role": "assistant",
        "content": "Olá! Como posso ajudar?",
    },
    {
        "role": "user",
        "content": "Liste os principais desafios de se abrir uma empresa.",
    },
]

generate_text(
    generate_text.tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    ),
    streamer=TextStreamer(generate_text.tokenizer, skip_special_tokens=True),
    max_new_tokens=512,
    do_sample=True,
    temperature=0.7,
    top_p=0.9,
    top_k=0,
    min_p=0.1,
    repetition_penalty=1.12,
)

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 7.5e-05
train_batch_size: 64
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 128
optimizer: Use adamw_torch with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
training_steps: 2990