Instructions to use luigicfilho/Numera-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use luigicfilho/Numera-v1 with Transformers:

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

pipe = pipeline("text-generation", model="luigicfilho/Numera-v1")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("luigicfilho/Numera-v1")
model = AutoModelForCausalLM.from_pretrained("luigicfilho/Numera-v1")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use luigicfilho/Numera-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/luigicfilho/Numera-v1

SGLang

How to use luigicfilho/Numera-v1 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 "luigicfilho/Numera-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": "luigicfilho/Numera-v1",
		"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 "luigicfilho/Numera-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": "luigicfilho/Numera-v1",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use luigicfilho/Numera-v1 with Docker Model Runner:
```
docker model run hf.co/luigicfilho/Numera-v1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Numera: The Numerically Generated Model

This model was automatically generated using LCDev-Numera, a proprietary tool for numerical model generation.

Model Details

Model Name: Numera (Gen-1)
Generated By: LCDev-Numera
Base Architecture: GPT-2
Type: Statistical Weight Generation
Date Generated: 2026-01-29

Model Technical Specifications

Here are the details for Numera (Gen-1) :

Total Parameters: ~82 Million ( 81,912,576 )
Architecture: GPT-2 Family (6 Layers, 12 Heads, 768 Hidden Size)
Vocab Size: 50,257 tokens
Format: SafeTensors (Universal, safe serialization)
Nature: Numerically Generated (Non-trained, statistical approximation)

Intended Use

This model is intended for research into:

Weight space analysis of Large Language Models.
Statistical properties of model weights.
Experimental initialization checkpoints.

Note: This model is a statistical approximation and not a trained model. It may exhibit repetitive behaviors or lack specific factual knowledge.

How to Use

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "./Numera-v1"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

prompt = "The future of AI is"
inputs = tokenizer(prompt, return_tensors="pt")

outputs = model.generate(**inputs, max_length=50)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

License

MIT

Downloads last month: 3

Safetensors

Model size

81.9M params

Tensor type

F32

Model tree for luigicfilho/Numera-v1

Quantizations

1 model

Collection including luigicfilho/Numera-v1

Numera-V1

Collection

Family of Gen-1 of Numera models • 3 items • Updated Feb 23 • 1