Instructions to use NebuIA/nebuia_extract_small with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NebuIA/nebuia_extract_small with Transformers:

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

pipe = pipeline("text-generation", model="NebuIA/nebuia_extract_small")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NebuIA/nebuia_extract_small")
model = AutoModelForCausalLM.from_pretrained("NebuIA/nebuia_extract_small")
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 NebuIA/nebuia_extract_small with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/NebuIA/nebuia_extract_small

SGLang

How to use NebuIA/nebuia_extract_small 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 "NebuIA/nebuia_extract_small" \
    --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": "NebuIA/nebuia_extract_small",
		"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 "NebuIA/nebuia_extract_small" \
        --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": "NebuIA/nebuia_extract_small",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NebuIA/nebuia_extract_small with Docker Model Runner:
```
docker model run hf.co/NebuIA/nebuia_extract_small
```

YAML Metadata Warning:The pipeline tag "text2text-generation" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other

Structure Extraction Model

nebuia_extract_small is an extraction model inspired by NuExtract. nebuia_extract_small is a version of qween 1.5b, fine-tuned on a private high-quality synthetic dataset for entity extraction in Spanish legal texts with an 8k context length. Supports JSON template like nu extract describing the information you need to extract. NebuIA Extract specializes in identifying and extracting legal entities and relevant information from Spanish legal documents.

Model Details

Model Description

Developed by: NebuIA
Language(s) (NLP): es
License: mit
Finetuned from model [optional]: Qween2 1.5b

Uses

Same template as NuExtract

import json
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch


def predict_extract(model, tokenizer, text, schema):
    schema = json.dumps(json.loads(schema), indent=4)
    input_llm =  "<|input|>\n### Template:\n" +  schema + "\n"
    
    input_llm +=  "### Text:\n"+text +"\n<|output|>\n"
    input_ids = tokenizer(input_llm, return_tensors="pt", truncation=True, max_length=4000).to("cuda")

    output = tokenizer.decode(model.generate(**input_ids)[0], skip_special_tokens=True)
    return output.split("<|output|>")[1].split("<|end-output|>")[0]


model = AutoModelForCausalLM.from_pretrained("NebuIA/nebuia_extract_small", trust_remote_code=True, torch_dtype=torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained("NebuIA/nebuia_extract_small", trust_remote_code=True)

model.to("cuda")

model.eval()

text = """large legal text"""

schema = """{
    "calusulas": [],
    "notario": "",
    "jurisdiccion": {
      "clausula_jurisdiccion": "",
      "lugar": ""
    }
}"""

prediction = predict_extract(model, tokenizer, text, schema)
print(prediction)

Downloads last month: 11

Safetensors

Model size

2B params

Tensor type

BF16