Edit model card

Model Card for Model ID

This model is the Llama-2-7b-hf fine-tuned with an adapter on the Spanish Alpaca dataset.

Model Details

Model Description

This is a Spanish chat model fine-tuned on a Spanish instruction dataset.

The model expect a prompt containing the instruction, with an option to add an input (see examples below).

  • Developed by: 4i Intelligent Insights
  • Model type: Chat model
  • Language(s) (NLP): Spanish
  • License: cc-by-nc-4.0 (inhereted from the alpaca-spanish dataset),
  • Finetuned from model : Llama 2 7B (license agreement)


The model is intended to be used directly without the need of further fine-tuning.

Bias, Risks, and Limitations

This model inherits the bias, risks, and limitations of its base model, Llama 2, and of the dataset used for fine-tuning. Note that the Spanish Alpaca dataset was obtained by translating the original Alpaca dataset. It contains translation errors that may have negatively impacted the fine-tuning of the model.

How to Get Started with the Model

Use the code below to get started with the model for inference. The adapter was directly merged into the original Llama 2 model.

The following code sample uses 4-bit quantization, you may load the model without it if you have enough VRAM.

from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig, TrainingArguments, GenerationConfig
import torch
model_name = "4i-ai/Llama-2-7b-alpaca-es"


tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=True)

def create_and_prepare_model():
        compute_dtype = getattr(torch, "float16")
        bnb_config = BitsAndBytesConfig(
        model = AutoModelForCausalLM.from_pretrained(
            model_name, quantization_config=bnb_config, device_map={"": 0}
        return model
model = create_and_prepare_model()

def generate(instruction, input=None):
    #Format the prompt to look like the training data
    if input is not None:
        prompt = "### Instruction:\n"+instruction+"\n\n### Input:\n"+input+"\n\n### Response:\n"
    else :
        prompt = "### Instruction:\n"+instruction+"\n\n### Response:\n"

    inputs = tokenizer(prompt, return_tensors="pt")
    input_ids = inputs["input_ids"].cuda()

    generation_output = model.generate(
            generation_config=GenerationConfig(temperature=1.0, top_p=0.75, top_k=40, num_beams=10), #hyperparameters for generation
            max_new_tokens=150, #maximum tokens generated, increase if you want longer asnwer (up to 2048 - the length of the prompt), generation "looks" slower for longer response

    for seq in generation_output.sequences:
        output = tokenizer.decode(seq, skip_special_tokens=True)
        print(output.split("### Response:")[1].strip())
generate("Háblame de la superconductividad.")
generate("Encuentra la capital de España.")
generate("Encuentra la capital de Portugal.")
generate("Organiza los números dados en orden ascendente.", "2, 3, 0, 8, 4, 10")
generate("Compila una lista de 5 estados de EE. UU. ubicados en el Oeste.")
generate("¿Cuál es el color de una fresa?")
generate("¿Cuál es el color de la siguiente fruta?", "fresa")

Expected output:

La superconductividad es un fenómeno físico en el que algunos materiales se convierten en conductores de corriente eléctrica a temperaturas muy bajas. Esto significa que la corriente eléctrica puede fluir a través del material sin pérdida de energía. La superconductividad fue descubierta por primera vez en 1911 por el físico alemán Heike Kamerlingh Onnes, quien descubrió que algunos materiales se convierten en conductores de corriente eléctrica a temperaturas muy bajas. Desde entonces, la superconductividad se ha utiliz
La capital de España es Madrid.
La capital de Portugal es Lisboa.
2, 3, 4, 8, 10, 0
California, Oregón, Washington, Nevada y Arizona.
El color de una fresa es rosa.
El color de la fresa es rojo.

Contact Us

4i.ai provides natural language processing solutions with dialog, vision and voice capabilities to deliver real-life multimodal human-machine conversations. Please contact us at info@4i.ai

Downloads last month
Model size
6.74B params
Tensor type
Inference Examples
Inference API (serverless) has been turned off for this model.

Dataset used to train 4i-ai/Llama-2-7b-alpaca-es