README.md

---
base_model:
- BSC-LT/salamandra-7b-instruct
datasets:
- alinia/EADOP-RAG-out-of-domain
language:
- ca
- es
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
tags:
- legal
---

# Salamandra 7B aligned EADOP Model Card
Salamandra 7B aligned EADOP is a full-finetuning version of 
[BSC Language Technologies Unit](https://huggingface.co/BSC-LT)'s 
[Salamndra Instruct 7B](https://huggingface.co/BSC-LT/salamandra-7b-instruct)
model by the at the Barcelona Supercomputing Center focused on improving
the handling of out-of-domain Questions in a RAG instruction-following setting.

The model has been finetuned on a dataset consisting of 2,000+ human annotated in- 
and out-of-domain user messages and assistant responses in the context of a chatbot that can
provide helpful information about the current Catalan legislation. 
The dataset [alinia/EADOP-RAG-out-of-domain](https://huggingface.co/datasets/alinia/EADOP-RAG-out-of-domain) 
was collected in collaboration with the 
[Entitat Autònoma del Diari Oficial i de Publicacions (EADOP)](https://dogc.gencat.cat/ca/sobre-el-dogc/eadop/) 
and it consists of user messages and assistant responses in Catalan and Spanish.

> [!WARNING]
> **DISCLAIMER:** This model is a proof-of-concept designed to demonstrate the effects of
finetuning an Instruction model with a small dataset of out-of-domain questions in the model's
capability to politely and informatively refuse to answer questions that are out-of-domain.
> As a proof-of-concept, the model is still prone to generate harmful or inappropriate content.
---

## Model Details
Please refer to the [Salamndra Instruct 7B model details](https://huggingface.co/BSC-LT/salamandra-7b-instruct#model-details) 
for the specific details about the model architecture and pretraining.

## Intended Use
This model was developed as a proof-of-concept to demonstrate the effects of finetuning 
an Instruction model with a small dataset of in- and out-of-domain questions in the model's 
capability to politely and informatively refuse to answer questions that are out-of-domain in 
the context of a domain-specific RAG-based chatbot.

## How to use

This model uses the ChatML, the same instruction-following conversation format as the base model.

```python
from datetime import datetime
from transformers import AutoTokenizer, AutoModelForCausalLM
import transformers
import torch

model_id = "BSC-LT/salamandra-7b-instruct"

text = "At what temperature does water boil?"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
 model_id,
 device_map="auto",
 torch_dtype=torch.bfloat16
 )

message = [ { "role": "user", "content": text } ]

prompt = tokenizer.apply_chat_template(
 message,
 tokenize=False,
 add_generation_prompt=True
)

inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=200)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

Using this template, each turn is preceded by a `<|im_start|>` delimiter and the role of the entity
(either `user`, for content supplied by the user, or `assistant` for LLM responses), and finished with the `<|im_end|>` token.

---

## Finetuning Data
Please refer to [alinia/EADOP-RAG-out-of-domain](https://huggingface.co/datasets/alinia/EADOP-RAG-out-of-domain) for the Dataset Card.


### Author
This model has been finetuned by [Alinia AI](https://alinia.ai/).


### Contact
For further information, please email [[email protected]](mailto:[email protected]).


### Acknowledgements
This project is part of a partnership with the Language Technologies Unit at the [Barcelona Supercomputing Center](https://www.bsc.es/).
The data collection process was supported by the [Entitat Autònoma del Diari Oficial i de Publicacions (EADOP)](https://dogc.gencat.cat/ca/sobre-el-dogc/eadop/).