---
library_name: adapter-transformers
license: mit
datasets:
- squad
- tiiuae/falcon-refinedweb
- adversarial_qa
- avnishkr/trimpixel
language:
- en
pipeline_tag: question-answering
tags:
- QLoRA
- Adapters
- llms
- Transformers
- Fine-Tuning
- PEFT
- SFTTrainer
- Open-Source
- LoRA
- Attention
- code
- Falcon-7b
---


# 🚀 Falcon-QAMaster

Falcon-7b-QueAns is a chatbot-like model for Question and Answering. It was built by fine-tuning [Falcon-7B](https://huggingface.co/tiiuae/falcon-7b) on the [SQuAD](https://huggingface.co/datasets/squad), [Adversarial_qa](https://huggingface.co/datasets/adversarial_qa), Trimpixel (Self-Made) datasets. This repo only includes the QLoRA adapters from fine-tuning with 🤗's [peft](https://github.com/huggingface/peft) package. 

## Model Summary

- **Model Type:** Causal decoder-only
- **Language(s):** English
- **Base Model:** Falcon-7B (License: Apache 2.0)
- **Dataset:** [SQuAD](https://huggingface.co/datasets/squad) (License: cc-by-4.0), [Adversarial_qa](https://huggingface.co/datasets/adversarial_qa) (License: cc-by-sa-4.0), [Falcon-RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) (odc-by), Trimpixel (Self-Made)
- **License(s):** Apache 2.0 inherited from "Base Model" and "Dataset"


## Why use Falcon-7B?

* **It outperforms comparable open-source models** (e.g., [MPT-7B](https://huggingface.co/mosaicml/mpt-7b), [StableLM](https://github.com/Stability-AI/StableLM), [RedPajama](https://huggingface.co/togethercomputer/RedPajama-INCITE-Base-7B-v0.1) etc.), thanks to being trained on 1,500B tokens of [RefinedWeb](https://huggingface.co/datasets/tiiuae/falcon-refinedweb) enhanced with curated corpora. See the [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
* **It features an architecture optimized for inference**, with FlashAttention ([Dao et al., 2022](https://arxiv.org/abs/2205.14135)) and multiquery ([Shazeer et al., 2019](https://arxiv.org/abs/1911.02150)). 
* **It is made available under a permissive Apache 2.0 license allowing for commercial use**, without any royalties or restrictions.

⚠️ **This is a finetuned version for specifically question and answering.** If you are looking for a version better suited to taking generic instructions in a chat format, we recommend taking a look at [Falcon-7B-Instruct](https://huggingface.co/tiiuae/falcon-7b-instruct). 

🔥 **Looking for an even more powerful model?** [Falcon-40B](https://huggingface.co/tiiuae/falcon-40b) is Falcon-7B's big brother!


## Model Details

The model was fine-tuned in 4-bit precision using 🤗 `peft` adapters, `transformers`, and `bitsandbytes`. Training relied on a method called "Low Rank Adapters" ([LoRA](https://arxiv.org/pdf/2106.09685.pdf)), specifically the [QLoRA](https://arxiv.org/abs/2305.14314) variant. The run took approximately 12 hours and was executed on a workstation with a single T4 NVIDIA GPU with 25 GB of available memory. See attached [Colab Notebook] used to train the model. 

### Model Date

July 13, 2023


Open source falcon 7b large language model fine tuned on SQuAD, Adversarial_qa, Trimpixel datasets for question and answering.
QLoRA technique used for fine tuning the model on consumer grade GPU
SFTTrainer is also used.

## Datasets

1.
Dataset used: SQuAD
Dataset Size: 87599
Training Steps: 350

2.
Dataset used: Adversarial_qa
Dataset Size: 30000
Training Steps: 400

3.
Dataset used: Trimpixel
Dataset Size: 1757
Training Steps: 400




## Training procedure


The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16

The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: False
- bnb_4bit_compute_dtype: float16
### Framework versions

- PEFT 0.4.0.dev0

- PEFT 0.4.0.dev0