falcon-7b-QueAns / README.md
avnishkr's picture
Update README.md
6b3a00e
metadata
library_name: peft
datasets:
  - squad
  - tiiuae/falcon-refinedweb
language:
  - en
tags:
  - llms
  - falcon-7b
  - open source llms
  - fine tuning llms
  - QLoRA
  - PEFT
  - LoRA

πŸš€ Falcon-7b-QueAns

Falcon-7b-QueAns is a chatbot-like model for Question and Answering. It was built by fine-tuning Falcon-7B on the SQuAD dataset. This repo only includes the QLoRA adapters from fine-tuning with πŸ€—'s peft package.

Model Summary

  • Model Type: Causal decoder-only
  • Language(s): English
  • Base Model: Falcon-7B (License: Apache 2.0)
  • Dataset: SQuAD (License: cc-by-4.0)
  • 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, StableLM, RedPajama etc.), thanks to being trained on 1,500B tokens of RefinedWeb enhanced with curated corpora. See the OpenLLM Leaderboard.
  • It features an architecture optimized for inference, with FlashAttention (Dao et al., 2022) and multiquery (Shazeer et al., 2019).
  • 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.

πŸ”₯ Looking for an even more powerful model? Falcon-40B is Falcon-7B's big brother!

Model Details

The model was fine-tuned in 4-bit precision using πŸ€— peft adapters, transformers, and bitsandbytes. Training relied on a method called "Low Rank Adapters" (LoRA), specifically the QLoRA variant. The run took approximately 4 hours and was executed on a workstation with a single T4 NVIDIA GPU with 15 GB of available memory. See attached [Colab Notebook] used to train the model.

Model Date

July 06, 2023

Open source falcon 7b large language model fine tuned on SQuAD dataset for question and answering.

QLoRA technique used for fine tuning the model on consumer grade GPU SFTTrainer is also used.

Dataset used: SQuAD Dataset Size: 87278 Training Steps: 500

Training procedure

The following bitsandbytes quantization config was used during training:

  • load_in_8bit: True
  • load_in_4bit: False
  • 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: True
  • load_in_4bit: False
  • 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