|
--- |
|
library_name: peft |
|
datasets: |
|
- squad |
|
- tiiuae/falcon-refinedweb |
|
language: |
|
- en |
|
tags: |
|
- llms |
|
- falcon-7b |
|
- open source llms |
|
- fine tuning llms |
|
- QLoRA |
|
- PEFT |
|
- LoRA |
|
--- |
|
|
|
# 🚀 Falcon-7b-QueAns |
|
|
|
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) dataset. 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) |
|
- **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 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 |
