library_name: peft
license: llama2
datasets:
- ehartford/dolphin
- garage-bAInd/Open-Platypus
tags:
- llama-2
inference: false
pipeline_tag: text-generation
llama-2-7b-dolphin 🦙🐬
This instruction model was built via parameter-efficient QLoRA finetuning of llama-2-7b on the first 5k rows of ehartford/dolphin and the first 5k riws of garage-bAInd/Open-Platypus. Finetuning was executed on 1x A100 (40 GB SXM) for roughly 1.3 hours on the Lambda Labs platform.
- Model license: Llama 2 Community License Agreement
- Basic usage: notebook
- Finetuning script: script
- Loss curves: plot
- Runtime stats: table
Example prompts and responses
Example 1:
User:
You are a helpful assistant. Write me a numbered list of things to do in New York City.\n
llama-2-7b-dolphin-peft:
coming
Example 2:
User:
You are a helpful assistant. Write a short email inviting my friends to a dinner party on Friday. Respond succinctly.\n"
llama-2-7b-dolphin-peft:
coming
Model Description
The architecture is a modification of a standard decoder-only transformer.
The llama-2-7b models have been modified from a standard transformer in the following ways:
- It uses the SwiGLU activation function
- It uses rotary positional embeddings (RoPE)
| Hyperparameter | Value |
|---|---|
| n_parameters | 7B |
| tokens | 2.0T |
| vocab size | 32000 |
| sequence length | 4096 |
Finetuning Description
The above loss curve was generated from the run's private wandb.ai log.
PreTraining Data
For more details on the pretraining process, see Llama-2-7b-hf.
The data was tokenized using the Llama-2-7b-hf tokenizer.
Limitations and Biases
The following language is modified from EleutherAI's GPT-NeoX-20B
This model can produce factually incorrect output, and should not be relied on to produce factually accurate information. This model was trained on various public datasets. While great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.
How to Use
coming
Runtime tests
coming
Acknowledgements
This model was finetuned by Daniel Furman on Sep 10, 2023 and is intended primarily for research purposes.
Disclaimer
The license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.
Meta citation for llama-2 blog
@online{Meta2023Introducing,
author = {Meta AI},
title = {Meta and Microsoft Introduce the Next Generation of Llama},
year = {2023},
url = {https://about.fb.com/news/2023/07/llama-2/},
note = {Accessed: 2023-07-24},
urldate = {2023-07-24}
}
Framework versions
- PEFT 0.5.0.dev0