llama-recipes
llm-toys
| llama-recipes | llm-toys | |
|---|---|---|
| 9 | 2 | |
| 9,588 | 115 | |
| 15.7% | - | |
| 9.8 | 7.2 | |
| 5 days ago | 10 months ago | |
| Jupyter Notebook | Python | |
| GNU General Public License v3.0 or later | Apache License 2.0 |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
llama-recipes
- Prompt Engineering with Llama2
-
Purple Llama by Meta AI
There are a whole bunch of prompts for this here: https://github.com/facebookresearch/llama-recipes/commit/109...
- [D] Recommendation for LLM fine-tuning codebase
- FLaNK Stack Weekly for 27 November 2023
- Finetune codellama for code completion task on specific programming language
-
[D] Tokenizers Truncation during Fine-tuning with Large Texts
Llama-recipes
-
How to fine tune llama2?
You can also try the recipe here https://github.com/facebookresearch/llama-recipes/blob/main/quickstart.ipynb
- Examples and recipes for Llama 2 model
- Llama Recipes
llm-toys
-
How to fine tune llama2?
You can use the train script here https://github.com/kuutsav/llm-toys/blob/main/llm_toys/train.py. The readme contains a sample training command.
-
[P] Finetuning qLoRAs for production use cases - Paraphrasing, Changing the tone of a sentence, Dialogue Summarization and Topic generation
All the details can be found here: https://github.com/kuutsav/llm-toys.
What are some alternatives?
FLaNK-OpenAi - Chat
nanoChatGPT - nanogpt turned into a chat model
LLaVA - [NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
DB-GPT-Hub - A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL
CogVLM - a state-of-the-art-level open visual language model | 多模态预训练模型
unsloth - Finetune Llama 3, Mistral & Gemma LLMs 2-5x faster with 80% less memory
BakLLaVA
LLM-Finetuning-Hub - Toolkit for fine-tuning, ablating and unit-testing open-source LLMs. [Moved to: https://github.com/georgian-io/LLM-Finetuning-Toolkit]
pymobiledevice3 - Pure python3 implementation for working with iDevices (iPhone, etc...).
Zicklein - Finetuning instruct-LLaMA on german datasets.
trl - Train transformer language models with reinforcement learning.
marvin - ✨ Build AI interfaces that spark joy