airoboros
llama.cpp
airoboros | llama.cpp | |
---|---|---|
8 | 773 | |
948 | 56,891 | |
- | - | |
8.7 | 10.0 | |
about 2 months ago | 5 days ago | |
Python | C++ | |
Apache License 2.0 | MIT License |
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.
airoboros
- TinyLlama project aims to pretrain a 1.1B Llama model on 3T tokens
- Airoboros: Customizable implementation of the self-instruct paper
-
airoboros (tool) overhaul
Just wanted to drop a note that I overhauled the airoboros tool not the models to have most of the prompts I've been using to build the datasets, plus a couple extras.
-
(2/2) May 2023
airoboros: using large language models to fine-tune large language models (https://github.com/jondurbin/airoboros)
-
Airoboros [7B/13B]
This is a fine-tuned LlaMa model, using completely synthetic training data created by https://github.com/jondurbin/airoboros
-
airobors-13b - 98% eval vs gpt-3.5-turbo
I used airoboros, a python tool I wrote, to generate the synthetic instruction response pairs, and included a jailbreak prompt to attempt to bypass OpenAI censorship. This is the only dataset used to fine-tune the model.
-
[P] airoboros 7b - instruction tuned on 100k synthetic instruction/responses
This is a 7b parameter, fine-tuned on 100k synthetic instruction/response pairs generated by gpt-3.5-turbo using my version of self-instruct airoboros
-
[P] airoboros: a rewrite of self-instruct/alpaca synthetic prompt generation
GitHub Repo
llama.cpp
-
Better and Faster Large Language Models via Multi-Token Prediction
For anyone interested in exploring this, llama.cpp has an example implementation here:
https://github.com/ggerganov/llama.cpp/tree/master/examples/...
- Llama.cpp Bfloat16 Support
-
Fine-tune your first large language model (LLM) with LoRA, llama.cpp, and KitOps in 5 easy steps
Getting started with LLMs can be intimidating. In this tutorial we will show you how to fine-tune a large language model using LoRA, facilitated by tools like llama.cpp and KitOps.
- GGML Flash Attention support merged into llama.cpp
-
Phi-3 Weights Released
well https://github.com/ggerganov/llama.cpp/issues/6849
- Lossless Acceleration of LLM via Adaptive N-Gram Parallel Decoding
- Llama.cpp Working on Support for Llama3
-
Embeddings are a good starting point for the AI curious app developer
Have just done this recently for local chat with pdf feature in https://recurse.chat. (It's a macOS app that has built-in llama.cpp server and local vector database)
Running an embedding server locally is pretty straightforward:
- Get llama.cpp release binary: https://github.com/ggerganov/llama.cpp/releases
- Mixtral 8x22B
- Llama.cpp: Improve CPU prompt eval speed
What are some alternatives?
WizardLM - Family of instruction-following LLMs powered by Evol-Instruct: WizardLM, WizardCoder and WizardMath
ollama - Get up and running with Llama 3, Mistral, Gemma, and other large language models.
TinyLlama - The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
gpt4all - gpt4all: run open-source LLMs anywhere
WizardVicunaLM - LLM that combines the principles of wizardLM and vicunaLM
text-generation-webui - A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.
datablations - Scaling Data-Constrained Language Models
GPTQ-for-LLaMa - 4 bits quantization of LLaMA using GPTQ
chain-of-thought-hub - Benchmarking large language models' complex reasoning ability with chain-of-thought prompting
ggml - Tensor library for machine learning
gorilla - Gorilla: An API store for LLMs
alpaca.cpp - Locally run an Instruction-Tuned Chat-Style LLM