CodeGen
cformers
CodeGen | cformers | |
---|---|---|
18 | 4 | |
4,769 | 313 | |
0.9% | 0.0% | |
6.1 | 6.7 | |
about 2 months ago | 5 months 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.
CodeGen
- FLaNK Stack Weekly 23 Oct 2023
-
Seeking Resources on Open-source Large Language Models Specializing in Causality Tasks
CodeGen (I included this model as there's some evidence in recent months that LLMs trained on code-related tasks better capture long-range dependencies compared to LLMs trained on 'just words')
-
Free alternative to OpenAI Copilot
https://github.com/salesforce/CodeGen these are used in fauxpilot https://github.com/fauxpilot/fauxpilot
- FauxPilot – an open-source GitHub Copilot server
-
GitHub Copilot X: The AI-powered developer experience
You can always use https://github.com/salesforce/CodeGen . But it does require managing the model hosting. You can use fauxpilot to mimic copilot functionality https://github.com/fauxpilot/fauxpilot
-
Will we see a “stable diffusion” version of ChatGPT?
freediver 2 days ago | prev | next [–] Here is an example of one general purpose open source LLM, probably the best you can get: https://github.com/EleutherAI/gpt-neox To manage your expectations it is nowhere as good as ChatGPT. If you are interested in programming only: https://github.com/salesforce/CodeGen
- Codegen: Open-Source Codex Equivalent
-
Exploring Ghostwriter, a GitHub Copilot alternative
Replit built Ghostwriter on the open source scene based on Salesforce’s Codegen, using Nvidia’s FasterTransformer and Triton server for highly optimized decoders, and the knowledge distillation process of the CodeGen model from two billion parameters to a faster model of one billion parameters.
-
We've filed a lawsuit against GitHub Copilot
https://github.com/moyix/fauxpilot is working on an open source variant. Based on https://github.com/salesforce/CodeGen
- Open Source model to generate code competitive with OpenAI Codex/GitHub Copilot
cformers
-
[P] rwkv.cpp: FP16 & INT4 inference on CPU for RWKV language model
it's a combination of things, and removing python from the loop isn't essential to achieving most of these performance gains. the main trick is quantizing the weights and compiling the model. concrete example that builds on top of ggml with python APIs: https://github.com/NolanoOrg/cformers
- Cformers 🚀 - "Transformers with a C-backend for lightning-fast CPU inference". | Nolano
-
FauxPilot – an open-source GitHub Copilot server
We will add quantized CodeGen for fast inference on CPUs up on cformers (https://github.com/NolanoOrg/cformers/) by later today.
What are some alternatives?
fauxpilot - FauxPilot - an open-source alternative to GitHub Copilot server
llama.cpp - LLM inference in C/C++
pifs - πfs - the data-free filesystem!
alpaca.cpp - Locally run an Instruction-Tuned Chat-Style LLM
FasterTransformer - Transformer related optimization, including BERT, GPT
RWKV-LM - RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
copilot
rwkv.cpp - INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
gpt-neox - An implementation of model parallel autoregressive transformers on GPUs, based on the DeepSpeed library.
llm - An ecosystem of Rust libraries for working with large language models
NewtonianEotWashToolkit - A simple point-wise Newtonian gravitational force calculator
gpt4all.cpp - Locally run an Assistant-Tuned Chat-Style LLM