repugnant-pickle
smolrsrwkv
| repugnant-pickle | smolrsrwkv | |
|---|---|---|
| 1 | 6 | |
| 20 | 91 | |
| - | - | |
| 4.7 | 5.6 | |
| 4 months ago | 8 months ago | |
| Rust | Rust | |
| 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.
repugnant-pickle
-
Introducing repugnant-pickle, a crate for scraping Python Pickle files in a basic way. Notable, it can deal with (some) PyTorch model files.
The repo has a detailed README: https://github.com/KerfuffleV2/repugnant-pickle
smolrsrwkv
-
Introducing repugnant-pickle, a crate for scraping Python Pickle files in a basic way. Notable, it can deal with (some) PyTorch model files.
For an example of actually using it, you can look at my little project for running inference on RWKV models: https://github.com/KerfuffleV2/smolrsrwkv It uses repugnant-pickle to enable loading PyTorch models directly with no conversion requirement or Python dependencies.
-
Is GPT-4 still just a language model trying to predict text?
If you want some proof, I wrote my own application that can run inference on RWKV models (competing approach similar to GPT which most LLMs use currently): https://github.com/KerfuffleV2/smolrsrwkv
-
I created a simple implementation of the RWKV language model (RWKV competes with the dominant Transformers-based approach which is the "T" in GPT)
It can now quantize to 8bit for 4x memory savings: https://github.com/KerfuffleV2/smolrsrwkv/tree/experiment-quantize
-
ChatGPT saved this dog's life...
Here's an implementation of RWKV I wrote that can run inference on models: https://github.com/KerfuffleV2/smolrsrwkv
-
LLMs are not that different from us -- A delve into our own conscious process
Now, I'm not an expert but I do know a little more than the average person. I actually just got done implementing a simple one based on the RWKV approach rather than transformers: https://github.com/KerfuffleV2/smolrsrwkv
What are some alternatives?
lucia - A flexible client API framework as well as a set of API collections
tract - Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference [Moved to: https://github.com/sonos/tract]
gda_compute - A GPU/CPU compute library written in rust focusing on computation on ndim Arrays
ChatRWKV - ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.
burn - Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals. [Moved to: https://github.com/Tracel-AI/burn]
Nuclia DB - NucliaDB, The AI Search database for RAG
Synthic - Automatically generate gameboy music using machine learning
askai - Command Line Interface for OpenAi ChatGPT
deku - Declarative binary reading and writing: bit-level, symmetric, serialization/deserialization
tract - Tiny, no-nonsense, self-contained, Tensorflow and ONNX inference
neuronika - Tensors and dynamic neural networks in pure Rust.