mamba.py
MemGPT
| mamba.py | MemGPT | |
|---|---|---|
| 1 | 15 | |
| 646 | 10,088 | |
| - | - | |
| 9.3 | 9.9 | |
| 8 days ago | 7 days ago | |
| Python | Python | |
| MIT License | 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.
mamba.py
-
AI21 Labs Unveils Jamba: The First Production-Grade Mamba-Based AI Model
llama.cpp probably won't be getting Jamba support anytime soon: https://github.com/ggerganov/llama.cpp/issues/6372#issuecomm...
There is an MLX Mamba implementation, but nothing for Jamba either: https://github.com/alxndrTL/mamba.py/tree/main/mlx
You could run PyTorch on CPU and w/ a 12B activation pass, it might even run relatively fast (8 tok/s?), but a q4 quant would also easily fit on 2x3090s and should run at >60 tok/s.
MemGPT
-
AI21 Labs Unveils Jamba: The First Production-Grade Mamba-Based AI Model
On a side note: working over longer contexts also reminds me of MemGPT(https://github.com/cpacker/MemGPT)
- FLaNK Weekly 18 Dec 2023
-
At this point we don’t necessarily need higher context windows. We need better truncation.
The MemGPT project is taking on this challenge.
-
Putting Together the Pieces of Transformative AI
Long Term Memory - Voyager, MemGPTand LongMem
-
[R] MemGPT: Towards LLMs as Operating Systems - UC Berkeley 2023 - Is able to create unbounded/infinite LLM context!
Blog: https://memgpt.ai/
-
MemGPT: Towards LLMs as Operating Systems - UC Berkeley 2023 - Is able to create unbounded/infinite LLM context!
Github: https://github.com/cpacker/MemGPT
-
MemGPT – LLMs with self-editing memory for unbounded context
Hey all, MemGPT authors here! Happy to answer any questions about the implementation.
If you want to try it out yourself, we have a Discord bot up-and-running on the MemGPT server (https://discord.gg/9GEQrxmVyE) where you can see the memory editing in action - as you chat you'll see MemGPT update its profile about you (and itself).
Everything's open source, so can also try running MemGPT locally using the code here: https://github.com/cpacker/MemGPT. In the repo we also have a document-focused example where you can chat with MemGPT about the LlamaIndex API docs.
- MemGPT — a combination of OS and GPT
What are some alternatives?
llama.cpp - LLM inference in C/C++
tidybot - TidyBot: Personalized Robot Assistance with Large Language Models
LongMem - Official implementation of our NeurIPS 2023 paper "Augmenting Language Models with Long-Term Memory".
mlx-examples - Examples in the MLX framework
Efficient-LLMs-Survey - [TMLR 2024] Efficient Large Language Models: A Survey
FLiPStackWeekly - FLaNK AI Weekly covering Apache NiFi, Apache Flink, Apache Kafka, Apache Spark, Apache Iceberg, Apache Ozone, Apache Pulsar, and more...
LLMCompiler - [ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling
Visual-Flow - Visual-Flow main repository
autogen - A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap
FLaNK-OpenAi - Chat
FLaNK-EveryTransitSystem - Every transit system
FLaNK-SaoPauloBrazil - FLaNK-SaoPauloBrazil