-
Hi @frdel, thanks for your great work!
I found AutoMemory to be quite inefficient because it produces a summarization of the same memories at every step of the conversation.
### Suggestion
My…
-
bitnet.cpp is the official inference framework for 1-bit LLMs (e.g., BitNet b1.58). It offers a suite of optimized kernels, that support fast and lossless inference of 1.58-bit models on CPU (with NPU…
-
1.PARE: Part Attention Regressor for 3D Human Body Estimation(2021)
img-->volumetric features(before the global average pooling)-->part branch: estimates attention weights +feature branch: performs S…
-
I noticed that for no matter what models used for vualt QA embedding, the default context length/chunk size is 2048 tokens, which may lead to a reduction of retrieval performance as any note longer th…
-
### Have you searched existing issues? 🔎
- [X] I have searched and found no existing issues
### Desribe the bug
 and the token properties for Damage Reduction.
It appears the following are missing:
- Magic
- Good
- Evil
- Chaotic
- Lawful
- Wound (example …
-
### 🚀 The feature, motivation and pitch
This paper might be of interest: https://arxiv.org/pdf/2306.14048.pdf
This paper mentions removing a small portion of the KV cache does not affect the resul…
-
- [ ] When user completes harvest flow, the UI isn't updated and it takes some time , in this time user can taps again on harvest and see the previous amount for harvest
please take a look on below …
-
We should be able to replace uses of moment-timezone's `.tz()` helper in our application code and switch to the date-fns timezone helpers or the local Date object. Those helpers rely on polyfilled tim…
-
Here's a reproducer exhibiting two issues:
```
{
{-# LANGUAGE FunctionalDependencies #-}
{-# LANGUAGE FlexibleInstances #-}
-- For ancient GHC 7.0.4
{-# LANGUAGE MultiParamTypeClasses #-}
mod…