Tomás Correia Marques
Tomás Correia Marques
Currently Fabric.js is at v5.2.1 and this project is using v3.6.3 Surprisingly, upgrading has not yielded much breaking changes (at least using the demo as testing ground) We could perhaps...
Well... we all knew this day would come... Spotify has updated its WebPlayer and SpotiWeb stopped working... Good news is that the new version does not seem to use flash,...
## Describe Your Changes - This PR adds support for Dolphin 2.6 Phi-2 (https://huggingface.co/cognitivecomputations/dolphin-2_6-phi-2) in Jan. This model is a finetuned version of Phi-2 with much better results for chat....
Found this super cool library from a newsletter, this is the sort of thing that really feels like magic 😍 I immediatelly had a bunch of ideas on how to...
First of all, thank you for being the ONLY real option to develop code on the Xadow GSM. I'm trying to connect to a MQTT broker that only accepts connections...
Currently local.ai server is allowing requests on `/completions`. However that means it's not compatible with most apps as they are prepared to make requests to servers from llama-cpp-python (`/v1/completions`) or...
https://huggingface.co/collections/NousResearch/hermes-3-66bd6c01399b14b08fe335ea https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B-GGUF https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B-GGUF
Could you share the migrations and postgress functions necessary for this project to run? The Readme only mentions the env var configuration but that is not enough to be able...
### Feature Description > Zamba2-2.7B is a hybrid model composed of state-space and transformer blocks https://huggingface.co/Zyphra/Zamba2-2.7B ### Motivation Quality and Size comparable to Phi2-2.7B but twice as fast and using...
Llama.cpp added support for RWKV models in https://github.com/ggerganov/llama.cpp/releases/tag/b3651 Can you sync the version llama.rn uses so that we can try those models? They are very lightweight and need a lot...