mate have you looked at uv? just do `brew install uv` followed by: `uv venv –python 3.12` that's it https://
docs.astral.sh/uv/
@reach_vb
-
UV: Fast Python package manager and environment tool
By
–
-
Model weights and inference code now available
By
–
check out the model weights and inference code here:
-
NVIDIA releases Hymba-1.5B open-source language model weights
By
–
yo! @NVIDIAAIDev finally released the weights for Hymba-1.5B – outperforms Llama, Qwen, and SmolLM2 with 6-12x less training trained ONLY on 1.5T tokens > massive reductions in KV cache size and improved throughput
> combines Mamba and Attention in a hybrid parallel -
Emerging Movement in AI Space: Beginning of Major Shift
By
–
incredible things are happening on the space, if you know where to look – feels like the beginning of a movement
-
Nvidia’s Role in AI Jobs: A Personal Investment Perspective
By
–
Oh I don't have the balls to short Nvidia – not when they are inherently making my job viable :p
-
Best Way to Invest in Chinese AI/ML Labs
By
–
What's the best way to take long bet on chinese AI/ML labs? Buying the index (ex: MSCI China) sounds a bit less reliable, but I'd kill to have an Public ETF tracking that
-
Model weights and inference code base now available
By
–
Check out the model weights and inference code base here:
-
OuteTTS v0.2: Compact Multilingual TTS with Voice Cloning
By
–
Smol TTS keeps getting better! Introducing OuteTTS v0.2 – 500M parameters, multilingual with voice cloning! 🔥
— Vaibhav (VB) Srivastav (@reach_vb) 25 novembre 2024
> Multilingual – English, Chinese, Korean & Japanese
> Cross platform inference w/ llama.cpp
> Zero-shot voice cloning
> Trained on 5 Billion audio tokens
> Qwen 2.5… pic.twitter.com/N4c4UkfrhzSmol TTS keeps getting better! Introducing OuteTTS v0.2 – 500M parameters, multilingual with voice cloning! > Multilingual – English, Chinese, Korean & Japanese
> Cross platform inference w/ llama.cpp
> Zero-shot voice cloning
> Trained on 5 Billion audio tokens
> Qwen 2.5 -
Qwen 2 VL + FLUX: Advanced Open Source Image Generation
By
–
Qwen 2 VL + FLUX > supports variation, img2img, inpainting, and controlnet-guided generation
> depth estimation and line detection for precise structural guidance
> aspect ratios up to 1536×1024 MIT licensed!
