Spark-5M-Base-v4
Сегодня мы представляем Spark v4, базовую модель ламы с 5M параметрами, обученную на 0,7B токенах Sample-10BT из Fineweb-Edu....
Сегодня мы представляем Spark v4, базовую модель ламы с 5M параметрами, обученную на 0,7B токенах Sample-10BT из Fineweb-Edu....
The Model cbalgeman/MiroThinker-v1.5-30B-mlx-4Bit was converted to MLX format from miromind-ai/MiroThinker-v1.5-30B using mlx-lm version 0.29.1. Модальности:Генерация текста Области применения:Диалог...
The Model 0hei0/MiroThinker-v1.5-30B-mlx-4Bit was converted to MLX format from miromind-ai/MiroThinker-v1.5-30B using mlx-lm version 0.29.1. Модальности:Генерация текста Области применения:Диалог...
This model was generated using llama.cpp at commit 10e978015. ——————:|:—————————:|:———-:|:—————:|:——————————————————————:| MiroThinker v1.0 demonstrates strong general-research performance across a...
This model is a lightweight variant of Qwen2.5-Omni-7B, customized to remove the vision encoder and support only audio...
Run them directly with llama.cpp, or any other llama.cpp based project Some of these quants (Q3KXL, Q4KL etc)...
MamaBot-Llama is an opensource fine-tuned large language model developed by HelpMum to assist with maternal healthcare by providing...
Original model: https://huggingface.co/Locutusque/OpenCerebrum-1.0-7b-DPO Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski Модальности:Генерация текста Области применения:Генерация...
This model was converted to GGUF format from apodex/Apodex-1.0-mini using llama.cpp via the ggml.ai’s GGUF-my-repo space. Refer to...
MiroThinker v1.5 is the world-leading search agent designed to advance tool-augmented reasoning and information-seeking capabilities. Unlike previous agents...