Past week
All results
- All results
- Verbatim
4 days ago · ggml is a machine learning (ML) library written in C and C++ with a focus on Transformer inference. The project is open-source and is being actively ...
4 days ago · This model was converted to GGUF format from ehristoforu/Qwen2-1.5b-it-chat-mistral using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original ...
2 days ago · Search code, repositories, users, issues, pull requests... · Provide feedback · Saved searches · Issues: ggerganov/llama.cpp.
5 days ago · Whats a good model for casual chatting? I was using something like Mistral ... ggml/src/ggml-cuda.cu:101: CUDA error. I'd love to be able to use the llama ...
5 days ago · GPTPortal - A feature-rich portal to chat with GPT-4, Claude, Gemini, Mistral, & OpenAI Assistant APIs via a lightweight Node.js web app; supports ...
4 days ago · I run this command, still get the same error, what else did I miss? make && LLAMA_NO_CCACHE=1 make ./llama-minicpmv-cli -m ./models/ggml-model-Q8_0.gguf -- ...
24 hours ago · Learn the basics of GGML and run it on your mac/ laptop from scratch! From the legends. @ngxson. ,. @ggerganov. and `slaren` What's GGML, you ask? > Written ...
5 days ago · Inference provides access to state-of-the-art open-source models! Heterogeneous Hardware Utilization: Make the most of your hardware resources with ggml.
4 days ago · 4-bit Llama 3.1 405B, 70B, 8B Now Available! ... @AIatMeta's Llama 3.1 models are now quantized to 4 bits by @neuralmagic's research team and available with ~100% ...