BakLLaVA is a multimodal model consisting of the Mistral 7B base model augmented with the LLaVA architecture.
876.7K Pulls 17 Tags Updated 2 years ago
Full 27B-class reasoning in binary transformer weights.
1,834 Pulls 1 Tag Updated 3 weeks ago
Base model: https://huggingface.co/prism-ml/Bonsai-27B-gguf --- Bonsai 27b 1bit. Fully working with OpenCode and Cline. Default context 32k.
967 Pulls 1 Tag Updated 3 weeks ago
Base model: https://huggingface.co/prism-ml/Bonsai-27B-gguf --- Bonsai 27b 2bits. Fully working with OpenCode and Cline. Default context 32k.
607 Pulls 1 Tag Updated 3 weeks ago
Base model: https://huggingface.co/prism-ml/Bonsai-27B-gguf --- Bonsai 27b 4bits. Fully working with OpenCode and Cline. Default context 32k.
245 Pulls 1 Tag Updated 3 weeks ago
225 Pulls 1 Tag Updated 3 weeks ago
More info on https://huggingface.co/prism-ml/Bonsai-8B-gguf
11.1K Pulls 1 Tag Updated 4 months ago
https://huggingface.co/prism-ml/Bonsai-27B-gguf
2,885 Pulls 1 Tag Updated 1 month ago
Ternary Bonsai: 1.58-bit Language Models at 8B, 4B, and 1.7B Scale.
1,622 Pulls 4 Tags Updated 2 months ago
PrismML Bonsai 1.7B (GGUF Q1_0). Stock Ollama cannot load Q1_0 yet — run via bonsai-ollama proxy + Prism llama-server: https://github.com/eSlider/bonsai-ollama
357 Pulls 1 Tag Updated 3 months ago
1,201 Pulls 2 Tags Updated 2 weeks ago
186 Pulls 1 Tag Updated 3 weeks ago
Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.
502.2K Pulls 5 Tags Updated 8 months ago
The IBM Granite 2B and 8B models are text-only dense LLMs trained on over 12 trillion tokens of data, demonstrated significant improvements over their predecessors in performance and speed in IBM’s initial testing.
1M Pulls 33 Tags Updated 1 year ago
MathΣtral: a 7B model designed for math reasoning and scientific discovery by Mistral AI.
540.7K Pulls 17 Tags Updated 2 years ago
111 billion parameter model optimized for demanding enterprises that require fast, secure, and high-quality AI
224.2K Pulls 5 Tags Updated 1 year ago
To help you with prompts in image and video generation. Same as used on https://goonsai.com Support: r/goonsai/
34.4K Pulls 1 Tag Updated 1 year ago
6,685 Pulls 1 Tag Updated 1 year ago
Just a no-bullshit, consumer specs AI.
12 Pulls 1 Tag Updated 7 months ago
Test model; first upload. Basic example of system prompt enhancement and exponential performance increase from said configuration. Built on command-r7b.
8 Pulls 1 Tag Updated 1 year ago