For testing purposes only. From https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-Text-i1-GGUF/blob/main/README.md.
578 Pulls 1 Tag Updated 11 months ago
Use `https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-text-only-i1-GGUF/blob/main/Llama-Breeze2-8B-Instruct-text-only.i1-Q4_K_M.gguf` and disable default template. Please run it with the code in `https://github.com/mtkresearch/mtkresearch`.
133 Pulls 1 Tag Updated 7 months ago
4,329 Pulls 1 Tag Updated 2 years ago
MediaTek Research Breeze-7B (hereinafter referred to as Breeze-7B) is a language model family that builds on top of Mistral-7B, specifically intended for Traditional Chinese use. 〈F16 / Q4〉
872 Pulls 3 Tags Updated 1 year ago
Converted to Q8_0 from https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v1_0
517 Pulls 1 Tag Updated 1 year ago
Breeze-7B-32k-Instruct derives from the base model Breeze-7B-32k-Base, making the resulting model amenable to be used as-is for commonly seen tasks. 〈f16, Q4, Q4_K_M〉
516 Pulls 3 Tags Updated 1 year ago
https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-64k-v0.1
344 Pulls 1 Tag Updated 2 years ago
Breeze-7B is a language model family that builds on top of Mistral-7B, specifically intended for Traditional Chinese use.
208 Pulls 14 Tags Updated 2 years ago
175 Pulls 3 Tags Updated 1 year ago
MediaTek-Research/Breeze-7B-Instruct-v0.1 from MediaTech Research
107 Pulls 1 Tag Updated 2 years ago
67 Pulls 2 Tags Updated 1 year ago
30 Pulls 2 Tags Updated 1 year ago
25 Pulls 1 Tag Updated 1 year ago
14 Pulls 1 Tag Updated 1 year ago
11 Pulls 1 Tag Updated 1 year ago
This is an essay writing model extremely effective at evading the ZeroGPT classifier. Performance is not guaranteed on other AI detection tools. This model is for research only, please do not use it for malicious purposes or to cheat on your homework.
116 Pulls 1 Tag Updated 7 months ago
9 Pulls 1 Tag Updated 1 year ago
8 Pulls 1 Tag Updated 1 year ago
A 7B math reasoning model from Allen AI, trained with RL-Zero to solve problems step-by-step like a skilled tutor. Supports 65K context for complex multi-step problems - runs on any laptop.
156 Pulls 7 Tags Updated 4 months ago
This is a brand new Mixture of Export (MoE) model from DeepSeek, specializing in coding instructions. (quantized IQ4_XS)
6,305 Pulls 3 Tags Updated 2 months ago