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`.
165 Pulls 1 Tag Updated 11 months ago
4,527 Pulls 1 Tag Updated 2 years ago
For testing purposes only. From https://huggingface.co/mradermacher/Llama-Breeze2-8B-Instruct-Text-i1-GGUF/blob/main/README.md.
764 Pulls 1 Tag Updated 1 year 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〉
951 Pulls 3 Tags Updated 2 years ago
Converted to Q8_0 from https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v1_0
667 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〉
577 Pulls 3 Tags Updated 2 years ago
https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-64k-v0.1
354 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.
216 Pulls 14 Tags Updated 2 years ago
176 Pulls 3 Tags Updated 2 years ago
MediaTek-Research/Breeze-7B-Instruct-v0.1 from MediaTech Research
114 Pulls 1 Tag Updated 2 years ago
68 Pulls 2 Tags Updated 2 years ago
30 Pulls 2 Tags Updated 2 years ago
27 Pulls 1 Tag Updated 2 years ago
15 Pulls 1 Tag Updated 2 years ago
11 Pulls 1 Tag Updated 2 years 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.
150 Pulls 1 Tag Updated 1 year ago
9 Pulls 1 Tag Updated 2 years ago
8 Pulls 1 Tag Updated 2 years ago
Decensored Qwen2.5-Coder-3B-Instruct with 3/100 refusals and near-zero KL divergence via Heretic abliteration.
1,251 Pulls 1 Tag Updated 1 month ago
BibleAI is a production-ready Gemma 4 E4B model specialized for Bible study, theology, church history, and faith-centered Q&A.
501 Pulls 2 Tags Updated 4 months ago