diff --git a/gallery/index.yaml b/gallery/index.yaml index a89c0e7dacdd..c08fcd67528d 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -22079,3 +22079,31 @@ - filename: Tlacuilo-12B.i1-Q4_K_M.gguf sha256: 94218112aa02113c8e21cd2c1d10818bea39bc6aee7e67be6014f86e80e76cb1 uri: huggingface://mradermacher/Tlacuilo-12B-i1-GGUF/Tlacuilo-12B.i1-Q4_K_M.gguf +- !!merge <<: *qwen3 + name: "capybara-instruct-8b" + urls: + - https://huggingface.co/mradermacher/capybara-instruct-8b-GGUF + description: | + **Model Name:** Qwen3-8B (Base Model) + **Repository:** [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) + **License:** Apache 2.0 + **Description:** + Qwen3-8B is a state-of-the-art 8.2-billion-parameter dense language model from Alibaba's Qwen series, designed for advanced reasoning, instruction following, and multilingual tasks. It uniquely supports seamless switching between **thinking mode** (for complex logic, math, and coding) and **non-thinking mode** (for efficient dialogue), enabling optimal performance across diverse use cases. Built with extensive training and optimized for both reasoning and conversational fluency, it excels in agent-based tasks, creative writing, and long-context processing (up to 131,072 tokens with YaRN scaling). + + **Key Features:** + - 8.2B parameters, 36 layers, GQA with 32 Q & 8 KV heads + - Native support for 32K tokens, up to 131K with YaRN scaling + - Dual-mode operation: thinking (reasoning) and non-thinking (dialogue) + - Strong multilingual support (100+ languages) + - Optimized for deployment via vLLM, SGLang, llama.cpp, and more + + **Best For:** Advanced reasoning, agent workflows, multilingual applications, and high-performance inference. + + > *Note: The model at `mradermacher/capybara-instruct-8b-GGUF` is a quantized and fine-tuned version of this base model.* + overrides: + parameters: + model: capybara-instruct-8b.Q4_K_M.gguf + files: + - filename: capybara-instruct-8b.Q4_K_M.gguf + sha256: 6b12a3db63f46f6267ff7bf90e29079060dba84427932ea596cf73277c8e9612 + uri: huggingface://mradermacher/capybara-instruct-8b-GGUF/capybara-instruct-8b.Q4_K_M.gguf