From 77fe21551a3d819dff997b74180d5b58479df915 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Wed, 16 Oct 2024 09:10:15 +0200 Subject: [PATCH] models(gallery): add llama-3.2-chibi-3b Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 99d941a9c60..f13f9e5bd2e 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -182,6 +182,21 @@ - filename: Fireball-Meta-Llama-3.2-8B-Instruct-agent-003-128k-code-DPO.Q4_K_M.gguf sha256: 7f45fa79bc6c9847ef9fbad08c3bb5a0f2dbb56d2e2200a5d37b260a57274e55 uri: huggingface://QuantFactory/Fireball-Meta-Llama-3.2-8B-Instruct-agent-003-128k-code-DPO-GGUF/Fireball-Meta-Llama-3.2-8B-Instruct-agent-003-128k-code-DPO.Q4_K_M.gguf +- !!merge <<: *llama32 + name: "llama-3.2-chibi-3b" + icon: https://huggingface.co/AELLM/Llama-3.2-Chibi-3B/resolve/main/chibi.jpg + urls: + - https://huggingface.co/AELLM/Llama-3.2-Chibi-3B + - https://huggingface.co/mradermacher/Llama-3.2-Chibi-3B-GGUF + description: | + Small parameter LLMs are ideal for navigating the complexities of the Japanese language, which involves multiple character systems like kanji, hiragana, and katakana, along with subtle social cues. Despite their smaller size, these models are capable of delivering highly accurate and context-aware results, making them perfect for use in environments where resources are constrained. Whether deployed on mobile devices with limited processing power or in edge computing scenarios where fast, real-time responses are needed, these models strike the perfect balance between performance and efficiency, without sacrificing quality or speed. + overrides: + parameters: + model: Llama-3.2-Chibi-3B.Q4_K_M.gguf + files: + - filename: Llama-3.2-Chibi-3B.Q4_K_M.gguf + sha256: 4b594cd5f66181202713f1cf97ce2f86d0acfa1b862a64930d5f512c45640a2f + uri: huggingface://mradermacher/Llama-3.2-Chibi-3B-GGUF/Llama-3.2-Chibi-3B.Q4_K_M.gguf - &qwen25 ## Qwen2.5 name: "qwen2.5-14b-instruct"