From 695f81a08baaff6045765c0c495def89043f0e2f Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Sun, 2 Mar 2025 10:24:17 +0100 Subject: [PATCH] chore(model gallery): add qihoo360_tinyr1-32b-preview (#4929) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index 2dc2d340..b2d4fad2 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -6654,6 +6654,22 @@ - filename: perplexity-ai_r1-1776-distill-llama-70b-Q4_K_M.gguf sha256: 4030b5778cbbd0723454c9a0c340c32dc4e86a98d46f5e6083527da6a9c90012 uri: huggingface://bartowski/perplexity-ai_r1-1776-distill-llama-70b-GGUF/perplexity-ai_r1-1776-distill-llama-70b-Q4_K_M.gguf +- !!merge <<: *deepseek-r1 + name: "qihoo360_tinyr1-32b-preview" + urls: + - https://huggingface.co/qihoo360/TinyR1-32B-Preview + - https://huggingface.co/bartowski/qihoo360_TinyR1-32B-Preview-GGUF + description: | + We introduce our first-generation reasoning model, Tiny-R1-32B-Preview, which outperforms the 70B model Deepseek-R1-Distill-Llama-70B and nearly matches the full R1 model in math. + + We applied supervised fine-tuning (SFT) to Deepseek-R1-Distill-Qwen-32B across three target domains—Mathematics, Code, and Science — using the 360-LLaMA-Factory training framework to produce three domain-specific models. We used questions from open-source data as seeds. Meanwhile, responses for mathematics, coding, and science tasks were generated by R1, creating specialized models for each domain. Building on this, we leveraged the Mergekit tool from the Arcee team to combine multiple models, creating Tiny-R1-32B-Preview, which demonstrates strong overall performance. + overrides: + parameters: + model: qihoo360_TinyR1-32B-Preview-Q4_K_M.gguf + files: + - filename: qihoo360_TinyR1-32B-Preview-Q4_K_M.gguf + sha256: 4eb3df9cc3d74e1dd75924a39b2ce7466a1053240375d5c969ea24b6045c2a09 + uri: huggingface://bartowski/qihoo360_TinyR1-32B-Preview-GGUF/qihoo360_TinyR1-32B-Preview-Q4_K_M.gguf - &qwen2 url: "github:mudler/LocalAI/gallery/chatml.yaml@master" ## Start QWEN2 name: "qwen2-7b-instruct"