From 75bb9f4c28b6ae110495d5d492ef876a0732a445 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Thu, 17 Apr 2025 09:00:11 +0200 Subject: [PATCH] chore(model gallery): add menlo_rezero-v0.1-llama-3.2-3b-it-grpo-250404 (#5194) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index d6a3c8ff..5401bb43 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -2688,6 +2688,20 @@ - filename: deepcogito_cogito-v1-preview-llama-3B-Q4_K_M.gguf sha256: 726a0ef5f818b8d238f2844f3204848bea66fb9c172b8ae0f6dc51b7bc081dd5 uri: huggingface://bartowski/deepcogito_cogito-v1-preview-llama-3B-GGUF/deepcogito_cogito-v1-preview-llama-3B-Q4_K_M.gguf +- !!merge <<: *llama32 + name: "menlo_rezero-v0.1-llama-3.2-3b-it-grpo-250404" + urls: + - https://huggingface.co/Menlo/ReZero-v0.1-llama-3.2-3b-it-grpo-250404 + - https://huggingface.co/bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF + description: | + ReZero trains a small language model to develop effective search behaviors instead of memorizing static data. It interacts with multiple synthetic search engines, each with unique retrieval mechanisms, to refine queries and persist in searching until it finds exact answers. The project focuses on reinforcement learning, preventing overfitting, and optimizing for efficiency in real-world search applications. + overrides: + parameters: + model: Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_K_M.gguf + files: + - filename: Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_K_M.gguf + sha256: b9f01bead9e163db9351af036d8d63ef479d7d48a1bb44934ead732a180f371c + uri: huggingface://bartowski/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-GGUF/Menlo_ReZero-v0.1-llama-3.2-3b-it-grpo-250404-Q4_K_M.gguf - &qwen25 name: "qwen2.5-14b-instruct" ## Qwen2.5 icon: https://avatars.githubusercontent.com/u/141221163