From 259ad3cfe61bd3e13fb12941875843416ea6d2c9 Mon Sep 17 00:00:00 2001 From: Ettore Di Giacinto Date: Thu, 3 Apr 2025 10:25:46 +0200 Subject: [PATCH] chore(model gallery): add all-hands_openhands-lm-1.5b-v0.1 (#5114) Signed-off-by: Ettore Di Giacinto --- gallery/index.yaml | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/gallery/index.yaml b/gallery/index.yaml index c2779b76..feccdb10 100644 --- a/gallery/index.yaml +++ b/gallery/index.yaml @@ -5485,6 +5485,36 @@ - filename: all-hands_openhands-lm-7b-v0.1-Q4_K_M.gguf sha256: d50031b04bbdad714c004a0dc117c18d26a026297c236cda36089c20279b2ec1 uri: huggingface://bartowski/all-hands_openhands-lm-7b-v0.1-GGUF/all-hands_openhands-lm-7b-v0.1-Q4_K_M.gguf +- !!merge <<: *qwen25 + name: "all-hands_openhands-lm-1.5b-v0.1" + icon: https://github.com/All-Hands-AI/OpenHands/blob/main/docs/static/img/logo.png?raw=true + urls: + - https://huggingface.co/all-hands/openhands-lm-1.5b-v0.1 + - https://huggingface.co/bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF + description: | + This is a smaller 1.5B model trained following the recipe of all-hands/openhands-lm-32b-v0.1. It is intended to be used for speculative decoding. Autonomous agents for software development are already contributing to a wide range of software development tasks. But up to this point, strong coding agents have relied on proprietary models, which means that even if you use an open-source agent like OpenHands, you are still reliant on API calls to an external service. + + Today, we are excited to introduce OpenHands LM, a new open coding model that: + + Is open and available on Hugging Face, so you can download it and run it locally + Is a reasonable size, 32B, so it can be run locally on hardware such as a single 3090 GPU + Achieves strong performance on software engineering tasks, including 37.2% resolve rate on SWE-Bench Verified + + Read below for more details and our future plans! + What is OpenHands LM? + + OpenHands LM is built on the foundation of Qwen Coder 2.5 Instruct 32B, leveraging its powerful base capabilities for coding tasks. What sets OpenHands LM apart is our specialized fine-tuning process: + + We used training data generated by OpenHands itself on a diverse set of open-source repositories + Specifically, we use an RL-based framework outlined in SWE-Gym, where we set up a training environment, generate training data using an existing agent, and then fine-tune the model on examples that were resolved successfully + It features a 128K token context window, ideal for handling large codebases and long-horizon software engineering tasks + overrides: + parameters: + model: all-hands_openhands-lm-1.5b-v0.1-Q4_K_M.gguf + files: + - filename: all-hands_openhands-lm-1.5b-v0.1-Q4_K_M.gguf + sha256: 30abd7860c4eb5f2f51546389407b0064360862f64ea55cdf95f97c6e155b3c6 + uri: huggingface://bartowski/all-hands_openhands-lm-1.5b-v0.1-GGUF/all-hands_openhands-lm-1.5b-v0.1-Q4_K_M.ggu - &llama31 url: "github:mudler/LocalAI/gallery/llama3.1-instruct.yaml@master" ## LLama3.1 icon: https://avatars.githubusercontent.com/u/153379578