brought to you by skratos115 (HF) / Kingatlas115 (GH) in colaboration with the official Opendevin Team ~xingyaoww This project involves the fine-tuning of the LLAMA3.18B-Instruct model using my own dataset skratos115/opendevin_DataDevinator that incorperates around 2k lines from argilla and trained with the help of Unsloth. The primary goal is to develop a more powerful LLM capable of effectively using the CodeAct framework for tool calling. This is still in early development and should not be used in production. We are working on building a bigger dataset for tool paths/ trajectories and could you all the help we can by using the feedback integration to help us build better trajectories and release to the public via MIT license for OSS model training. read more here:https://x.com/gneubig/status/1802740786242420896 and http://www.linkedin.com/feed/update/urn:li:activity:7208507606728929280/ — Model Name: LLAMA3.18BOpenDevinDEVINator — Dataset: skratos115/opendevinDataDevinator — Training Platform**: Unsloth provided full merged files or Quantized f16, q4km, Q5km gguf files. I used the LLAMA3.18BOpenDevinDEVINatorQ5K_M.gguf for my testing and got it to write me a simple script,…
Модальности:
Генерация текста
Области применения:
Следование инструкциям Диалог / чат
Задача: Генерация текста
Автор: skratos115
Теги: gguf, llama 3.1, instruct, unsloth, OpenDevin, endpoints_compatible, conversational
Лайков: 3 | Загрузок: 87
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
