XAgentLlaMa is a collection of fine-tuned generative text models ranging in scale from 7 billion to 34 billion based on Llama 2 and Code Llama. This is the repository for the 34B fine-tuned model, optimized for XAgent with strong function call ability. We collect around 300K pieces of data and fine-tune Code-Llama 34B with 48 A100 GPUs. More details will be released later. This model is trained with a special function call format, and should be used with XAgentGen to get best performance. If the json format of globalarguments is provided, the output will contains the globalarguments at any time. Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the 7B instruct-tuned version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom. To use this model, please make sure to install transformers from main until the next version is released: — [x] Code completion. — [x] Infilling. — [x] Instructions / chat. — [ ] Python specialist. *Note: Use of this model is…
Модальности:
Генерация текста
Области применения:
Генерация кода
Задача: Генерация текста
Автор: XAgentTeam
Теги: llama, llama-2, function calling, code, endpoints_compatible
Лайков: 3 | Загрузок: 11
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
