FireAct Llama/CodeLlama is a collection of fine-tuned generative text models for performing ReAct with external search tools. Links to other models can be found in the Index section. Model Developers System 2 Research, Cambridge LTL, Monash University, Princeton PLI. Variations FireAct models including Llama-2-7B full fine-tuned models, and Llama-2-[7B,13B], CodeLlama-[7B,13B,34B] LoRA fine-tuned models. All released models are fine-tuned on multi-task (HotpotQA/StrategyQA/MMLU) and multi-type (ReAct/CoT/Reflexion) data. FireAct Llama-2: — fireactllama27blora — fireactllama213blora FireAct CodeLlama: — fireactcodellama7blora — fireactcodellama13blora — fireactcodellama34b_lora The following bitsandbytes quantization config was used during training: — loadin8bit: True — loadin4bit: False — llmint8threshold: 6.0 — llmint8skipmodules: None — llmint8enablefp32cpuoffload: False — llmint8hasfp16weight: False — bnb4bitquanttype: fp4 — bnb4bitusedoublequant: False — bnb4bitcomputedtype: float32
Модальности:
Генерация текста
Задача: Генерация текста
Автор: forestai
Теги: peft, tensorboard, facebook, meta, llama, llama-2, en
Лайков: 2 | Загрузок: 3
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.