This model is a fine-tuned version of BEE-spoke-data/NanoLlama-GQA-L10-A32_KV8-v12-minipile on the None dataset. It achieves the following results on the evaluation set: — Loss: 2.5937 — Accuracy: 0.4948 hf-causal-experimental (pretrained=BEE-spoke-data/NanoLlama-GQA-L10-A32KV8-v13-KI,revision=main,trustremotecode=True,dtype=’float’), limit: None, providedescription: False, numfewshot: 0, batchsize: 8 The following hyperparameters were used during training: — learningrate: 0.00025 — trainbatchsize: 8 — evalbatchsize: 4 — seed: 2280 — gradientaccumulationsteps: 16 — totaltrainbatchsize:
Модальности:
Генерация текста
Задача: Генерация текста
Автор: BEE-spoke-data
Теги: llama, generated_from_trainer, smol_llama, llama2, model-index, text-generation-inference, endpoints_compatible
Лайков: 2 | Загрузок: 21
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.