This is quantized version of rinna/gemma-2-baku-2b-it created using llama.cpp The model is an instruction-tuned variant of rinna/gemma-2-baku-2b, utilizing Chat Vector and Odds Ratio Preference Optimization (ORPO) for fine-tuning. It adheres to the gemma-2 chat format. A 26-layer, 2304-hidden-size transformer-based language model. Please refer to the Gemma 2 Model Card for detailed information on the model’s architecture. Model merging. The base model was endowed with instruction-following capabilities through a chat vector addition process. The chat vector was derived by subtracting the parameter vectors of google/gemma-2-2b from google/gemma-2-2b-it, as follows. ~~~~text rinna/gemma-2-baku-2b + 1.0 * (google/gemma-2-2b-it — google/gemma-2-2b) ~~~~ During this process, the embedding layer was excluded during the subtraction and addition of parameter vectors. OPRO was applied using a subset of the following dataset to further refine the performance of the merged model. ~~~~python from transformers import AutoTokenizer, AutoModelForCausalLM import torch model_id = «rinna/gemma-2-baku-2b-it» dtype = torch.bfloat16 tokenizer = AutoTokenizer.frompretrained(modelid) model =…
Модальности:
Генерация текста
Области применения:
Диалог / чат
Задача: Генерация текста
Автор: QuantFactory
Теги: gguf, gemma2, conversational, ja, en, endpoints_compatible
Лайков: 3 | Загрузок: 894
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
