walid bettahar

main: seed: 1 main: model base = '/mnt/c/Users/walid.bettahar/virtualassistant/build/VirtualAssistant/dolphin-2.2.1-mistral-7b.Q2_K.gguf' llama_model_loader: loaded meta data with 20 key-value pairs and 291 tensors from /mnt/c/Users/walid.bettahar/virtualassistant/build/VirtualAssistant/dolphin-2.2.1-mistral-7b.Q2_K.gguf (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note:...

Can i fine tune "dolphin-2.2.1-mistral-7b.Q2_K.gguf" with torchtune ? using cpu ?

13

Here , i'm trying to finetune dolphin-2.2.1-mistral-7b.Q2_K.gguf using my own data set as "fichier.txt" can i do it ? and how ? and it's also confusing can someone explain how...

BOS ,and EOS tokens

3

Hi everyone ! I have a question it might be dumb but i want to understand\ llm_load_print_meta: BOS token = 1 '' llm_load_print_meta: EOS token = 2 '' llm_load_print_meta: UNK...