noteworthy changes

tokenizer omits <|audio|> to prevent finetunes resizing the embeddings unneccessarily
config.json uses the correct EOS to end generation on end of audio
generation_config.json uses the correct EOS to end generation on end of audio + has a reasonable default temperature
chat_template.jinja maps user messages to transcripts and assistant messages to audio for simple conversational context management

Safetensors

Model size

1B params

Tensor type

BF16

Model tree for nytopop/1b_or_base

Base model

Finetuned

(1)

this model

Quantizations