# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("nytopop/3b_or_base")
model = AutoModelForCausalLM.from_pretrained("nytopop/3b_or_base")Quick Links
noteworthy changes
- tokenizer omits
<|audio|>to prevent finetunes resizing the embeddings unneccessarily config.jsonuses the correct EOS to end generation on end of audiogeneration_config.jsonuses the correct EOS to end generation on end of audio + has a reasonable default temperaturechat_template.jinjamaps user messages to transcripts and assistant messages to audio for simple conversational context management
- Downloads last month
- 1
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="nytopop/3b_or_base")