Hugging Face's logo

Annuvin
/
orpheus-3b-0.1-pt-GGUF

GGUF
Inference Endpoints
conversational
Model card Files Community
1

Orpheus-3b-0.1-pretrained in GGUF format.

This model had some problems with the tokenizer, so I removed the last audio token (which doesn't seem to be used here) from the vocabulary to get llama.cpp to stop complaining about token_embd.weight size mismatch. It still seems to work fine.

Downloads last month
419
GGUF
Model size
3.78B params
Architecture
llama

4-bit

5-bit

6-bit

8-bit

16-bit

View +2 files
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for Annuvin/orpheus-3b-0.1-pt-GGUF

Base model

meta-llama/Llama-3.2-3B-Instruct
Finetuned
canopylabs/orpheus-3b-0.1-pretrained
Quantized
(2)
this model

Collection including Annuvin/orpheus-3b-0.1-pt-GGUF