Text-to-Speech
Transformers
Safetensors
English
llama
text-generation
text-generation-inference
6-bit
exl2
Instructions to use dillonroach/Orpheus-3b-ft-6bpw-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dillonroach/Orpheus-3b-ft-6bpw-exl2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="dillonroach/Orpheus-3b-ft-6bpw-exl2")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("dillonroach/Orpheus-3b-ft-6bpw-exl2") model = AutoModelForCausalLM.from_pretrained("dillonroach/Orpheus-3b-ft-6bpw-exl2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_from_model_config": true, | |
| "bos_token_id": 128000, | |
| "do_sample": true, | |
| "eos_token_id": 128009, | |
| "temperature": 0.6, | |
| "top_p": 0.9, | |
| "token_repetition_penalty":1.1, | |
| "transformers_version": "4.49.0" | |
| } | |