Reinforcement Learning
Keras
PyTorch
JAX
Safetensors
English
advancedlisa
multimodal
vision
audio
multispectral
emotion-recognition
scene-understanding
object-detection
spatial-reasoning
conversational-ai
Instructions to use Qybera/LisaV3.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use Qybera/LisaV3.0 with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://Qybera/LisaV3.0") - Notebooks
- Google Colab
- Kaggle
| { | |
| "max_length": 512, | |
| "min_length": 10, | |
| "do_sample": true, | |
| "early_stopping": false, | |
| "num_beams": 1, | |
| "num_beam_groups": 1, | |
| "diversity_penalty": 0.0, | |
| "num_return_sequences": 1, | |
| "length_penalty": 1.0, | |
| "repetition_penalty": 1.0, | |
| "no_repeat_ngram_size": 0, | |
| "renormalize_logits": false, | |
| "remove_invalid_values": false, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "return_dict_in_generate": false, | |
| "pad_token_id": 9999, | |
| "eos_token_id": 9999, | |
| "bos_token_id": 9999, | |
| "max_audio_length": 300, | |
| "audio_sample_rate": 16000, | |
| "mel_bins": 80, | |
| "temperature": 0.8, | |
| "top_k": 50, | |
| "top_p": 0.9, | |
| "voice_temperature": 0.7, | |
| "prosody_control": true, | |
| "emotion_control": true | |
| } |