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:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://Qybera/LisaV3.0") - Notebooks
- Google Colab
- Kaggle
Upload 6 files
Browse files- config.json +77 -77
- flax_model.msgpack +2 -2
- generation_config.json +3 -3
- model.safetensors +1 -1
- pytorch_model.bin +1 -1
config.json
CHANGED
|
@@ -1,78 +1,78 @@
|
|
| 1 |
-
{
|
| 2 |
-
"model_type": "advancedlisa",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"AdvancedLISA"
|
| 5 |
-
],
|
| 6 |
-
"vocab_size": 10000,
|
| 7 |
-
"max_position_embeddings": 30,
|
| 8 |
-
"hidden_size": 1024,
|
| 9 |
-
"num_attention_heads": 16,
|
| 10 |
-
"num_hidden_layers": 8,
|
| 11 |
-
"intermediate_size": 1024,
|
| 12 |
-
"hidden_act": "gelu",
|
| 13 |
-
"hidden_dropout_prob": 0.1,
|
| 14 |
-
"attention_probs_dropout_prob": 0.1,
|
| 15 |
-
"initializer_range": 0.02,
|
| 16 |
-
"layer_norm_eps": 1e-12,
|
| 17 |
-
"total_parameters": 190809376,
|
| 18 |
-
"trainable_parameters": 190809376,
|
| 19 |
-
"vision_channels": 5,
|
| 20 |
-
"audio_channels": 1,
|
| 21 |
-
"vision_hidden": 512,
|
| 22 |
-
"audio_hidden": 512,
|
| 23 |
-
"fused_dim": 1024,
|
| 24 |
-
"voice_hidden": 512,
|
| 25 |
-
"vision_layers": 4,
|
| 26 |
-
"audio_layers": 4,
|
| 27 |
-
"reasoning_layers": 8,
|
| 28 |
-
"mel_bins": 80,
|
| 29 |
-
"max_memory": 50,
|
| 30 |
-
"components": {
|
| 31 |
-
"vision_encoder": {
|
| 32 |
-
"type": "MultispectralVisionEncoder",
|
| 33 |
-
"parameters": 15544195
|
| 34 |
-
},
|
| 35 |
-
"audio_encoder": {
|
| 36 |
-
"type": "AdvancedAudioEncoder",
|
| 37 |
-
"parameters": 29479243
|
| 38 |
-
},
|
| 39 |
-
"fusion_module": {
|
| 40 |
-
"type": "AdvancedFusionModule",
|
| 41 |
-
"parameters": 16803334
|
| 42 |
-
},
|
| 43 |
-
"reasoning_module": {
|
| 44 |
-
"type": "ReasoningModule",
|
| 45 |
-
"parameters": 68231168
|
| 46 |
-
},
|
| 47 |
-
"voice_synthesis": {
|
| 48 |
-
"type": "IndependentVoiceSynthesis",
|
| 49 |
-
"parameters": 8061965
|
| 50 |
-
},
|
| 51 |
-
"self_awareness": {
|
| 52 |
-
"type": "SelfAwarenessModule",
|
| 53 |
-
"parameters": 22579201
|
| 54 |
-
},
|
| 55 |
-
"conversation_memory": {
|
| 56 |
-
"type": "ConversationMemory",
|
| 57 |
-
"parameters": 6823937
|
| 58 |
-
}
|
| 59 |
-
},
|
| 60 |
-
"frame_size": [
|
| 61 |
-
224,
|
| 62 |
-
224
|
| 63 |
-
],
|
| 64 |
-
"seq_len": 30,
|
| 65 |
-
"audio_sample_rate": 16000,
|
| 66 |
-
"n_mels": 80,
|
| 67 |
-
"hop_length": 512,
|
| 68 |
-
"fps": 5,
|
| 69 |
-
"max_duration": 60,
|
| 70 |
-
"batch_size": 2,
|
| 71 |
-
"num_epochs": 20,
|
| 72 |
-
"learning_rate": 0.0001,
|
| 73 |
-
"weight_decay": 1e-05,
|
| 74 |
-
"lr_step_size": 15,
|
| 75 |
-
"lr_gamma": 0.8,
|
| 76 |
-
"gradient_clip": 1.0,
|
| 77 |
-
"warmup_steps": 1000
|
| 78 |
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "advancedlisa",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"AdvancedLISA"
|
| 5 |
+
],
|
| 6 |
+
"vocab_size": 10000,
|
| 7 |
+
"max_position_embeddings": 30,
|
| 8 |
+
"hidden_size": 1024,
|
| 9 |
+
"num_attention_heads": 16,
|
| 10 |
+
"num_hidden_layers": 8,
|
| 11 |
+
"intermediate_size": 1024,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"attention_probs_dropout_prob": 0.1,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"layer_norm_eps": 1e-12,
|
| 17 |
+
"total_parameters": 190809376,
|
| 18 |
+
"trainable_parameters": 190809376,
|
| 19 |
+
"vision_channels": 5,
|
| 20 |
+
"audio_channels": 1,
|
| 21 |
+
"vision_hidden": 512,
|
| 22 |
+
"audio_hidden": 512,
|
| 23 |
+
"fused_dim": 1024,
|
| 24 |
+
"voice_hidden": 512,
|
| 25 |
+
"vision_layers": 4,
|
| 26 |
+
"audio_layers": 4,
|
| 27 |
+
"reasoning_layers": 8,
|
| 28 |
+
"mel_bins": 80,
|
| 29 |
+
"max_memory": 50,
|
| 30 |
+
"components": {
|
| 31 |
+
"vision_encoder": {
|
| 32 |
+
"type": "MultispectralVisionEncoder",
|
| 33 |
+
"parameters": 15544195
|
| 34 |
+
},
|
| 35 |
+
"audio_encoder": {
|
| 36 |
+
"type": "AdvancedAudioEncoder",
|
| 37 |
+
"parameters": 29479243
|
| 38 |
+
},
|
| 39 |
+
"fusion_module": {
|
| 40 |
+
"type": "AdvancedFusionModule",
|
| 41 |
+
"parameters": 16803334
|
| 42 |
+
},
|
| 43 |
+
"reasoning_module": {
|
| 44 |
+
"type": "ReasoningModule",
|
| 45 |
+
"parameters": 68231168
|
| 46 |
+
},
|
| 47 |
+
"voice_synthesis": {
|
| 48 |
+
"type": "IndependentVoiceSynthesis",
|
| 49 |
+
"parameters": 8061965
|
| 50 |
+
},
|
| 51 |
+
"self_awareness": {
|
| 52 |
+
"type": "SelfAwarenessModule",
|
| 53 |
+
"parameters": 22579201
|
| 54 |
+
},
|
| 55 |
+
"conversation_memory": {
|
| 56 |
+
"type": "ConversationMemory",
|
| 57 |
+
"parameters": 6823937
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"frame_size": [
|
| 61 |
+
224,
|
| 62 |
+
224
|
| 63 |
+
],
|
| 64 |
+
"seq_len": 30,
|
| 65 |
+
"audio_sample_rate": 16000,
|
| 66 |
+
"n_mels": 80,
|
| 67 |
+
"hop_length": 512,
|
| 68 |
+
"fps": 5,
|
| 69 |
+
"max_duration": 60,
|
| 70 |
+
"batch_size": 2,
|
| 71 |
+
"num_epochs": 20,
|
| 72 |
+
"learning_rate": 0.0001,
|
| 73 |
+
"weight_decay": 1e-05,
|
| 74 |
+
"lr_step_size": 15,
|
| 75 |
+
"lr_gamma": 0.8,
|
| 76 |
+
"gradient_clip": 1.0,
|
| 77 |
+
"warmup_steps": 1000
|
| 78 |
}
|
flax_model.msgpack
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7df838568adf69c40187b160734384b5898f0388882e5890e38ea407e733ec6
|
| 3 |
+
size 764926633
|
generation_config.json
CHANGED
|
@@ -16,9 +16,9 @@
|
|
| 16 |
"output_hidden_states": false,
|
| 17 |
"output_scores": false,
|
| 18 |
"return_dict_in_generate": false,
|
| 19 |
-
"pad_token_id":
|
| 20 |
-
"eos_token_id":
|
| 21 |
-
"bos_token_id":
|
| 22 |
"max_audio_length": 300,
|
| 23 |
"audio_sample_rate": 16000,
|
| 24 |
"mel_bins": 80,
|
|
|
|
| 16 |
"output_hidden_states": false,
|
| 17 |
"output_scores": false,
|
| 18 |
"return_dict_in_generate": false,
|
| 19 |
+
"pad_token_id": 9999,
|
| 20 |
+
"eos_token_id": 9999,
|
| 21 |
+
"bos_token_id": 9999,
|
| 22 |
"max_audio_length": 300,
|
| 23 |
"audio_sample_rate": 16000,
|
| 24 |
"mel_bins": 80,
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 763316160
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:075b72ef88ffb73f02d1eef53dc715aea82924dad497237f75e5f5411d5fb760
|
| 3 |
size 763316160
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 763454511
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc196eb9a95d8d36d8c96cd441b7fab78cac0b6b869729c5260f7000dd414333
|
| 3 |
size 763454511
|