Any-to-Any
Transformers
Safetensors
English
xoron
multimodal
Mixture of Experts
text-to-image
image editing
image to video
text-to-video
video editing
text-to-speech
speech-to-text
speech-to-speech
image-to-text
video-to-text
agentic
tool-use
flow-matching
3d-rope
titok
vidtok
dual-stream-attention
zero-shot-voice-cloning
bigvgan
snake-activation
multi-receptive-field-fusion
custom_code
Delete config.json
Browse files- config.json +0 -50
config.json
DELETED
|
@@ -1,50 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"model_name": "Xoron-Dev-MultiMoE",
|
| 3 |
-
"hidden_size": 1024,
|
| 4 |
-
"num_layers": 12,
|
| 5 |
-
"num_heads": 16,
|
| 6 |
-
"intermediate_size": 2048,
|
| 7 |
-
"vocab_size": 151643,
|
| 8 |
-
"max_position_embeddings": 131072,
|
| 9 |
-
"use_sliding_window": true,
|
| 10 |
-
"sliding_window": 4096,
|
| 11 |
-
"use_moe": true,
|
| 12 |
-
"num_experts": 8,
|
| 13 |
-
"num_experts_per_tok": 2,
|
| 14 |
-
"moe_layer_freq": 2,
|
| 15 |
-
"router_aux_loss_coef": 0.1,
|
| 16 |
-
"vision_model_name": "openai/clip-vit-base-patch16",
|
| 17 |
-
"freeze_vision": false,
|
| 18 |
-
"num_vision_tokens": 64,
|
| 19 |
-
"max_video_frames": 32,
|
| 20 |
-
"enable_generation": true,
|
| 21 |
-
"generation_image_size": 256,
|
| 22 |
-
"generation_video_size": 256,
|
| 23 |
-
"generation_latent_channels": 4,
|
| 24 |
-
"generation_base_channels": 128,
|
| 25 |
-
"generation_inference_steps": 8,
|
| 26 |
-
"tokenizer_name": "Qwen/Qwen2.5-1.5B",
|
| 27 |
-
"use_lora": true,
|
| 28 |
-
"lora_r": 32,
|
| 29 |
-
"lora_alpha": 64,
|
| 30 |
-
"lora_dropout": 0.05,
|
| 31 |
-
"lora_target_modules": [
|
| 32 |
-
"q_proj",
|
| 33 |
-
"k_proj",
|
| 34 |
-
"v_proj",
|
| 35 |
-
"o_proj",
|
| 36 |
-
"gate_proj",
|
| 37 |
-
"up_proj",
|
| 38 |
-
"down_proj"
|
| 39 |
-
],
|
| 40 |
-
"train_lora_only": false,
|
| 41 |
-
"use_cross_attention": true,
|
| 42 |
-
"cross_attention_layers": 4,
|
| 43 |
-
"cross_attention_heads": 8,
|
| 44 |
-
"cross_attention_dropout": 0.1,
|
| 45 |
-
"use_flash_attention": true,
|
| 46 |
-
"output_dir": "./xoron-model",
|
| 47 |
-
"has_audio_encoder": true,
|
| 48 |
-
"has_audio_decoder": true,
|
| 49 |
-
"lora_applied": true
|
| 50 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|