Commit
•
b365495
1
Parent(s):
b6fb94f
Upload config.json
Browse files- config.json +104 -0
config.json
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "hieptuyet1102/MoE_LlaVa_Qwen1.5_0.5bx4Top2_Vista_filter_reasoning",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MoELLaVAQwen1_5ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151643,
|
| 9 |
+
"freeze_mm_mlp_adapter": false,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"image_aspect_ratio": "pad",
|
| 13 |
+
"image_projector_type": "mlp2x_gelu",
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 2816,
|
| 16 |
+
"lora": {
|
| 17 |
+
"lora_alpha": 256,
|
| 18 |
+
"lora_bias": "none",
|
| 19 |
+
"lora_dropout": 0.05,
|
| 20 |
+
"lora_enable": true,
|
| 21 |
+
"lora_r": 128,
|
| 22 |
+
"only_lora_ffn": true,
|
| 23 |
+
"target_modules": [
|
| 24 |
+
"up_proj",
|
| 25 |
+
"down_proj",
|
| 26 |
+
"gate_proj"
|
| 27 |
+
]
|
| 28 |
+
},
|
| 29 |
+
"max_position_embeddings": 32768,
|
| 30 |
+
"max_window_layers": 21,
|
| 31 |
+
"mm_hidden_size": 768,
|
| 32 |
+
"mm_image_tower": "google/siglip-base-patch16-256-multilingual",
|
| 33 |
+
"mm_projector_lr": 1.25e-06,
|
| 34 |
+
"mm_use_im_patch_token": false,
|
| 35 |
+
"mm_use_im_start_end": false,
|
| 36 |
+
"mm_video_tower": null,
|
| 37 |
+
"mm_vision_select_feature": "patch",
|
| 38 |
+
"mm_vision_select_layer": -2,
|
| 39 |
+
"model_type": "moe_llava_qwen1_5",
|
| 40 |
+
"moe": {
|
| 41 |
+
"capacity_factor": 1.5,
|
| 42 |
+
"ep_size": 1,
|
| 43 |
+
"eval_capacity_factor": 2.0,
|
| 44 |
+
"min_capacity": 0,
|
| 45 |
+
"moe_enable": true,
|
| 46 |
+
"moe_layers_idx": [
|
| 47 |
+
0,
|
| 48 |
+
2,
|
| 49 |
+
4,
|
| 50 |
+
6,
|
| 51 |
+
8,
|
| 52 |
+
10,
|
| 53 |
+
12,
|
| 54 |
+
14,
|
| 55 |
+
16,
|
| 56 |
+
18,
|
| 57 |
+
20,
|
| 58 |
+
22
|
| 59 |
+
],
|
| 60 |
+
"moe_mode": "sparse",
|
| 61 |
+
"num_experts": [
|
| 62 |
+
4,
|
| 63 |
+
4,
|
| 64 |
+
4,
|
| 65 |
+
4,
|
| 66 |
+
4,
|
| 67 |
+
4,
|
| 68 |
+
4,
|
| 69 |
+
4,
|
| 70 |
+
4,
|
| 71 |
+
4,
|
| 72 |
+
4,
|
| 73 |
+
4
|
| 74 |
+
],
|
| 75 |
+
"router_aux_loss_coef": 0.01,
|
| 76 |
+
"top_k_experts": 2,
|
| 77 |
+
"train_modules": [
|
| 78 |
+
"up_proj",
|
| 79 |
+
"down_proj",
|
| 80 |
+
"gate_proj"
|
| 81 |
+
],
|
| 82 |
+
"use_residual": false
|
| 83 |
+
},
|
| 84 |
+
"num_attention_heads": 16,
|
| 85 |
+
"num_hidden_layers": 24,
|
| 86 |
+
"num_key_value_heads": 16,
|
| 87 |
+
"pad_token_id": 151643,
|
| 88 |
+
"rms_norm_eps": 1e-06,
|
| 89 |
+
"rope_theta": 1000000.0,
|
| 90 |
+
"sliding_window": 32768,
|
| 91 |
+
"tie_word_embeddings": true,
|
| 92 |
+
"tokenizer_padding_side": "right",
|
| 93 |
+
"torch_dtype": "float16",
|
| 94 |
+
"transformers_version": "4.37.0",
|
| 95 |
+
"tune_mm_mlp_adapter": false,
|
| 96 |
+
"use_cache": true,
|
| 97 |
+
"use_mm_proj": true,
|
| 98 |
+
"use_sliding_window": false,
|
| 99 |
+
"video_global_proj": false,
|
| 100 |
+
"video_projector_type": "linear",
|
| 101 |
+
"video_spatial_proj": false,
|
| 102 |
+
"video_temproal_proj": false,
|
| 103 |
+
"vocab_size": 151646
|
| 104 |
+
}
|