DynMoE-StableLM-1.6B / config.json
kenshinn's picture
upload model
a21f226 verified
raw
history blame
2.2 kB
{
"_name_or_path": "./checkpoints/MoE-LLaVA-StableLM-Stage2",
"architectures": [
"MoELLaVAStablelmForCausalLM"
],
"auto_map": {
"AutoConfig": "stabilityai/stablelm-2-1_6b--configuration_stablelm_epoch.StableLMEpochConfig",
"AutoModelForCausalLM": "stabilityai/stablelm-2-1_6b--modeling_stablelm_epoch.StableLMEpochForCausalLM"
},
"bos_token_id": 100257,
"eos_token_id": 100257,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 2048,
"image_aspect_ratio": "pad",
"image_projector_type": "mlp2x_gelu",
"initializer_range": 0.02,
"intermediate_size": 5632,
"max_position_embeddings": 4096,
"mm_hidden_size": 1024,
"mm_image_tower": "openai/clip-vit-large-patch14-336",
"mm_projector_lr": null,
"mm_use_im_patch_token": false,
"mm_use_im_start_end": false,
"mm_video_tower": null,
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -2,
"model_type": "moe_llava_stablelm",
"moe": {
"capacity_factor": 1.5,
"ep_size": 1,
"eval_capacity_factor": 2.0,
"min_capacity": 0,
"moe_enable": true,
"moe_layers_idx": [
0,
2,
4,
6,
8,
10,
12,
14,
16,
18,
20,
22
],
"moe_mode": "sparse",
"num_experts": [
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4,
4
],
"router_aux_loss_coef": 0.01,
"top_k_experts": -1,
"train_modules": [
"gate_proj",
"up_proj",
"down_proj",
"wg"
],
"use_residual": false
},
"norm_eps": 1e-05,
"num_attention_heads": 32,
"num_heads": 32,
"num_hidden_layers": 24,
"num_key_value_heads": 32,
"pad_token_id": 100280,
"rope_pct": 0.25,
"rope_theta": 10000,
"rotary_scaling_factor": 1.0,
"tie_word_embeddings": false,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.37.0",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mm_proj": true,
"use_qkv_bias": true,
"video_global_proj": false,
"video_projector_type": "linear",
"video_spatial_proj": false,
"video_temproal_proj": false,
"vocab_size": 100352
}