vicuna_dinov2_patch / source_config.json
wjdghks950's picture
Upload verified MoL checkpoint package
8cb6b8b verified
Raw History Blame Contribute Delete
2.06 kB
{
"_name_or_path": "lmsys/vicuna-13b-v1.5",
"architectures": [
"RouterLlavaLlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"attn_level": "patch_layer",
"bos_token_id": 1,
"cap_softmax": false,
"cap_softmax_value": 0.06,
"confidence_gate": false,
"confidence_gate_slope": 10.0,
"confidence_gate_threshold": 0.6,
"dino_mm_projector_lr": null,
"dino_mm_text_hidden_size": 2048,
"encoder_type": "dinov2_txt",
"eos_token_id": 2,
"force_reserve_layer": true,
"freeze_mm_mlp_adapter": false,
"freeze_residual_scaling_coef": true,
"fusion_type": "cross_attn",
"hidden_act": "silu",
"hidden_size": 5120,
"image_aspect_ratio": "pad",
"initializer_range": 0.02,
"intermediate_size": 13824,
"learnable_gate": true,
"max_length": 4096,
"max_position_embeddings": 4096,
"mm_hidden_size": 5120,
"mm_hidden_size_dino": 1024,
"mm_patch_merge_type": "flat",
"mm_projector_lr": 2e-05,
"mm_projector_type": "mlp2x_gelu",
"mm_text_hidden_size": 5120,
"mm_use_im_patch_token": false,
"mm_use_im_start_end": false,
"mm_use_text_enc": true,
"mm_vision_select_feature": "patch",
"mm_vision_tower": "openai/clip-vit-large-patch14-336",
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 1,
"reserve_layer": -2,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"router_lr": 2e-05,
"save_router_stats": true,
"save_steps_router_stats": 5,
"text_attention_dim": 1024,
"text_attention_type": "qk",
"text_conditioning": "attention",
"tie_word_embeddings": false,
"tokenizer_model_max_length": 2048,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.36.2",
"tune_mm_mlp_adapter": false,
"tune_residual_scaling_coef": false,
"use_cache": true,
"use_mm_proj": true,
"use_text_conditioned_router": true,
"use_text_only_gating": false,
"vision_tower_delta": false,
"vocab_size": 32000
}