Text Generation
Transformers
Safetensors
imp
custom_code
imp-v1-3b / config.json
Oyoy1235's picture
update phi-2 version
989a1a3
{
"_name_or_path": "MILVLG/Imp-v1-3b",
"activation_function": "gelu_new",
"architectures": [
"ImpForCausalLM"
],
"attn_pdrop": 0.0,
"auto_map": {
"AutoConfig": "configuration_imp.ImpConfig",
"AutoModelForCausalLM": "modeling_imp.ImpForCausalLM"
},
"embd_pdrop": 0.0,
"eos_token_id": 50295,
"freeze_mm_mlp_adapter": false,
"image_aspect_ratio": "square",
"image_token": "<image>",
"image_token_index": 50296,
"img_processor": null,
"initializer_range": 0.02,
"mm_hidden_size": 1152,
"mm_projector_lr": 2e-05,
"mm_projector_type": "mlp2x_gelu",
"mm_use_im_patch_token": false,
"mm_use_im_start_end": false,
"mm_vision_select_feature": "patch",
"mm_vision_select_layer": -2,
"mm_vision_tower": "google/siglip-so400m-patch14-384",
"model_type": "imp",
"pad_token_id": 50256,
"resid_pdrop": 0.1,
"tie_word_embeddings": false,
"tokenizer_model_max_length": 3072,
"tokenizer_padding_side": "right",
"torch_dtype": "float16",
"transformers_version": "4.39.2",
"use_cache": true,
"use_mm_proj": true,
"vision_tower_config": {
"attention_dropout": 0.0,
"attn_implementation": null,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"image_size": 384,
"intermediate_size": 4304,
"layer_norm_eps": 1e-06,
"model_type": "siglip_vision_model",
"num_attention_heads": 16,
"num_channels": 3,
"num_hidden_layers": 27,
"patch_size": 14
},
"vocab_size": 51200,
"attention_dropout": 0.0,
"hidden_act": "gelu_new",
"hidden_size": 2560,
"intermediate_size": 10240,
"layer_norm_eps": 1e-05,
"max_position_embeddings": 3072,
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"partial_rotary_factor": 0.4,
"qk_layernorm": false,
"rope_scaling": null,
"rope_theta": 10000.0
}