File size: 1,170 Bytes
5407462 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 | {
"_name_or_path": "outputs/mobilevlm_v2-1.pretrain-1246k",
"architectures": [
"MobileLlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 2048,
"image_aspect_ratio": "pad",
"image_grid_pinpoints": null,
"initializer_range": 0.02,
"intermediate_size": 5632,
"max_position_embeddings": 2048,
"max_sequence_length": 2048,
"mm_hidden_size": 1024,
"mm_projector_lr": null,
"mm_projector_type": "ldpnetv2",
"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": "openai/clip-vit-large-patch14-336",
"model_type": "mobilevlm",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"tune_mm_mlp_adapter": false,
"use_cache": false,
"use_mm_proj": true,
"vision_tower_type": "clip",
"vocab_size": 32000
}
|