Dispider / config.json
Mar2Ding's picture
Upload folder using huggingface_hub
89170b7 verified
{
"_name_or_path": "Dispider_ckpt",
"architectures": [
"LongQwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"clip_hidden_size": 4096,
"clip_projector_type": "mlp2x_gelu",
"compress_hidden_size": 1536,
"compress_projector_lr": null,
"compress_projector_type": "mlp2x_gelu",
"eos_token_id": 151645,
"freeze_compress_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 3584,
"image_aspect_ratio": "square",
"initializer_range": 0.02,
"intermediate_size": 18944,
"max_position_embeddings": 32768,
"max_window_layers": 28,
"mm_compressor": "/mnt/petrelfs/dingshuangrui/LLaVA/checkpoints/long-qwen-16f-64r-4p-16-causal-qwen-streaming-final/stream_compressor",
"mm_use_im_patch_token": false,
"mm_use_im_start_end": false,
"model_type": "qwen2",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"sliding_window": 131072,
"tie_word_embeddings": false,
"tokenizer_model_max_length": 32768,
"tokenizer_padding_side": "right",
"torch_dtype": "bfloat16",
"transformers_version": "4.41.2",
"tune_clip_mlp_adapter": false,
"tune_compress_mlp_adapter": false,
"use_cache": true,
"use_compress_proj": true,
"use_sliding_window": false,
"vocab_size": 152064
}