|
{ |
|
"_name_or_path": "/mnt/hwfile/mllm/qianrui/checkpoints/llava-qwen-2-pool-16f-64r-4p-causal", |
|
"architectures": [ |
|
"GroundQwenForCausalLM" |
|
], |
|
"attention_dropout": 0.0, |
|
"bos_token_id": 151643, |
|
"eos_token_id": 151645, |
|
"freeze_mm_mlp_adapter": false, |
|
"hidden_act": "silu", |
|
"hidden_size": 1536, |
|
"image_aspect_ratio": "square", |
|
"initializer_range": 0.02, |
|
"intermediate_size": 8960, |
|
"max_position_embeddings": 32768, |
|
"max_window_layers": 28, |
|
"mm_hidden_size": 1024, |
|
"mm_projector_lr": null, |
|
"mm_projector_type": "pool", |
|
"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", |
|
"model_type": "ground_qwen", |
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 28, |
|
"num_key_value_heads": 2, |
|
"pool_num": 4, |
|
"resolution": 64, |
|
"rms_norm_eps": 1e-06, |
|
"rope_theta": 1000000.0, |
|
"sliding_window": null, |
|
"tie_word_embeddings": true, |
|
"tokenizer_model_max_length": 32768, |
|
"tokenizer_padding_side": "right", |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.41.2", |
|
"tune_mm_mlp_adapter": false, |
|
"use_cache": true, |
|
"use_mm_proj": true, |
|
"use_sliding_window": false, |
|
"vocab_size": 151936 |
|
} |
|
|