360VL-8B / config.json
xiechunyu's picture
first commit
16f1801
raw
history blame
1.37 kB
{
"_name_or_path": "qh360_vl-8B",
"architectures": [
"QH360_VL_LlamaForCausalLM"
],
"auto_map": {
"AutoConfig": "modeling_360vl.QH360_VLConfig",
"AutoModelForCausalLM": "modeling_360vl.QH360_VL_LlamaForCausalLM"
},
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": 128001,
"freeze_mm_mlp_adapter": false,
"hidden_act": "silu",
"hidden_size": 4096,
"image_aspect_ratio": "pad",
"image_grid_pinpoints": null,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 8192,
"mm_hidden_size": 1024,
"mm_num_tokens": 577,
"mm_projector_config": "qh360_vl-8B/proj_config.json",
"mm_projector_lr": null,
"mm_projector_type": "c-abs",
"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": "QH_360VL",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"proj_2": true,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.37.2",
"tune_mm_mlp_adapter": false,
"use_cache": true,
"use_mm_proj": true,
"vocab_size": 128256
}