vora_chartvqa / config.json
yalharbi's picture
Upload VoRAForCausalLM
7099eaa verified
{
"architectures": [
"VoRAForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_vora.VoRAConfig",
"AutoModelForCausalLM": "modeling_vora.VoRAForCausalLM"
},
"aux_vision": "",
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 3584,
"image_size": 448,
"initializer_range": 0.02,
"intermediate_size": 18944,
"llm": "Qwen/Qwen2.5-7B-Instruct",
"lora": {
"layers": 24,
"r": 1024,
"target_modules": [
"self_attn.q_proj",
"self_attn.k_proj",
"self_attn.v_proj",
"self_attn.o_proj",
"mlp.up_proj",
"mlp.gate_proj",
"mlp.down_proj"
]
},
"max_position_embeddings": 32768,
"max_window_layers": 28,
"model_type": "vora",
"num_attention_heads": 28,
"num_hidden_layers": 28,
"num_key_value_heads": 4,
"patch_size": 14,
"pretrained": "/root/.cache/huggingface/hub/models--Hon-Wong--VoRA-7B-Instruct/snapshots/6598d808aebd0bac624665f92b3433f2d311afd0/",
"reuse_aux_vision_embedding_layers": "",
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"skip_aux_cls": false,
"sliding_window": 131072,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.50.3",
"use_cache": true,
"use_sliding_window": false,
"vision_attention_mask": "bidirectional",
"vision_embedding": "AIMv2Embedding",
"vision_embedding_intermediate_size": 1536,
"vocab_size": 152064
}