vora-parse-p1 / config.json
yevvonlim's picture
Add files using upload-large-folder tool
0c085bd verified
{
"architectures": [
"VoRAForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_vora.VoRAConfig",
"AutoModelForCausalLM": "modeling_vora.VoRAForCausalLM"
},
"aux_vision": "/workspace/VoRAParse/output/jina-clip/image-encoder.pt",
"bos_token_id": 151643,
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"image_size": 512,
"initializer_range": 0.02,
"intermediate_size": 12288,
"llm": "Qwen/Qwen3-8B",
"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": 40960,
"max_window_layers": 36,
"model_type": "vora",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"patch_size": 14,
"reuse_aux_vision_embedding_layers": "",
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"skip_aux_cls": false,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.51.3",
"use_cache": true,
"use_sliding_window": false,
"vision_attention_mask": "bidirectional",
"vision_embedding": "AIMv2Embedding",
"vision_embedding_intermediate_size": 1536,
"vocab_size": 151936
}