hyper-align / config.json
MengqiLei's picture
Add Hyper-Align projector checkpoint
bec5839 verified
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"consistency_start_step": 0,
"consistency_warmup_steps": 0,
"eos_token_id": 151645,
"freeze_mm_mlp_adapter": false,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"htp_num_layers": 1,
"htp_semantic_core_dim": 384,
"htp_structure_sidecar_dim": 64,
"hypergraph_semantic_dim": 1024,
"hypergraph_structure_dim": 24,
"initializer_range": 0.02,
"intermediate_size": 12288,
"lambda_ord": 0.01,
"lambda_rel": 0.01,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 40960,
"max_window_layers": 36,
"mm_hidden_size": 1048,
"mm_projector_type": "htp",
"mm_use_graph_special_token": false,
"mm_use_graph_start_end": false,
"model_type": "hyperlm_qwen3",
"num_attention_heads": 32,
"num_hidden_layers": 36,
"num_key_value_heads": 8,
"projector_incidence_mode": "sample_real",
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.53.0",
"tune_mm_mlp_adapter": true,
"use_cache": true,
"use_mm_proj": true,
"use_sliding_window": false,
"vocab_size": 151936
}