KSA-V2-1.9B-base / config.json
OpenOneRec's picture
Release KSA-V2-1.9B-base weights and inference runtime
03c3dff verified
Raw History Blame Contribute Delete
2.47 kB
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"auto_map": {
"AutoModel": "modeling_qwen3.Qwen3Model",
"AutoModelForCausalLM": "modeling_qwen3.Qwen3ForCausalLM"
},
"bos_token_id": 151643,
"eos_token_id": 151643,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"max_position_embeddings": 131072,
"max_window_layers": 24,
"mix_coeff": 0.0,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000,
"sksa_apply_sparse_attention": true,
"sksa_enabled": true,
"sksa_indexer_block_size": 4,
"sksa_indexer_chunk_attention_include_summary": false,
"sksa_indexer_chunk_attention_qk_source": "independent",
"sksa_indexer_chunk_attention_v_source": "independent",
"sksa_indexer_force_sink": true,
"sksa_indexer_head_dim": 128,
"sksa_indexer_heads": 8,
"sksa_indexer_qk_norm": false,
"sksa_indexer_query_block_size": 512,
"sksa_indexer_query_rank": 512,
"sksa_indexer_rope_dim": 64,
"sksa_indexer_scorer_backend": "fused",
"sksa_indexer_summary_key_source": "chunk_attention",
"sksa_indexer_teacher_pooling": "max",
"sksa_indexer_token_budget": 4096,
"sksa_local_window_tokens": 1024,
"sksa_routing_mode": "summary_indexer",
"sksa_sparse_full_layers": [
3,
7,
11,
15,
19,
23
],
"sliding_window": null,
"summary_chunk_position_ids_type": "origin",
"summary_chunk_size": 8,
"summary_independent_attention_layernorm": false,
"summary_independent_parameters": true,
"summary_layer_freq": "([1]*4)*6",
"summary_meta_pool_block_size": 512,
"summary_meta_pool_group_size": "([128]*1+[128]*1+[128]*1+[0]*1)*6",
"summary_meta_pool_mass_correction": "log_group_size",
"summary_meta_pool_mode": "dimension_wise",
"summary_meta_pool_position": "group_last",
"summary_partial_chunk_policy": "defer",
"summary_sliding_chunk_num": "([128]*3+[16384]*1)*6",
"summary_token_begin": 151936,
"summary_token_num": 1,
"summary_token_position_ids_type": "last_chunk_slice_right",
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "5.0.0",
"truncate_predict_nums": 151936,
"use_cache": true,
"use_sliding_window": false,
"use_summary_attention": true,
"vocab_size": 151937
}