37 lines
825 B
JSON
37 lines
825 B
JSON
|
{
|
||
|
|
"adapter_class": "LfmHSSAAttentionAdapter",
|
||
|
|
"converted_layers": [
|
||
|
|
2,
|
||
|
|
5,
|
||
|
|
8,
|
||
|
|
10,
|
||
|
|
12,
|
||
|
|
14
|
||
|
|
],
|
||
|
|
"format_version": 1,
|
||
|
|
"hssa_config": {
|
||
|
|
"attention_backend": "torch",
|
||
|
|
"attention_dropout": 0.0,
|
||
|
|
"block_size": 64,
|
||
|
|
"head_dim": 64,
|
||
|
|
"hidden_size": 1024,
|
||
|
|
"local_window": 256,
|
||
|
|
"num_attention_heads": 16,
|
||
|
|
"num_key_value_heads": 8,
|
||
|
|
"prefill_group_chunk_size": 32,
|
||
|
|
"qk_norm": false,
|
||
|
|
"query_group_size": 16,
|
||
|
|
"router_aux_max_groups": 256,
|
||
|
|
"router_aux_num_candidates": 32,
|
||
|
|
"router_aux_target_temperature": 0.25,
|
||
|
|
"router_beam_width": 16,
|
||
|
|
"router_dim": 128,
|
||
|
|
"router_score_bias": 0.25,
|
||
|
|
"router_temperature": 1.0,
|
||
|
|
"top_blocks": 8
|
||
|
|
},
|
||
|
|
"model_type": "lfm2",
|
||
|
|
"source_model": "models/LFM2.5-350M-Base",
|
||
|
|
"transformers_version": "5.13.1"
|
||
|
|
}
|