97 lines
2.2 KiB
JSON
97 lines
2.2 KiB
JSON
|
{
|
||
|
|
"architectures": [
|
||
|
|
"Lfm2ForCausalLM"
|
||
|
|
],
|
||
|
|
"block_auto_adjust_ff_dim": true,
|
||
|
|
"block_dim": 1024,
|
||
|
|
"block_ffn_dim_multiplier": 1.0,
|
||
|
|
"block_mlp_init_scale": 1.0,
|
||
|
|
"block_multiple_of": 256,
|
||
|
|
"block_norm_eps": 1e-05,
|
||
|
|
"block_out_init_scale": 1.0,
|
||
|
|
"block_use_swiglu": true,
|
||
|
|
"block_use_xavier_init": true,
|
||
|
|
"bos_token_id": 1,
|
||
|
|
"conv_L_cache": 3,
|
||
|
|
"conv_bias": false,
|
||
|
|
"conv_dim": 1024,
|
||
|
|
"conv_use_xavier_init": true,
|
||
|
|
"dtype": "bfloat16",
|
||
|
|
"eos_token_id": 7,
|
||
|
|
"full_attn_idxs": null,
|
||
|
|
"hidden_size": 1024,
|
||
|
|
"hssa_conversion": {
|
||
|
|
"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"
|
||
|
|
},
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"intermediate_size": 6656,
|
||
|
|
"layer_types": [
|
||
|
|
"conv",
|
||
|
|
"conv",
|
||
|
|
"full_attention",
|
||
|
|
"conv",
|
||
|
|
"conv",
|
||
|
|
"full_attention",
|
||
|
|
"conv",
|
||
|
|
"conv",
|
||
|
|
"full_attention",
|
||
|
|
"conv",
|
||
|
|
"full_attention",
|
||
|
|
"conv",
|
||
|
|
"full_attention",
|
||
|
|
"conv",
|
||
|
|
"full_attention",
|
||
|
|
"conv"
|
||
|
|
],
|
||
|
|
"max_position_embeddings": 128000,
|
||
|
|
"model_type": "lfm2",
|
||
|
|
"norm_eps": 1e-05,
|
||
|
|
"num_attention_heads": 16,
|
||
|
|
"num_heads": 16,
|
||
|
|
"num_hidden_layers": 16,
|
||
|
|
"num_key_value_heads": 8,
|
||
|
|
"pad_token_id": 0,
|
||
|
|
"rope_parameters": {
|
||
|
|
"rope_theta": 1000000.0,
|
||
|
|
"rope_type": "default"
|
||
|
|
},
|
||
|
|
"tie_word_embeddings": true,
|
||
|
|
"transformers_version": "5.13.1",
|
||
|
|
"use_cache": true,
|
||
|
|
"use_pos_enc": true,
|
||
|
|
"vocab_size": 65536
|
||
|
|
}
|