71 lines
1.8 KiB
JSON
71 lines
1.8 KiB
JSON
{
|
|
"architectures": [
|
|
"MinistralDualRopeForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"auto_map": {
|
|
"AutoConfig": "configuration_ministral_dual_rope.MinistralDualRopeConfig",
|
|
"AutoModel": "modeling_ministral_dual_rope.MinistralDualRopeModel",
|
|
"AutoModelForCausalLM": "modeling_ministral_dual_rope.MinistralDualRopeForCausalLM"
|
|
},
|
|
"bos_token_id": 248044,
|
|
"eos_token_id": 248044,
|
|
"head_dim": 128,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 3072,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 8192,
|
|
"layer_types": [
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"full_attention",
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"full_attention",
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"full_attention",
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"full_attention",
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"sliding_attention",
|
|
"full_attention"
|
|
],
|
|
"max_position_embeddings": 131072,
|
|
"model_type": "ministral_dual_rope",
|
|
"num_attention_heads": 24,
|
|
"num_hidden_layers": 28,
|
|
"num_key_value_heads": 8,
|
|
"pad_token_id": null,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_local_base_freq": 500000.0,
|
|
"rope_parameters": {
|
|
"factor": 64.0,
|
|
"high_freq_factor": 4.0,
|
|
"low_freq_factor": 1.0,
|
|
"original_max_position_embeddings": 2048,
|
|
"rope_theta": 500000.0,
|
|
"rope_type": "llama3"
|
|
},
|
|
"sliding_window": 512,
|
|
"tie_word_embeddings": false,
|
|
"transformers_version": "5.6.2",
|
|
"use_cache": true,
|
|
"vocab_size": 248320
|
|
}
|