62 lines
1.2 KiB
JSON
62 lines
1.2 KiB
JSON
{
|
|
"architectures": [
|
|
"Lfm2MoeForCausalLM"
|
|
],
|
|
"bos_token_id": 1,
|
|
"conv_L_cache": 3,
|
|
"conv_bias": false,
|
|
"dtype": "bfloat16",
|
|
"eos_token_id": 7,
|
|
"hidden_size": 2048,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 7168,
|
|
"layer_types": [
|
|
"conv",
|
|
"conv",
|
|
"full_attention",
|
|
"conv",
|
|
"conv",
|
|
"conv",
|
|
"full_attention",
|
|
"conv",
|
|
"conv",
|
|
"conv",
|
|
"full_attention",
|
|
"conv",
|
|
"conv",
|
|
"conv",
|
|
"full_attention",
|
|
"conv",
|
|
"conv",
|
|
"conv",
|
|
"full_attention",
|
|
"conv",
|
|
"conv",
|
|
"full_attention",
|
|
"conv",
|
|
"conv"
|
|
],
|
|
"max_position_embeddings": 128000,
|
|
"model_type": "lfm2_moe",
|
|
"moe_intermediate_size": 1792,
|
|
"norm_eps": 1e-05,
|
|
"norm_topk_prob": true,
|
|
"num_attention_heads": 32,
|
|
"num_dense_layers": 2,
|
|
"num_experts": 32,
|
|
"num_experts_per_tok": 4,
|
|
"num_hidden_layers": 24,
|
|
"num_key_value_heads": 8,
|
|
"pad_token_id": 0,
|
|
"rope_parameters": {
|
|
"rope_theta": 1000000.0,
|
|
"rope_type": "default"
|
|
},
|
|
"routed_scaling_factor": 1.0,
|
|
"tie_word_embeddings": true,
|
|
"transformers_version": "5.0.1.dev0",
|
|
"use_cache": true,
|
|
"use_expert_bias": true,
|
|
"vocab_size": 65536
|
|
}
|