hf-transformers-bot's picture
Update tiny models for LagunaForCausalLM
dd1f1c4 verified
Raw
History Blame Contribute Delete
1.43 kB
{
"architectures": [
"LagunaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 2,
"dtype": "float32",
"eos_token_id": 2,
"gating": true,
"head_dim": 8,
"hidden_act": "gelu",
"hidden_size": 32,
"initializer_range": 0.02,
"intermediate_size": 32,
"is_decoder": true,
"layer_types": [
"full_attention",
"sliding_attention"
],
"max_position_embeddings": 512,
"mlp_layer_types": [
"dense",
"sparse"
],
"model_type": "laguna",
"moe_apply_router_weight_on_input": false,
"moe_intermediate_size": 16,
"moe_routed_scaling_factor": 1.0,
"moe_router_logit_softcapping": 0.0,
"num_attention_heads": 2,
"num_attention_heads_per_layer": [
2,
2
],
"num_experts": 8,
"num_experts_per_tok": 2,
"num_hidden_layers": 2,
"num_key_value_heads": 2,
"output_router_logits": false,
"pad_token_id": 9,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"full_attention": {
"partial_rotary_factor": 0.5,
"rope_theta": 500000.0,
"rope_type": "default"
},
"sliding_attention": {
"partial_rotary_factor": 1.0,
"rope_theta": 10000.0,
"rope_type": "default"
}
},
"router_aux_loss_coef": 0.001,
"shared_expert_intermediate_size": 16,
"sliding_window": 32,
"tie_word_embeddings": false,
"transformers_version": "5.16.0.dev0",
"use_cache": true,
"vocab_size": 100352
}