|
{ |
|
"architectures": [ |
|
"GraniteMoeSharedForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0, |
|
"attention_multiplier": 0.0078125, |
|
"bos_token_id": 0, |
|
"embedding_multiplier": 12, |
|
"eos_token_id": 0, |
|
"hidden_act": "silu", |
|
"hidden_size": 1536, |
|
"initializer_range": 0.1, |
|
"intermediate_size": 512, |
|
"logits_scaling": 6, |
|
"max_position_embeddings": 4096, |
|
"model_type": "granitemoeshared", |
|
"num_attention_heads": 12, |
|
"num_experts_per_tok": 6, |
|
"num_hidden_layers": 40, |
|
"num_key_value_heads": 4, |
|
"num_local_experts": 62, |
|
"output_router_logits": false, |
|
"pad_token_id": 0, |
|
"residual_multiplier": 0.22, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": null, |
|
"rope_theta": 10000, |
|
"router_aux_loss_coef": 0.0, |
|
"shared_intermediate_size": 1024, |
|
"tie_word_embeddings": true, |
|
"transformers_version": "4.49.0.dev0", |
|
"use_cache": true, |
|
"vocab_size": 50257 |
|
} |
|
|