33 lines
791 B
JSON
33 lines
791 B
JSON
{
|
|
"architectures": [
|
|
"GraniteForCausalLM"
|
|
],
|
|
"attention_bias": false,
|
|
"attention_dropout": 0.0,
|
|
"attention_multiplier": 0.015625,
|
|
"bos_token_id": 100257,
|
|
"dtype": "bfloat16",
|
|
"embedding_multiplier": 12,
|
|
"eos_token_id": 100257,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 1024,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 2048,
|
|
"logits_scaling": 4,
|
|
"max_position_embeddings": 32768,
|
|
"mlp_bias": false,
|
|
"model_type": "granite",
|
|
"num_attention_heads": 16,
|
|
"num_hidden_layers": 28,
|
|
"num_key_value_heads": 4,
|
|
"pad_token_id": 100256,
|
|
"residual_multiplier": 0.263,
|
|
"rms_norm_eps": 1e-05,
|
|
"rope_scaling": null,
|
|
"rope_theta": 10000000,
|
|
"tie_word_embeddings": true,
|
|
"transformers_version": "4.57.6",
|
|
"use_cache": true,
|
|
"vocab_size": 100352
|
|
}
|