27 lines
660 B
JSON
27 lines
660 B
JSON
|
|
{
|
||
|
|
"architectures": [
|
||
|
|
"CausalLM"
|
||
|
|
],
|
||
|
|
"model_type": "danai",
|
||
|
|
"vocab_size": 32768,
|
||
|
|
"hidden_size": 512,
|
||
|
|
"intermediate_size": 1376,
|
||
|
|
"num_hidden_layers": 12,
|
||
|
|
"num_attention_heads": 8,
|
||
|
|
"num_key_value_heads": 4,
|
||
|
|
"head_dim": 64,
|
||
|
|
"hidden_act": "silu",
|
||
|
|
"max_position_embeddings": 2048,
|
||
|
|
"initializer_range": 0.02,
|
||
|
|
"rms_norm_eps": 1e-05,
|
||
|
|
"use_cache": true,
|
||
|
|
"tie_word_embeddings": true,
|
||
|
|
"rope_theta": 10000.0,
|
||
|
|
"rope_scaling": null,
|
||
|
|
"torch_dtype": "bfloat16",
|
||
|
|
"transformers_version": "5.15.0",
|
||
|
|
"total_parameters": 54525952,
|
||
|
|
"model_name": "danAI-55M-Reasoning",
|
||
|
|
"author": "Asjad Ilahi (asjadilahi)",
|
||
|
|
"license": "apache-2.0"
|
||
|
|
}
|