Files
Chytrej2-90M-Base/config.json

29 lines
666 B
JSON
Raw Normal View History

{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 2,
"dtype": "bfloat16",
"eos_token_id": 2,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 512,
"initializer_range": 0.02,
"intermediate_size": 1376,
"max_position_embeddings": 8192,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 8,
"num_hidden_layers": 24,
"num_key_value_heads": 4,
"pad_token_id": 3,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"tie_word_embeddings": true,
"transformers_version": "5.3.0",
"use_cache": false,
"vocab_size": 32000
}