Files
bhineka-gpt/config.json

25 lines
578 B
JSON
Raw Normal View History

{
"architectures": [
"LlamaForCausalLM"
],
"model_type": "llama",
"bos_token_id": 1,
"eos_token_id": 2,
"pad_token_id": 0,
"hidden_act": "silu",
"hidden_size": 1152,
"initializer_range": 0.02,
"intermediate_size": 3072,
"max_position_embeddings": 2048,
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.40.0",
"use_cache": true,
"vocab_size": 64000
}