APT2-1B-Base / config.json
chrisociepa's picture
Upload model and tokenizer files
bd2aa78
raw
history blame contribute delete
580 Bytes
{
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 2816,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 16,
"num_hidden_layers": 73,
"num_key_value_heads": 16,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.33.2",
"use_cache": true,
"vocab_size": 8000
}