MiniTransformer-91M / config.json
Vivid86's picture
Upload folder using huggingface_hub
0540bca verified
Raw History Blame Contribute Delete
599 Bytes
{
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 2,
"eos_token_id": 3,
"pad_token_id": 0,
"hidden_act": "silu",
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 2048,
"max_position_embeddings": 1024,
"model_type": "llama",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"num_key_value_heads": 12,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": true,
"torch_dtype": "float16",
"transformers_version": "4.45.0",
"use_cache": true,
"vocab_size": 8192
}