hyperdex-test / config.json
GGUFGuy's picture
NanoDex 1m 路 299,892,736 fineweb-edu tokens 路 loss 3.5412
da3d0c4 verified
Raw
History Blame Contribute Delete
730 Bytes
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 0,
"dtype": "float32",
"eos_token_id": 0,
"head_dim": 16,
"hidden_act": "silu",
"hidden_size": 96,
"initializer_range": 0.041666666666666664,
"intermediate_size": 472,
"max_position_embeddings": 512,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 6,
"num_hidden_layers": 5,
"num_key_value_heads": 2,
"pad_token_id": 1,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "default"
},
"tie_word_embeddings": true,
"transformers_version": "5.17.0",
"use_cache": true,
"vocab_size": 2048
}