llama-base-512-clmbr / config.json
Miking98's picture
Upload folder using huggingface_hub
9b27a8a verified
raw
history blame contribute delete
967 Bytes
{
"_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 0,
"cls_token_id": 5,
"eos_token_id": 1,
"hidden_act": "silu",
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 2688,
"mask_token_id": 6,
"max_position_embeddings": 512,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 12,
"num_hidden_layers": 8,
"num_key_value_heads": 4,
"pad_token_id": 4,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000,
"sep_token_id": 3,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.44.2",
"unk_token_id": 2,
"use_cache": true,
"vocab_size": 39818
}