Llama-3-8B-16K / config.json
mattshumer's picture
bdf174fc007c048b694fe8cbc3b728fbb0b7f5faa0fa500e6738b89e5643ab33
359595f verified
raw
history blame
706 Bytes
{
"_name_or_path": "meta-llama/Meta-Llama-3-8B",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": 128001,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 16000,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 1000000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.40.0.dev0",
"use_cache": false,
"vocab_size": 128256
}