Transformers
PyTorch
llama
text-generation-inference
Inference Endpoints
mc2-llama-13b / config.json
luciusssss's picture
Upload 5 files
70ddcec verified
raw
history blame
544 Bytes
{
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"tokenizer_class": "LlamaTokenizer",
"transformers_version": "4.33.1",
"use_cache": true,
"vocab_size": 71768
}