mamba-gpt-3b / config.json
chiliu
First model version
175af89
raw
history blame contribute delete
622 Bytes
{
"_name_or_path": "openlm-research/open_llama_3b",
"architectures": [
"LlamaForCausalLM"
],
"attention_probs_dropout_prob": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_dropout_prob": 0.0,
"hidden_size": 3200,
"initializer_range": 0.02,
"intermediate_size": 8640,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 26,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.29.2",
"use_cache": true,
"vocab_size": 32000
}