Llama-2-13b-Drop8Block / config.json
s1ghhh
upload
452bb89
raw
history blame contribute delete
914 Bytes
{
"_name_or_path": null,
"architectures": [
"LlamaForCausalLM"
],
"auto_map": {
"AutoConfig": "configuration_dropped_llama.LlamaConfig",
"AutoModelForCausalLM": "modeling_dropped_llama.LlamaForCausalLM"
},
"drop_mlp_list": [33, 32, 31, 34, 30, 35, 29, 28],
"drop_attn_list": [33, 32, 31, 34, 30, 35, 29, 28],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0.dev0",
"use_cache": true,
"vocab_size": 32000
}