llama
seed-x-17b-instruct / config.json
tttoaster's picture
upload model
d4679d1
raw
history blame
761 Bytes
{
"_name_or_path": "/chat_sh/share_300719895/user/yuyingge/jinguo_code/DiscreteLearning_debug/train_output/04_08_seedx_llama13b_vitg_448_anyres_pretrain/checkpoint-36000-merged/llm",
"architectures": [
"LlamaForCausalLM"
],
"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,
"pad_token_id": 0,
"pretraining_tp": 2,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.30.2",
"use_cache": true,
"vocab_size": 32330
}