LLaMAX3-8B-Alpaca / config.json
Lego-MT's picture
First model version
49193eb
raw
history blame contribute delete
913 Bytes
{
"_name_or_path": "/cpfs01/shared/NLP-A100/NLP-A100_hdd/yqlu/model/trained_model/llama3_pretrain/sft/Meta-Llama-3-8B_Meta-Llama-3-8B_fedmt_mc4_low_1_sampling_long_gap1_seed0_shuf_2048_5_bfloat16_2e-5-v1_checkpoint-13500_alpaca_128_1_bfloat16_2e-5/checkpoint-812",
"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": 8192,
"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": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.40.0",
"use_cache": true,
"vocab_size": 128256
}