LLaMAX2-7B-Alpaca / config.json
Lego-MT's picture
First model version
7e5d45e
raw
history blame contribute delete
849 Bytes
{
"_name_or_path": "/cpfs01/shared/NLP-A100/NLP-A100_hdd/yqlu/model/trained_model/checkpoint-9000_mc4_and_fedmt_normal_sampling_2048_3_bfloat16_2e-5-v3_checkpoint-1300_alpaca_128_1_bfloat16_2e-5/checkpoint-814",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 11008,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 32,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.36.2",
"use_cache": true,
"vocab_size": 32000
}