TableLlama / config.json
zhangtianshu
First model version
283df9d
raw
history blame
688 Bytes
{
"_name_or_path": "/ML-A800/models/Llama-2-7b-longlora-8k-ft",
"architectures": [
"LlamaForCausalLM"
],
"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": {
"factor": 2.0,
"type": "linear"
},
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.33.2",
"use_cache": true,
"vocab_size": 32001
}