WizardLM-13B-V1.0 / config.json
WizardLM's picture
WizardLM-13B-1.0 weight diff
b259676
raw
history blame
635 Bytes
{
"_name_or_path": "/workspaceblobstore/qins/llamax/trained_models/13B_sg_alpaca_prefix_mix280k_2048_e3_2e_5/checkpoint-1440",
"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,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.30.0.dev0",
"use_cache": false,
"vocab_size": 32001
}