openpangu_7b_lora / config.json
killer66678's picture
Initial release: merged LoRA weights, license, model card
0e3f80c verified
raw
history blame contribute delete
861 Bytes
{
"architectures": [
"PanguEmbeddedForCausalLM"
],
"attention_dropout": 0.0,
"auto_map": {
"AutoConfig": "configuration_openpangu_dense.PanguEmbeddedConfig",
"AutoModel": "modeling_openpangu_dense.PanguEmbeddedForCausalLM",
"AutoModelForCausalLM": "modeling_openpangu_dense.PanguEmbeddedForCausalLM"
},
"bias": true,
"bos_token_id": 1,
"dtype": "bfloat16",
"eos_token_id": 45892,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12800,
"max_position_embeddings": 32768,
"model_type": "PanguEmbedded",
"num_attention_heads": 32,
"num_hidden_layers": 34,
"num_key_value_heads": 8,
"pad_token_id": 0,
"rms_norm_eps": 1e-05,
"rope_theta": 16000000.0,
"tie_word_embeddings": false,
"transformers_version": "4.56.1",
"use_cache": true,
"vocab_size": 153376
}