llama_chinese_70B / config.json
root
train with more data
b813654
raw
history blame
619 Bytes
{
"architectures": [
"LLaMAForCausalLM"
],
"bos_token_id": null,
"eos_token_id": null,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 28672,
"max_position_embeddings": 2048,
"max_sequence_length": 4096,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 80,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.33.1",
"use_cache": true,
"vocab_size": 59672
}