NexusRaven-13B / config.json
brian-yu-nexusflow's picture
Duplicate from Nexusflow/NexusRaven-13B_20230928
51e4adc
raw
history blame
671 Bytes
{
"_name_or_path": "codellama/CodeLlama-13b-Instruct-hf",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"low_cpu_mem_usage": true,
"max_position_embeddings": 16384,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 1000000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.33.2",
"use_cache": true,
"vocab_size": 32024
}