EverythingLM-13b-16k / config.json
totally-not-an-llm's picture
Upload 11 files
de94729
raw
history blame contribute delete
724 Bytes
{
"_name_or_path": "/home/pikal/Coding/everythinglm/LLongMA-2-13b-16k",
"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": 16384,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 2,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 4.0,
"type": "linear"
},
"tie_word_embeddings": false,
"torch_dtype": "float16",
"transformers_version": "4.31.0",
"use_cache": true,
"use_flash_attention": false,
"vocab_size": 32000
}