25 lines
580 B
JSON
25 lines
580 B
JSON
{
|
|
"_name_or_path": "airoboros-13b-gpt4-1.4",
|
|
"architectures": [
|
|
"LlamaForCausalLM"
|
|
],
|
|
"bos_token_id": 0,
|
|
"eos_token_id": 1,
|
|
"hidden_act": "silu",
|
|
"hidden_size": 5120,
|
|
"initializer_range": 0.02,
|
|
"intermediate_size": 13824,
|
|
"max_position_embeddings": 2048,
|
|
"max_sequence_length": 2048,
|
|
"model_type": "llama",
|
|
"num_attention_heads": 40,
|
|
"num_hidden_layers": 40,
|
|
"pad_token_id": -1,
|
|
"rms_norm_eps": 1e-06,
|
|
"tie_word_embeddings": false,
|
|
"torch_dtype": "float16",
|
|
"transformers_version": "4.28.1",
|
|
"use_cache": false,
|
|
"vocab_size": 32000
|
|
}
|