pseudotensor's picture
Add 32k version of codellama instruct
f402e86
raw
history blame contribute delete
609 Bytes
{
"architectures": [
"LlamaForCausalLM"
],
"pad_token_id": 0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 8192,
"initializer_range": 0.02,
"intermediate_size": 22016,
"max_position_embeddings": 32768,
"model_type": "llama",
"num_attention_heads": 64,
"num_hidden_layers": 48,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.33.0.dev0",
"use_cache": true,
"vocab_size": 32000,
"rope_theta": 1000000
}