thr3a's picture
630978b916ea68cec626270a745b3a5fd952ec20565007b4caab048ecc23ded0
0938ec8 verified
raw
history blame
841 Bytes
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 7168,
"max_position_embeddings": 4096,
"model_type": "llama",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"num_key_value_heads": 16,
"pretraining_tp": 1,
"quantization": {
"group_size": 128,
"bits": 8
},
"quantization_config": {
"group_size": 128,
"bits": 8
},
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 10000,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.40.2",
"use_cache": true,
"vocab_size": 99584
}