config.json

{
	"architectures": [
		"LlamaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 1,
	"eos_token_id": 361,
	"hidden_act": "silu",
	"hidden_size": 4096,
	"initializer_range": 0.02,
	"intermediate_size": 14336,
	"max_position_embeddings": 4096,
	"mlp_bias": false,
	"model_type": "llama",
	"num_attention_heads": 32,
	"num_hidden_layers": 32,
	"num_key_value_heads": 8,
	"pad_token_id": 0,
	"pretraining_tp": 1,
	"quantization_config": {
		"bits": 6.5,
		"calibration": {
			"dataset": "(default)",
			"length": 2048,
			"rows": 115
		},
		"head_bits": 8,
		"quant_method": "exl2",
		"version": "0.1.8"
	},
	"rms_norm_eps": 1e-05,
	"rope_scaling": null,
	"rope_theta": 500000.0,
	"tie_word_embeddings": false,
	"torch_dtype": "float16",
	"transformers_version": "4.44.0",
	"use_cache": true,
	"vocab_size": 102400
}