File size: 1,075 Bytes
9ad43e9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
{
	"_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
	"architectures": [
		"LlamaForCausalLM"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"bos_token_id": 128000,
	"eos_token_id": [
		128001,
		128008,
		128009
	],
	"head_dim": 128,
	"hidden_act": "silu",
	"hidden_size": 3072,
	"initializer_range": 0.02,
	"intermediate_size": 8192,
	"max_position_embeddings": 131072,
	"mlp_bias": false,
	"model_type": "llama",
	"num_attention_heads": 24,
	"num_hidden_layers": 28,
	"num_key_value_heads": 8,
	"pretraining_tp": 1,
	"quantization_config": {
		"bits": 6.5,
		"calibration": {
			"dataset": "(default)",
			"length": 2048,
			"rows": 115
		},
		"head_bits": 8,
		"quant_method": "exl2",
		"version": "0.2.7"
	},
	"rms_norm_eps": 1e-05,
	"rope_scaling": {
		"factor": 32.0,
		"high_freq_factor": 4.0,
		"low_freq_factor": 1.0,
		"original_max_position_embeddings": 8192,
		"rope_type": "llama3"
	},
	"rope_theta": 500000.0,
	"tie_word_embeddings": true,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.46.1",
	"use_cache": true,
	"vocab_size": 193800
}