shuyuej commited on
Commit
0a31baa
1 Parent(s): b6d49b5

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +52 -0
  2. model.safetensors +3 -0
  3. quantize_config.json +13 -0
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./save_folder",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "hidden_act": "silu",
15
+ "hidden_size": 8192,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 28672,
18
+ "max_position_embeddings": 131072,
19
+ "mlp_bias": false,
20
+ "model_type": "llama",
21
+ "num_attention_heads": 64,
22
+ "num_hidden_layers": 80,
23
+ "num_key_value_heads": 8,
24
+ "pretraining_tp": 1,
25
+ "quantization_config": {
26
+ "bits": 4,
27
+ "checkpoint_format": "gptq",
28
+ "damp_percent": 0.01,
29
+ "desc_act": true,
30
+ "group_size": 1024,
31
+ "model_file_base_name": null,
32
+ "model_name_or_path": null,
33
+ "quant_method": "gptq",
34
+ "static_groups": false,
35
+ "sym": true,
36
+ "true_sequential": true
37
+ },
38
+ "rms_norm_eps": 1e-05,
39
+ "rope_scaling": {
40
+ "factor": 8.0,
41
+ "high_freq_factor": 4.0,
42
+ "low_freq_factor": 1.0,
43
+ "original_max_position_embeddings": 8192,
44
+ "rope_type": "llama3"
45
+ },
46
+ "rope_theta": 500000.0,
47
+ "tie_word_embeddings": false,
48
+ "torch_dtype": "float16",
49
+ "transformers_version": "4.43.1",
50
+ "use_cache": true,
51
+ "vocab_size": 128256
52
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2175212920c4d4fc5211ce761dae997066a0d074ccc34830ef9148ad7cb80013
3
+ size 38623146768
quantize_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bits": 4,
3
+ "group_size": 1024,
4
+ "damp_percent": 0.01,
5
+ "desc_act": true,
6
+ "static_groups": false,
7
+ "sym": true,
8
+ "true_sequential": true,
9
+ "model_name_or_path": null,
10
+ "model_file_base_name": null,
11
+ "quant_method": "gptq",
12
+ "checkpoint_format": "gptq"
13
+ }