smiled0g commited on
Commit
d7c9564
·
verified ·
1 Parent(s): bc4c985

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForSequenceClassification"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 49,
8
+ "eos_token_id": 50,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3"
17
+ },
18
+ "initializer_range": 0.02,
19
+ "intermediate_size": 4096,
20
+ "label2id": {
21
+ "LABEL_0": 0,
22
+ "LABEL_1": 1,
23
+ "LABEL_2": 2,
24
+ "LABEL_3": 3
25
+ },
26
+ "max_position_embeddings": 256,
27
+ "mlp_bias": false,
28
+ "model_type": "llama",
29
+ "num_attention_heads": 16,
30
+ "num_hidden_layers": 16,
31
+ "num_key_value_heads": 16,
32
+ "pad_token_id": 52,
33
+ "pretraining_tp": 1,
34
+ "rms_norm_eps": 1e-06,
35
+ "rope_scaling": null,
36
+ "rope_theta": 10000.0,
37
+ "tie_word_embeddings": false,
38
+ "torch_dtype": "float32",
39
+ "transformers_version": "4.46.0",
40
+ "use_cache": true,
41
+ "vocab_size": 53
42
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cae2b5a59218b90a21e109ca32092aa8e69eb8734c2b81f6ab0f5190fb2eda69
3
+ size 1074127008
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a048d07939286d88a1dfa92b87d71e28302719440897fb3b738c6a9530889b60
3
+ size 2148344954
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cac18eaa1abad310c6a04342b6dba2252bf016b7b3dc34948cde24a669384353
3
+ size 1064
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5df9ae39540e2e8e5a145088031bab7365c612bad44a62defac1ede81896409
3
+ size 5240