beaverlizi
commited on
Commit
•
46bee6e
1
Parent(s):
eece627
End of training
Browse files- README.md +2 -2
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- tokenizer.json +6 -16
- tokenizer_config.json +2 -1
- training_args.bin +2 -2
README.md
CHANGED
@@ -54,8 +54,8 @@ The following hyperparameters were used during training:
|
|
54 |
|
55 |
### Framework versions
|
56 |
|
57 |
-
- PEFT 0.
|
58 |
-
- Transformers 4.
|
59 |
- Pytorch 2.2.2+cu121
|
60 |
- Datasets 2.16.0
|
61 |
- Tokenizers 0.19.1
|
|
|
54 |
|
55 |
### Framework versions
|
56 |
|
57 |
+
- PEFT 0.12.0
|
58 |
+
- Transformers 4.44.2
|
59 |
- Pytorch 2.2.2+cu121
|
60 |
- Datasets 2.16.0
|
61 |
- Tokenizers 0.19.1
|
adapter_config.json
CHANGED
@@ -18,15 +18,15 @@
|
|
18 |
"peft_type": "LORA",
|
19 |
"r": 16,
|
20 |
"rank_pattern": {},
|
21 |
-
"revision":
|
22 |
"target_modules": [
|
23 |
"gate_proj",
|
24 |
-
"q_proj",
|
25 |
-
"v_proj",
|
26 |
"down_proj",
|
27 |
"o_proj",
|
|
|
|
|
28 |
"k_proj",
|
29 |
-
"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
18 |
"peft_type": "LORA",
|
19 |
"r": 16,
|
20 |
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
"target_modules": [
|
23 |
"gate_proj",
|
|
|
|
|
24 |
"down_proj",
|
25 |
"o_proj",
|
26 |
+
"v_proj",
|
27 |
+
"up_proj",
|
28 |
"k_proj",
|
29 |
+
"q_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcde731edc2aba39e3aa3ce672740a7f878a389bf334da3276bc109eaa523b11
|
3 |
size 167832240
|
tokenizer.json
CHANGED
@@ -31,23 +31,13 @@
|
|
31 |
"special": true
|
32 |
}
|
33 |
],
|
34 |
-
"normalizer":
|
35 |
-
|
36 |
-
"
|
37 |
-
|
38 |
-
|
39 |
-
|
40 |
-
},
|
41 |
-
{
|
42 |
-
"type": "Replace",
|
43 |
-
"pattern": {
|
44 |
-
"String": " "
|
45 |
-
},
|
46 |
-
"content": "▁"
|
47 |
-
}
|
48 |
-
]
|
49 |
},
|
50 |
-
"pre_tokenizer": null,
|
51 |
"post_processor": {
|
52 |
"type": "TemplateProcessing",
|
53 |
"single": [
|
|
|
31 |
"special": true
|
32 |
}
|
33 |
],
|
34 |
+
"normalizer": null,
|
35 |
+
"pre_tokenizer": {
|
36 |
+
"type": "Metaspace",
|
37 |
+
"replacement": "▁",
|
38 |
+
"prepend_scheme": "first",
|
39 |
+
"split": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
},
|
|
|
41 |
"post_processor": {
|
42 |
"type": "TemplateProcessing",
|
43 |
"single": [
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
|
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
@@ -31,7 +32,7 @@
|
|
31 |
"bos_token": "<s>",
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
34 |
-
"legacy":
|
35 |
"model_max_length": 32768,
|
36 |
"pad_token": "<unk>",
|
37 |
"padding_side": "right",
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
|
|
32 |
"bos_token": "<s>",
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
"eos_token": "</s>",
|
35 |
+
"legacy": false,
|
36 |
"model_max_length": 32768,
|
37 |
"pad_token": "<unk>",
|
38 |
"padding_side": "right",
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e9ba0506548d9171250f448fa22c69e49ba78aeef98b22718381e98613852fe
|
3 |
+
size 5432
|