Training in progress, epoch 0
Browse files- adapter_config.json +6 -6
- adapter_model.safetensors +2 -2
- tokenizer.json +1 -29
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
-
"base_model_name_or_path":
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
@@ -20,14 +20,14 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"gate_proj",
|
25 |
-
"q_proj",
|
26 |
"up_proj",
|
27 |
-
"lm_head",
|
28 |
"o_proj",
|
|
|
29 |
"down_proj",
|
30 |
-
"
|
|
|
|
|
31 |
],
|
32 |
"task_type": "CAUSAL_LM",
|
33 |
"use_dora": false,
|
|
|
1 |
{
|
2 |
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": null,
|
5 |
"bias": "none",
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"k_proj",
|
|
|
|
|
24 |
"up_proj",
|
|
|
25 |
"o_proj",
|
26 |
+
"v_proj",
|
27 |
"down_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"q_proj",
|
30 |
+
"lm_head"
|
31 |
],
|
32 |
"task_type": "CAUSAL_LM",
|
33 |
"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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c2c06b8faed4f38736d1c667397400d23bbabdd200b81de4abea6c197d11f8a
|
3 |
+
size 1204686168
|
tokenizer.json
CHANGED
@@ -56,12 +56,6 @@
|
|
56 |
"post_processor": {
|
57 |
"type": "TemplateProcessing",
|
58 |
"single": [
|
59 |
-
{
|
60 |
-
"SpecialToken": {
|
61 |
-
"id": "<s>",
|
62 |
-
"type_id": 0
|
63 |
-
}
|
64 |
-
},
|
65 |
{
|
66 |
"Sequence": {
|
67 |
"id": "A",
|
@@ -70,24 +64,12 @@
|
|
70 |
}
|
71 |
],
|
72 |
"pair": [
|
73 |
-
{
|
74 |
-
"SpecialToken": {
|
75 |
-
"id": "<s>",
|
76 |
-
"type_id": 0
|
77 |
-
}
|
78 |
-
},
|
79 |
{
|
80 |
"Sequence": {
|
81 |
"id": "A",
|
82 |
"type_id": 0
|
83 |
}
|
84 |
},
|
85 |
-
{
|
86 |
-
"SpecialToken": {
|
87 |
-
"id": "<s>",
|
88 |
-
"type_id": 1
|
89 |
-
}
|
90 |
-
},
|
91 |
{
|
92 |
"Sequence": {
|
93 |
"id": "B",
|
@@ -95,17 +77,7 @@
|
|
95 |
}
|
96 |
}
|
97 |
],
|
98 |
-
"special_tokens": {
|
99 |
-
"<s>": {
|
100 |
-
"id": "<s>",
|
101 |
-
"ids": [
|
102 |
-
1
|
103 |
-
],
|
104 |
-
"tokens": [
|
105 |
-
"<s>"
|
106 |
-
]
|
107 |
-
}
|
108 |
-
}
|
109 |
},
|
110 |
"decoder": {
|
111 |
"type": "Sequence",
|
|
|
56 |
"post_processor": {
|
57 |
"type": "TemplateProcessing",
|
58 |
"single": [
|
|
|
|
|
|
|
|
|
|
|
|
|
59 |
{
|
60 |
"Sequence": {
|
61 |
"id": "A",
|
|
|
64 |
}
|
65 |
],
|
66 |
"pair": [
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
{
|
68 |
"Sequence": {
|
69 |
"id": "A",
|
70 |
"type_id": 0
|
71 |
}
|
72 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
73 |
{
|
74 |
"Sequence": {
|
75 |
"id": "B",
|
|
|
77 |
}
|
78 |
}
|
79 |
],
|
80 |
+
"special_tokens": {}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
81 |
},
|
82 |
"decoder": {
|
83 |
"type": "Sequence",
|
tokenizer_config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"add_bos_token":
|
3 |
"add_eos_token": false,
|
4 |
"add_prefix_space": null,
|
5 |
"added_tokens_decoder": {
|
|
|
1 |
{
|
2 |
+
"add_bos_token": false,
|
3 |
"add_eos_token": false,
|
4 |
"add_prefix_space": null,
|
5 |
"added_tokens_decoder": {
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a45dc026e9e7b54e6bb03fa91797a0cbd6c6745168fe426a4e05d62cfb790ff
|
3 |
size 5112
|