TanviGupta
commited on
Commit
•
adec093
1
Parent(s):
d58a639
Training in progress, step 2
Browse files- adapter_config.json +4 -10
- adapter_model.bin +3 -0
- adapter_model.safetensors +1 -1
- special_tokens_map.json +1 -7
- tokenizer.json +6 -1
- tokenizer_config.json +0 -112
- training_args.bin +2 -2
adapter_config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
"base_model_name_or_path": "vilsonrodrigues/falcon-7b-instruct-sharded",
|
5 |
"bias": "none",
|
@@ -8,22 +7,17 @@
|
|
8 |
"init_lora_weights": true,
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
11 |
-
"loftq_config": {},
|
12 |
"lora_alpha": 32,
|
13 |
"lora_dropout": 0.05,
|
14 |
-
"megatron_config": null,
|
15 |
-
"megatron_core": "megatron.core",
|
16 |
"modules_to_save": null,
|
17 |
"peft_type": "LORA",
|
18 |
"r": 32,
|
19 |
-
"rank_pattern": {},
|
20 |
"revision": null,
|
21 |
"target_modules": [
|
22 |
-
"dense_h_to_4h",
|
23 |
"query_key_value",
|
24 |
-
"
|
25 |
-
"
|
|
|
26 |
],
|
27 |
-
"task_type": "CAUSAL_LM"
|
28 |
-
"use_rslora": false
|
29 |
}
|
|
|
1 |
{
|
|
|
2 |
"auto_mapping": null,
|
3 |
"base_model_name_or_path": "vilsonrodrigues/falcon-7b-instruct-sharded",
|
4 |
"bias": "none",
|
|
|
7 |
"init_lora_weights": true,
|
8 |
"layers_pattern": null,
|
9 |
"layers_to_transform": null,
|
|
|
10 |
"lora_alpha": 32,
|
11 |
"lora_dropout": 0.05,
|
|
|
|
|
12 |
"modules_to_save": null,
|
13 |
"peft_type": "LORA",
|
14 |
"r": 32,
|
|
|
15 |
"revision": null,
|
16 |
"target_modules": [
|
|
|
17 |
"query_key_value",
|
18 |
+
"dense",
|
19 |
+
"dense_h_to_4h",
|
20 |
+
"dense_4h_to_h"
|
21 |
],
|
22 |
+
"task_type": "CAUSAL_LM"
|
|
|
23 |
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b49b16a5d00f2cb968265f23c32f65be63704e42370217b411a1c2cfa8854eae
|
3 |
+
size 261189453
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 261131840
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cf6ef492c483636aa7ee07c5fdd1ce3e7c3d2b8ecdb10b30d8d58a2c1f0f618
|
3 |
size 261131840
|
special_tokens_map.json
CHANGED
@@ -12,12 +12,6 @@
|
|
12 |
">>SUFFIX<<",
|
13 |
">>MIDDLE<<"
|
14 |
],
|
15 |
-
"eos_token":
|
16 |
-
"content": "<|endoftext|>",
|
17 |
-
"lstrip": false,
|
18 |
-
"normalized": false,
|
19 |
-
"rstrip": false,
|
20 |
-
"single_word": false
|
21 |
-
},
|
22 |
"pad_token": "<|endoftext|>"
|
23 |
}
|
|
|
12 |
">>SUFFIX<<",
|
13 |
">>MIDDLE<<"
|
14 |
],
|
15 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
"pad_token": "<|endoftext|>"
|
17 |
}
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 256,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
tokenizer_config.json
CHANGED
@@ -1,116 +1,5 @@
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
3 |
-
"added_tokens_decoder": {
|
4 |
-
"0": {
|
5 |
-
"content": ">>TITLE<<",
|
6 |
-
"lstrip": false,
|
7 |
-
"normalized": false,
|
8 |
-
"rstrip": false,
|
9 |
-
"single_word": false,
|
10 |
-
"special": true
|
11 |
-
},
|
12 |
-
"1": {
|
13 |
-
"content": ">>ABSTRACT<<",
|
14 |
-
"lstrip": false,
|
15 |
-
"normalized": false,
|
16 |
-
"rstrip": false,
|
17 |
-
"single_word": false,
|
18 |
-
"special": true
|
19 |
-
},
|
20 |
-
"2": {
|
21 |
-
"content": ">>INTRODUCTION<<",
|
22 |
-
"lstrip": false,
|
23 |
-
"normalized": false,
|
24 |
-
"rstrip": false,
|
25 |
-
"single_word": false,
|
26 |
-
"special": true
|
27 |
-
},
|
28 |
-
"3": {
|
29 |
-
"content": ">>SUMMARY<<",
|
30 |
-
"lstrip": false,
|
31 |
-
"normalized": false,
|
32 |
-
"rstrip": false,
|
33 |
-
"single_word": false,
|
34 |
-
"special": true
|
35 |
-
},
|
36 |
-
"4": {
|
37 |
-
"content": ">>COMMENT<<",
|
38 |
-
"lstrip": false,
|
39 |
-
"normalized": false,
|
40 |
-
"rstrip": false,
|
41 |
-
"single_word": false,
|
42 |
-
"special": true
|
43 |
-
},
|
44 |
-
"5": {
|
45 |
-
"content": ">>ANSWER<<",
|
46 |
-
"lstrip": false,
|
47 |
-
"normalized": false,
|
48 |
-
"rstrip": false,
|
49 |
-
"single_word": false,
|
50 |
-
"special": true
|
51 |
-
},
|
52 |
-
"6": {
|
53 |
-
"content": ">>QUESTION<<",
|
54 |
-
"lstrip": false,
|
55 |
-
"normalized": false,
|
56 |
-
"rstrip": false,
|
57 |
-
"single_word": false,
|
58 |
-
"special": true
|
59 |
-
},
|
60 |
-
"7": {
|
61 |
-
"content": ">>DOMAIN<<",
|
62 |
-
"lstrip": false,
|
63 |
-
"normalized": false,
|
64 |
-
"rstrip": false,
|
65 |
-
"single_word": false,
|
66 |
-
"special": true
|
67 |
-
},
|
68 |
-
"8": {
|
69 |
-
"content": ">>PREFIX<<",
|
70 |
-
"lstrip": false,
|
71 |
-
"normalized": false,
|
72 |
-
"rstrip": false,
|
73 |
-
"single_word": false,
|
74 |
-
"special": true
|
75 |
-
},
|
76 |
-
"9": {
|
77 |
-
"content": ">>SUFFIX<<",
|
78 |
-
"lstrip": false,
|
79 |
-
"normalized": false,
|
80 |
-
"rstrip": false,
|
81 |
-
"single_word": false,
|
82 |
-
"special": true
|
83 |
-
},
|
84 |
-
"10": {
|
85 |
-
"content": ">>MIDDLE<<",
|
86 |
-
"lstrip": false,
|
87 |
-
"normalized": false,
|
88 |
-
"rstrip": false,
|
89 |
-
"single_word": false,
|
90 |
-
"special": true
|
91 |
-
},
|
92 |
-
"11": {
|
93 |
-
"content": "<|endoftext|>",
|
94 |
-
"lstrip": false,
|
95 |
-
"normalized": false,
|
96 |
-
"rstrip": false,
|
97 |
-
"single_word": false,
|
98 |
-
"special": true
|
99 |
-
}
|
100 |
-
},
|
101 |
-
"additional_special_tokens": [
|
102 |
-
">>TITLE<<",
|
103 |
-
">>ABSTRACT<<",
|
104 |
-
">>INTRODUCTION<<",
|
105 |
-
">>SUMMARY<<",
|
106 |
-
">>COMMENT<<",
|
107 |
-
">>ANSWER<<",
|
108 |
-
">>QUESTION<<",
|
109 |
-
">>DOMAIN<<",
|
110 |
-
">>PREFIX<<",
|
111 |
-
">>SUFFIX<<",
|
112 |
-
">>MIDDLE<<"
|
113 |
-
],
|
114 |
"clean_up_tokenization_spaces": true,
|
115 |
"eos_token": "<|endoftext|>",
|
116 |
"model_input_names": [
|
@@ -118,6 +7,5 @@
|
|
118 |
"attention_mask"
|
119 |
],
|
120 |
"model_max_length": 2048,
|
121 |
-
"pad_token": "<|endoftext|>",
|
122 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
123 |
}
|
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"clean_up_tokenization_spaces": true,
|
4 |
"eos_token": "<|endoftext|>",
|
5 |
"model_input_names": [
|
|
|
7 |
"attention_mask"
|
8 |
],
|
9 |
"model_max_length": 2048,
|
|
|
10 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
11 |
}
|
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:c78cdf5af9dd84fb5ce366b87bdfb81794a9752362610382ffd78b090481d2bc
|
3 |
+
size 4155
|