concord dsl commited on
Commit
f22a0bd
·
1 Parent(s): a7b6995

add final PolyCoder0.4B weights for code search finetuned on CoSQA and CSN

Browse files
checkpoint-best-aver/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-best-aver/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1ed17fe2b97cd1ca4bf5d852dd418a7a72b5cc31c36f4e672945501651c2a6f
3
+ size 2830761413
checkpoint-best-aver/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aea60b57b8b61f97067c7196b560aaadb33ec9ae6c161ecf2ac2e98a5f5dd8f8
3
+ size 1516101761
checkpoint-best-aver/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d836644193ca032649e2268d36d73be5049be19d1eac54b42c4eacee406d023
3
+ size 627
checkpoint-best-aver/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-best-aver/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-best-aver/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "do_lower_case": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "special_tokens_map_file": "/home/mootez/projects/def-tusharma/mootez/hf_models/PolyCoder-0.4B/special_tokens_map.json",
25
+ "tokenizer_class": "GPT2Tokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
checkpoint-best-aver/training_0.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0960328a414efaa8f7f20ecb6130d1f177585d4f8d7c5957022bc9754266bca9
3
+ size 1973
checkpoint-best-aver/training_1.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9451b195d85970e0d6775910b3f2b2b6af5d92f1a685c43eabc4bf3f3c92c61
3
+ size 1973
checkpoint-best-aver/training_10.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fd9e356ac4e785a6ba88a63f1ddeee38ec46f0b3d16309d691cf1ee680524b2
3
+ size 1975
checkpoint-best-aver/training_2.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b7bd508993112a2035711bff541e3da12d8bd7ee4c2ce7d34c023e3143223b6
3
+ size 1973
checkpoint-best-aver/training_3.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1e5b8d4ae35010f62acdb1bfafddf6e497a8115ad05e7289fde37a913c03017
3
+ size 1973
checkpoint-best-aver/training_4.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c2d294cd4315a883d928331d5ed2cc13c640eb24e022de3ac4ee12eae1649ce
3
+ size 1973
checkpoint-best-aver/training_5.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9edbb50c3febec6f6f0066f0a13c903e2e8ce2b9575aec6a3eb227e243a8b59
3
+ size 1973
checkpoint-best-aver/training_6.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35f5d3f709a41a27482f6f6ab3b21c09813893d9e7d5ef24828eeec03f117bad
3
+ size 1973
checkpoint-best-aver/training_9.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aadbd0a4d73559cada89f0d3716725c4b2519bee9accc427e4a733a5b979c7bd
3
+ size 1973
checkpoint-best-aver/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-last/idx_file.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 19
checkpoint-last/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-last/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad022caab4344780326bc8e293709e342311517056fa6833955eb6d234043a74
3
+ size 2830761413
checkpoint-last/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b62b0daf00064bee0ad956ddba2fe2ca229b5d61f23d6457c18e4e66f3d48e2e
3
+ size 1516101761
checkpoint-last/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67080b4cf077d5d8231861c369490433d594b636bb7de899f7db1c379713b34d
3
+ size 627
checkpoint-last/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-last/step_file.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 20
checkpoint-last/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-last/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "do_lower_case": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "special_tokens_map_file": "/home/mootez/projects/def-tusharma/mootez/hf_models/PolyCoder-0.4B/special_tokens_map.json",
25
+ "tokenizer_class": "GPT2Tokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
checkpoint-last/vocab.json ADDED
The diff for this file is too large to render. See raw diff