chinnadhurai sankar
commited on
Commit
•
b199b74
1
Parent(s):
3f338f6
initial commit
Browse files- models/elm-0.25_news_content_generation/added_tokens.json +3 -0
- models/elm-0.25_news_content_generation/ckpt.pt +3 -0
- models/elm-0.25_news_content_generation/example_prompts.json +15 -0
- models/elm-0.25_news_content_generation/merges.txt +0 -0
- models/elm-0.25_news_content_generation/special_tokens_map.json +30 -0
- models/elm-0.25_news_content_generation/tokenizer.json +0 -0
- models/elm-0.25_news_content_generation/tokenizer_config.json +30 -0
- models/elm-0.25_news_content_generation/vocab.json +0 -0
- models/elm-0.75_news_content_generation/added_tokens.json +3 -0
- models/elm-0.75_news_content_generation/ckpt.pt +3 -0
- models/elm-0.75_news_content_generation/example_prompts.json +15 -0
- models/elm-0.75_news_content_generation/merges.txt +0 -0
- models/elm-0.75_news_content_generation/special_tokens_map.json +30 -0
- models/elm-0.75_news_content_generation/tokenizer.json +0 -0
- models/elm-0.75_news_content_generation/tokenizer_config.json +30 -0
- models/elm-0.75_news_content_generation/vocab.json +0 -0
- models/elm-1.0_news_content_generation/added_tokens.json +3 -0
- models/elm-1.0_news_content_generation/ckpt.pt +3 -0
- models/elm-1.0_news_content_generation/example_prompts.json +15 -0
- models/elm-1.0_news_content_generation/merges.txt +0 -0
- models/elm-1.0_news_content_generation/special_tokens_map.json +30 -0
- models/elm-1.0_news_content_generation/tokenizer.json +0 -0
- models/elm-1.0_news_content_generation/tokenizer_config.json +30 -0
- models/elm-1.0_news_content_generation/vocab.json +0 -0
models/elm-0.25_news_content_generation/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 50257
|
3 |
+
}
|
models/elm-0.25_news_content_generation/ckpt.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbcee5197e621a8de1d1871bbfeb1a5f7c9cc7ef878d12903e74acc141653e2e
|
3 |
+
size 840171202
|
models/elm-0.25_news_content_generation/example_prompts.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"inputs": [
|
3 |
+
"New neurons for life? Old people can still make fresh brain cells, study finds",
|
4 |
+
"Quips is an AI to help ALS patients speak with their own voice",
|
5 |
+
"Lucid beats Tesla Model S Plaid prototype on racetrack with its own tri-motor Air test vehicle",
|
6 |
+
"Inside Virgin Hyperloop, I caught a glimpse of a high-speed transport future",
|
7 |
+
"Speed up your website in 15 minutes (Sponsor)",
|
8 |
+
"Scientists Invent 'Invisible' Metamaterial With Bonus Reflect Mode",
|
9 |
+
"Kings of Leon Will Be the First Band to Release an Album as an NFT",
|
10 |
+
"In Rural Fukushima, 'The Border Between Monkeys And Humans Has Blurred'",
|
11 |
+
"Scientists May Have Discovered The First Planet Orbiting Three Stars At Once",
|
12 |
+
"Eat Less Red Meat, Scientists Said. Now Some Believe That Was Bad Advice"
|
13 |
+
],
|
14 |
+
"template": "[INST]The following headline is the headline of a news report. Please write the content of the news passage based on only this headline.\n\nHeadline: {input} \n\nContent:[/INST]"
|
15 |
+
}
|
models/elm-0.25_news_content_generation/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
models/elm-0.25_news_content_generation/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
models/elm-0.25_news_content_generation/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
models/elm-0.25_news_content_generation/tokenizer_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"50256": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"50257": {
|
14 |
+
"content": "[PAD]",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
}
|
21 |
+
},
|
22 |
+
"bos_token": "<|endoftext|>",
|
23 |
+
"clean_up_tokenization_spaces": true,
|
24 |
+
"eos_token": "<|endoftext|>",
|
25 |
+
"errors": "replace",
|
26 |
+
"model_max_length": 1024,
|
27 |
+
"pad_token": "[PAD]",
|
28 |
+
"tokenizer_class": "GPT2Tokenizer",
|
29 |
+
"unk_token": "<|endoftext|>"
|
30 |
+
}
|
models/elm-0.25_news_content_generation/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
models/elm-0.75_news_content_generation/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 50257
|
3 |
+
}
|
models/elm-0.75_news_content_generation/ckpt.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:846c2c75363b6343cc796a69739103203507b4cd159d15e91f4f866a32c3b769
|
3 |
+
size 1696314274
|
models/elm-0.75_news_content_generation/example_prompts.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"inputs": [
|
3 |
+
"New neurons for life? Old people can still make fresh brain cells, study finds",
|
4 |
+
"Quips is an AI to help ALS patients speak with their own voice",
|
5 |
+
"Lucid beats Tesla Model S Plaid prototype on racetrack with its own tri-motor Air test vehicle",
|
6 |
+
"Inside Virgin Hyperloop, I caught a glimpse of a high-speed transport future",
|
7 |
+
"Speed up your website in 15 minutes (Sponsor)",
|
8 |
+
"Scientists Invent 'Invisible' Metamaterial With Bonus Reflect Mode",
|
9 |
+
"Kings of Leon Will Be the First Band to Release an Album as an NFT",
|
10 |
+
"In Rural Fukushima, 'The Border Between Monkeys And Humans Has Blurred'",
|
11 |
+
"Scientists May Have Discovered The First Planet Orbiting Three Stars At Once",
|
12 |
+
"Eat Less Red Meat, Scientists Said. Now Some Believe That Was Bad Advice"
|
13 |
+
],
|
14 |
+
"template": "[INST]The following headline is the headline of a news report. Please write the content of the news passage based on only this headline.\n\nHeadline: {input} \n\nContent:[/INST]"
|
15 |
+
}
|
models/elm-0.75_news_content_generation/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
models/elm-0.75_news_content_generation/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
models/elm-0.75_news_content_generation/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
models/elm-0.75_news_content_generation/tokenizer_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"50256": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"50257": {
|
14 |
+
"content": "[PAD]",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
}
|
21 |
+
},
|
22 |
+
"bos_token": "<|endoftext|>",
|
23 |
+
"clean_up_tokenization_spaces": true,
|
24 |
+
"eos_token": "<|endoftext|>",
|
25 |
+
"errors": "replace",
|
26 |
+
"model_max_length": 1024,
|
27 |
+
"pad_token": "[PAD]",
|
28 |
+
"tokenizer_class": "GPT2Tokenizer",
|
29 |
+
"unk_token": "<|endoftext|>"
|
30 |
+
}
|
models/elm-0.75_news_content_generation/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
models/elm-1.0_news_content_generation/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[PAD]": 50257
|
3 |
+
}
|
models/elm-1.0_news_content_generation/ckpt.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8dd2579ef879fe40eae5a85dd255edab41644ecb425c98c41fb5ff626bf6257c
|
3 |
+
size 2124385874
|
models/elm-1.0_news_content_generation/example_prompts.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"inputs": [
|
3 |
+
"New neurons for life? Old people can still make fresh brain cells, study finds",
|
4 |
+
"Quips is an AI to help ALS patients speak with their own voice",
|
5 |
+
"Lucid beats Tesla Model S Plaid prototype on racetrack with its own tri-motor Air test vehicle",
|
6 |
+
"Inside Virgin Hyperloop, I caught a glimpse of a high-speed transport future",
|
7 |
+
"Speed up your website in 15 minutes (Sponsor)",
|
8 |
+
"Scientists Invent 'Invisible' Metamaterial With Bonus Reflect Mode",
|
9 |
+
"Kings of Leon Will Be the First Band to Release an Album as an NFT",
|
10 |
+
"In Rural Fukushima, 'The Border Between Monkeys And Humans Has Blurred'",
|
11 |
+
"Scientists May Have Discovered The First Planet Orbiting Three Stars At Once",
|
12 |
+
"Eat Less Red Meat, Scientists Said. Now Some Believe That Was Bad Advice"
|
13 |
+
],
|
14 |
+
"template": "[INST]The following headline is the headline of a news report. Please write the content of the news passage based on only this headline.\n\nHeadline: {input} \n\nContent:[/INST]"
|
15 |
+
}
|
models/elm-1.0_news_content_generation/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
models/elm-1.0_news_content_generation/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
models/elm-1.0_news_content_generation/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
models/elm-1.0_news_content_generation/tokenizer_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"50256": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"50257": {
|
14 |
+
"content": "[PAD]",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
}
|
21 |
+
},
|
22 |
+
"bos_token": "<|endoftext|>",
|
23 |
+
"clean_up_tokenization_spaces": true,
|
24 |
+
"eos_token": "<|endoftext|>",
|
25 |
+
"errors": "replace",
|
26 |
+
"model_max_length": 1024,
|
27 |
+
"pad_token": "[PAD]",
|
28 |
+
"tokenizer_class": "GPT2Tokenizer",
|
29 |
+
"unk_token": "<|endoftext|>"
|
30 |
+
}
|
models/elm-1.0_news_content_generation/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|