Pushed by DataDreamer
Browse filesUpdate datadreamer.json
- datadreamer.json +73 -0
datadreamer.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_card": {
|
3 |
+
"Model Card": [
|
4 |
+
"https://huggingface.co/google/t5-v1_1-base"
|
5 |
+
],
|
6 |
+
"License Information": [
|
7 |
+
"apache-2.0"
|
8 |
+
],
|
9 |
+
"Citation Information": [
|
10 |
+
"\n@inproceedings{Wolf_Transformers_State-of-the-Art_Natural_2020,\n author = {Wolf, Thomas and Debut, Lysandre and Sanh, Victor and Chaumond, Julien",
|
11 |
+
"\n@Misc{peft,\n title = {PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods},\n author = {Sourab Mangrulkar and Sylvain Gugger and Lysandre Debut and Younes"
|
12 |
+
]
|
13 |
+
},
|
14 |
+
"data_card": {
|
15 |
+
"Generate Research Paper Abstracts": {
|
16 |
+
"Model Name": [
|
17 |
+
"gpt-4"
|
18 |
+
],
|
19 |
+
"Model Card": [
|
20 |
+
"https://cdn.openai.com/papers/gpt-4-system-card.pdf"
|
21 |
+
],
|
22 |
+
"License Information": [
|
23 |
+
"https://openai.com/policies"
|
24 |
+
],
|
25 |
+
"Citation Information": [
|
26 |
+
"@article{OpenAI2023GPT4TR,\n title={GPT-4 Technical Report},\n author={OpenAI},\n journal={ArXiv},\n year={2023},\n volume={abs/2303.08774},\n url={https://api.semanticscholar.org/CorpusID:257532815}\n}",
|
27 |
+
"@article{ouyang2022training,\n title={Training language models to follow instructions with human feedback},\n author={Ouyang, Long and Wu, Jeffrey and Jiang, Xu and Almeida, Diogo and Wainwright, Carroll and Mishkin, Pamela and Zhang, Chong and Agarwal, Sandhini and Slama, Katarina and Ray, Alex and others},\n journal={Advances in Neural Information Processing Systems},\n volume={35},\n pages={27730--27744},\n year={2022}\n}"
|
28 |
+
]
|
29 |
+
},
|
30 |
+
"Generate Tweets from Abstracts": {
|
31 |
+
"Model Name": [
|
32 |
+
"gpt-4"
|
33 |
+
],
|
34 |
+
"Model Card": [
|
35 |
+
"https://cdn.openai.com/papers/gpt-4-system-card.pdf"
|
36 |
+
],
|
37 |
+
"License Information": [
|
38 |
+
"https://openai.com/policies"
|
39 |
+
],
|
40 |
+
"Citation Information": [
|
41 |
+
"@article{OpenAI2023GPT4TR,\n title={GPT-4 Technical Report},\n author={OpenAI},\n journal={ArXiv},\n year={2023},\n volume={abs/2303.08774},\n url={https://api.semanticscholar.org/CorpusID:257532815}\n}",
|
42 |
+
"@article{ouyang2022training,\n title={Training language models to follow instructions with human feedback},\n author={Ouyang, Long and Wu, Jeffrey and Jiang, Xu and Almeida, Diogo and Wainwright, Carroll and Mishkin, Pamela and Zhang, Chong and Agarwal, Sandhini and Slama, Katarina and Ray, Alex and others},\n journal={Advances in Neural Information Processing Systems},\n volume={35},\n pages={27730--27744},\n year={2022}\n}"
|
43 |
+
]
|
44 |
+
}
|
45 |
+
},
|
46 |
+
"__version__": "0.1.0",
|
47 |
+
"datetime": "2024-01-18T18:59:52.071528",
|
48 |
+
"type": "TrainHFFineTune",
|
49 |
+
"name": "Train an Abstract => Tweet Model",
|
50 |
+
"version": 1.0,
|
51 |
+
"fingerprint": "3e30bb93dbb5e421",
|
52 |
+
"req_versions": {
|
53 |
+
"dill": "0.3.7",
|
54 |
+
"sqlitedict": "2.1.0",
|
55 |
+
"torch": "2.1.2",
|
56 |
+
"numpy": "1.26.3",
|
57 |
+
"transformers": "4.36.2",
|
58 |
+
"datasets": "2.16.1",
|
59 |
+
"huggingface_hub": "0.20.2",
|
60 |
+
"accelerate": "0.26.1",
|
61 |
+
"peft": "0.7.1",
|
62 |
+
"tiktoken": "0.5.2",
|
63 |
+
"tokenizers": "0.15.0",
|
64 |
+
"openai": "1.8.0",
|
65 |
+
"ctransformers": "0.2.27",
|
66 |
+
"optimum": "1.16.1",
|
67 |
+
"bitsandbytes": "0.42.0",
|
68 |
+
"litellm": "1.15.3",
|
69 |
+
"trl": "0.7.6",
|
70 |
+
"setfit": "1.0.3"
|
71 |
+
},
|
72 |
+
"interpreter": "3.10.13 (main, Sep 11 2023, 13:44:35) [GCC 11.2.0]"
|
73 |
+
}
|