lilloukas Ariel Lee commited on
Commit
f8ae334
1 Parent(s): feb7b4c

Update README.md (#5)

Browse files

- Update README.md (8cb3d80909e86402a3efdc13acba45cc9c9a6180)


Co-authored-by: Ariel Lee <[email protected]>

Files changed (1) hide show
  1. README.md +15 -2
README.md CHANGED
@@ -13,7 +13,7 @@ metrics:
13
 
14
  # 🥳 Platypus-30B has arrived!
15
 
16
- Platypus-30B is an instruction fine-tuned model based on the LLaMA-30B transformer architecture and takes advantage of [LoRA]([LoRA](https://arxiv.org/pdf/2106.09685.pdf).
17
 
18
  | Metric | Value |
19
  |-----------------------|-------|
@@ -47,7 +47,7 @@ Dataset of highly filtered and curated question and answer pairs. Release TBD.
47
 
48
  ## Limitations and bias
49
 
50
- The base LLaMA model is trained on various data, some of which may contain offensive, harmful, and biased content that can lead to toxic behavior. See Section 5.1 of the LLaMA [paper](https://arxiv.org/abs/2302.13971). We have not performed any studies to determine how fine-tuning on the aforementioned datasets affect the model's behavior and toxicity. Do not treat chat responses from this model as a substitute for human judgment or as a source of truth. Please use responsibly.
51
 
52
  ## Citations
53
 
@@ -58,4 +58,17 @@ The base LLaMA model is trained on various data, some of which may contain offen
58
  journal={arXiv preprint arXiv:2302.13971},
59
  year={2023}
60
  }
 
 
 
 
 
 
 
 
 
 
 
 
 
61
  ```
 
13
 
14
  # 🥳 Platypus-30B has arrived!
15
 
16
+ Platypus-30B is an instruction fine-tuned model based on the LLaMA-30B transformer architecture and takes advantage of LoRA.
17
 
18
  | Metric | Value |
19
  |-----------------------|-------|
 
47
 
48
  ## Limitations and bias
49
 
50
+ The base LLaMA model is trained on various data, some of which may contain offensive, harmful, and biased content that can lead to toxic behavior. See Section 5.1 of the LLaMA paper. We have not performed any studies to determine how fine-tuning on the aforementioned datasets affect the model's behavior and toxicity. Do not treat chat responses from this model as a substitute for human judgment or as a source of truth. Please use responsibly.
51
 
52
  ## Citations
53
 
 
58
  journal={arXiv preprint arXiv:2302.13971},
59
  year={2023}
60
  }
61
+ @article{DBLP:journals/corr/abs-2106-09685,
62
+ author = {Edward J. Hu and
63
+ Yelong Shen and
64
+ Phillip Wallis and
65
+ Zeyuan Allen{-}Zhu and
66
+ Yuanzhi Li and
67
+ Shean Wang and
68
+ Weizhu Chen},
69
+ title = {LoRA: Low-Rank Adaptation of Large Language Models},
70
+ journal = {CoRR},
71
+ year = {2021},
72
+ url = {https://arxiv.org/abs/2106.09685},
73
+ }
74
  ```