Dampish commited on
Commit
961061c
1 Parent(s): c1c78d0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -3
README.md CHANGED
@@ -46,19 +46,27 @@ StellarX, like its sibling models, is intended primarily for research purposes.
46
 
47
  It's important to note that StellarX is not intended for direct deployment without supervision. It is not designed for human-facing interactions, unlike models like ChatGPT, which have been fine-tuned using reinforcement learning from human feedback to better understand human instructions and dialogue.
48
 
49
- Furthermore, StellarX is limited to the English language and cannot be used for translation or text generation in other languages.
50
 
51
  Lastly, users should be aware of potential biases and limitations inherent in
52
 
53
- the training dataset. The Pile, used to train StellarX, contains texts known to include profanity, offensive content, and documented biases related to gender, religion, and race. Curation of StellarX's outputs and appropriate disclosure to the audience about the artificially generated nature of the text are strongly recommended.
54
 
55
  ## Community and Support
56
 
57
- To inquire about StellarX and receive support, you can join the Dampish's Discord server and engage in discussions in the #release-discussion channel. It is recommended to explore the existing documentation and resources available for GPT-NeoX-20B to familiarize yourself with the model before seeking assistance on Discord. For general correspondence, you can reach out to [email protected].
 
58
 
59
  ## Summary
60
 
61
  StellarX, a base language model developed by the Dampish, offers impressive language capabilities and flexibility. Trained on an extensive dataset and built upon the GPT-NeoX architecture, StellarX excels in various natural language processing tasks. Its carbon-friendly and resource-efficient design makes it accessible for local device deployment. Researchers and enthusiasts can freely explore StellarX for research purposes and personal use, while commercial users should adhere to the licensing terms.
62
 
63
 
 
 
 
 
 
 
 
64
  --ChatGPT
 
46
 
47
  It's important to note that StellarX is not intended for direct deployment without supervision. It is not designed for human-facing interactions, unlike models like ChatGPT, which have been fine-tuned using reinforcement learning from human feedback to better understand human instructions and dialogue.
48
 
49
+ Furthermore, StellarX is not limited to the English language if trained properly and can sometimes be used for translation aswell as text generation in other languages.
50
 
51
  Lastly, users should be aware of potential biases and limitations inherent in
52
 
53
+ the training dataset. The Pile, used to train StellarX, contains texts known to include profanity, offensive content, and documented biases related to gender, religion, and race. Curation of StellarX's outputs and appropriate disclosure to the audience about the artificially generated nature of the text are strongly recommended.
54
 
55
  ## Community and Support
56
 
57
+ To inquire about StellarX and receive support, you can join the Dampish's
58
+ server and engage in discussions in the #questions channel. It is recommended to explore the existing documentation and resources available for GPT-NeoX-20B to familiarize yourself with the model before seeking assistance on. For better information about GPT-NeoX, you can reach out to eleutherAI.
59
 
60
  ## Summary
61
 
62
  StellarX, a base language model developed by the Dampish, offers impressive language capabilities and flexibility. Trained on an extensive dataset and built upon the GPT-NeoX architecture, StellarX excels in various natural language processing tasks. Its carbon-friendly and resource-efficient design makes it accessible for local device deployment. Researchers and enthusiasts can freely explore StellarX for research purposes and personal use, while commercial users should adhere to the licensing terms.
63
 
64
 
65
+ Discord: https://discord.gg/vasyNnUa
66
+ Reach out to me personally on Discord via the username: Dampish#3607
67
+
68
+ Thank you for your time.
69
+
70
+
71
+
72
  --ChatGPT