An uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2 7B.
237 Pulls Updated 5 months ago
Updated 5 months ago
5 months ago
7c430080facc · 4.6GB
Readme
DolphinCoder StarCoder2 7b 🐬
sponsored by latitude.sh.
Join our Discord! https://discord.gg/cognitivecomputations
This model is based on StarCoder2-7b and is subject to bigcode-openrail-m license.
This Dolphin is really good at coding, I trained with a lot of coding data.
This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models
You are responsible for any content you create using this model. Enjoy responsibly.
Training
It took 2 days to train 3 epochs on 8x L40S’s using qLoRA and Axolotl
Prompt format:
This model uses ChatML prompt format.
<|im_start|>system
You are DolphinCoder, a helpful AI programming assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant
Example:
<|im_start|>system
You are DolphinCoder, a master at software engineering and coding in any programming language.
<|im_start|>user
Please write me a program in golang that parses all the lines in a file, and reverses them character-wise, and saves it to a new file.
<|im_start|>assistant
Quantized models
Gratitude
- This model was made possible by the generous sponsorship of latitude.sh.
- Welcome Microsoft to Open Source AI! Thank you for the Orca-Math Dataset!
- Huge thank you to BigCode for training and publishing the weights of StarCoder2
- HUGE Thank you to the dataset authors: @ise-uiuc, @teknium, @m-a-p
- And HUGE thanks to @winglian and the Axolotl contributors for making the best training framework!
- Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way.