monsoon-nlp commited on
Commit
cfa422c
1 Parent(s): 471604c

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -18,7 +18,9 @@ widget:
18
 
19
  # nyrkr-joker-llama
20
 
21
- Essentials:
 
 
22
  - Based on LLaMa2-7b-hf (version 2, 7B params)
23
  - Used [QLoRA](https://github.com/artidoro/qlora/blob/main/qlora.py) to fine-tune on [1.2k rows of New Yorker caption contest](https://huggingface.co/datasets/jmhessel/newyorker_caption_contest)
24
  - Merged LLaMa2 with the adapter weights (from checkpoint step=160, epoch=2.7)
 
18
 
19
  # nyrkr-joker-llama
20
 
21
+ *New Yorker* cartoon description and caption -> attempt at a joke explanation
22
+
23
+ Technical details:
24
  - Based on LLaMa2-7b-hf (version 2, 7B params)
25
  - Used [QLoRA](https://github.com/artidoro/qlora/blob/main/qlora.py) to fine-tune on [1.2k rows of New Yorker caption contest](https://huggingface.co/datasets/jmhessel/newyorker_caption_contest)
26
  - Merged LLaMa2 with the adapter weights (from checkpoint step=160, epoch=2.7)