Issues
- 0
- 1
- 3
Scores and probability calcuations
#15 opened by namdw - 13
- 0
DPO baseline implementation
#22 opened by yesiam-png - 3
- 0
SPPO Implementation on Axolotl!
#21 opened by kaykyr - 1
Adaptation for 4-bit Quantization Training/Responses Generation (with 2 Home GPUs)
#16 opened by kaykyr - 1
- 3
Any chance it work on my homelab?
#13 opened by kaykyr - 2
Suggestion: Gemma 2 9B and 27B.
#3 opened by kaykyr - 4
- 0
Ranking speed & training hyperparameters
#10 opened by skramer-dev - 0
Some packages' version are too old
#7 opened by qy1026 - 1
Questions about the training code
#6 opened by blackblue9 - 0
ShareGPT appending
#4 opened by Kquant03 - 1
Is it possible to run llama 3-70B and/or mixtral 8x22b through this process?
#1 opened by RandomInternetPreson - 2
ConnectionError: Couldn't reach 'synthetic_data_llama-3-8b-instruct-sppo-iter3_score' on the Hub (ConnectionError)
#2 opened by xinghuang2050