ArjDLAI/TestofNxcode-CQ-7B-orpo
Set do_sample=True
Update generation_kwargs dictionary
Format generation_kwargs dictionary
Update model to NTQAI/Nxcode-CQ-7B-orpo
Skip prompt for streamer
Add streamer to generation_kwargs
Add input_ids key to generation_kwargs
Add streaming again
Access input properties with .
Try to handle inputs slightly different
Fix problem with attention mask
Add progress bar
Set attention mask
Do not stream response, by now
Restore chat template
Add chat template directly to tokenizer
use chat template
Remove not needed string
Remove dead code
Apply a found chat template
Fix bos token
Put python code into a code block
Add streamer kwargs
Typo fix
Manually build chat template
Remove chat template usage
Add accelerate to requirements.txt
Refactor to fit model recomended usage
Refactor to fit model recomended usage
Add accelerate to requirements.txt
Add bitsandbytes to requirements.txt
Substitute 'pytorch' by 'torch' in requirements.txt
Add wheel to requirements.txt
Add pytorch to requirements.txt
Update requirements.txt
Remove requirements.txt
Update requirements.txt
Add quantization
Generate a full requirements.txt
Add pytorch to requirements.txt
Add transformers to requirements.txt
Remove unused packages
Do some refactorization
Add generation code
Add huggingface login
Add Git ignore file
Add application file
initial commit