Issues
- 1
Pointer to supported gguf models?
#36 opened by pitsianis - 1
Support chat templates
#17 opened by cafaxo - 1
- 5
- 2
Make the quantization code less insane
#14 opened by cafaxo - 3
A GPU version of inference code
#7 opened by BangBOOM - 0
Hope support more model formats
#24 opened by zsz00 - 1
Support saving weights to a standard format
#32 opened by trholding - 1
- 3
Training code
#4 opened by cafaxo - 0
interrupt output
#33 opened by lazarusA - 0
Support weight decay for Adam optimizer
#29 opened by fabian-sp - 3
- 2
LoRA and finetuning
#22 opened by Thodoris1999 - 0
Create vocabulary from text
#20 opened by cafaxo - 0
Speed up tokenizer
#19 opened by cafaxo - 3
amazing speed!
#12 opened by yi - 3
More high-level operations
#11 opened by pitsianis - 4
ggml model ERROR: TaskFailedException nested task error: bitcast: target type not a leaf primitive type
#16 opened by pitsianis - 0
Test perplexity
#13 opened by cafaxo - 5
Quantization support
#10 opened by cafaxo - 1
adding prompting
#3 opened by BangBOOM - 0
- 0
Adapt to new tokenizer.bin format
#1 opened by cafaxo