Pinned issues
Issues
- 1
- 6
No stop words?
#21 opened by CyberTimon - 4
How to chat with history?
#37 opened by redthing1 - 22
illegal hardware instruction python
#29 opened by kufton - 4
Where to find the llama tokenizer?
#5 opened by ParisNeo - 1
- 4
- 5
- 6
Support for GPT2 and GPTJ?
#35 opened by mallorbc - 5
Sanely handle the new ggml weights against the old llama weights distributed by nomic
#1 opened by bmschmidt - 0
[EASY] PR the ggML converted gpt4all model
#33 opened by AndriyMulyar - 6
symbol not found in flat namespace '_cblas_sgemm'
#36 opened by aribo - 6
Segfault when running from Linux
#18 opened by DeadRedmond - 3
Run checksums against models?
#2 opened by bmschmidt - 14
- 1
- 7
OOM using gpt4all model (code 137, SIGKILL)
#12 opened by MLTQ - 1
ggml model is not recognized
#25 opened by TenKenZero - 1
Cannot convert the model to new ggml format
#24 opened by kaanyalova - 1
- 1
Error converting the model to ggml format (using tokenizer for huggingface as suggested - Python 3.10.10)
#15 opened by namp - 1
Are embeddings planned?
#20 opened by thiswillbeyourgithub - 1
'Model' object has no attribute '_ctx'
#16 opened by nocpinmylf - 0
Extract logits
#3 opened by bmschmidt - 1
GPU support ?
#6 opened by a5225662 - 2
Error running the example code
#9 opened by itachiluan - 2
- 3
Error running quickstart code - AttributeError: 'Model' object has no attribute '_ctx'`
#8 opened by MLTQ