error : unknown data type:U8
#4 opened 19 days ago
by
bamudx
VLLM with error Blockwise quantization only supports 16/32-bit floats, but got torch.uint8
6
#3 opened about 1 month ago
by
ChloeHuang1
How to convert this model to GGUF?
2
#2 opened about 1 month ago
by
degot
The `tokenizer_config.json` is missing the `chat_template` jinja?
1
#1 opened about 1 month ago
by
ubergarm