Re-quantize and re-upload model
#1
by
mtasic85
- opened
@Lyte llama.cpp fixed issue with BOS/EOS tokens, and all models need to be re-quantized and re-uploaded.
Please check https://github.com/ggerganov/llama.cpp/issues/9315
okay thanks for letting me know, I'll get to it asap!
@mtasic85 done using latest llama.cpp same as the other repo. feel free to try quantizing them yourself I've included the notebook i use to do this, it's the same one that i used for both RWKV models.
Lyte
changed discussion status to
closed