Request: DOI

#30 opened 8 months ago by

ShinDC

GPTQ 4Bit Llama 3.2-3B-Instruct with 100% Accuracy recovery

#29 opened 8 months ago by

Qubitium

Request: DOI

#28 opened 8 months ago by

coming123

Request: DOI

#27 opened 8 months ago by

HesabAlaki4

Request: DOI

#24 opened 8 months ago by

lafesalomette

Token indices sequence length is longer than the specified maximum sequence length for this model (269923 > 131072)

#23 opened 8 months ago by

wasimsafdar

what is the chat template?

👀 1

#22 opened 9 months ago by

Blannikus

Request: DOI

#21 opened 9 months ago by

Leavesprior

1B and 3B are nice. Please make also an 8B so we can compare it to gemini flash 8B.

#20 opened 9 months ago by

ZeroWw

Issues w/ downloading the model: llama download: error: Model meta-llama/Llama-3.2-3B-Instruct not found

#19 opened 9 months ago by

Minimak88

Unable to Load Model

#18 opened 9 months ago by

NeMesIss

Extra "assistnat\n\n" at the beginning of the output

#17 opened 9 months ago by

alimah

Adding Evaluation Results

#16 opened 9 months ago by

Weyaxi

roger036

#15 opened 9 months ago by

Taylormann4u

Giving contextual messages to sagemaker instance in python

#14 opened 9 months ago by

bperin42

MMLU-Pro benchmark

#13 opened 9 months ago by

kth8

Cannot download the model with huggingface-cli

#11 opened 9 months ago by

lulmer

Thanks. This is astonishingly good for its size.

#9 opened 9 months ago by

phil111