quant of jondurbin's bagel-dpo-34b-v0.2
fits into 24gb with 16k context on windows
python3 convert.py \
-i /input/jondurbin_bagel-dpo-34b-v0.2/ \
-c /input/pippa_cleaned/0000.parquet \
-o /output/temp/ \
-cf /output/bagel-dpo-34b-v0.2-4.65bpw-h6-exl2/ \
-l 8192 \
-ml 8192 \
-b 4.65 \
-hb 6
- Downloads last month
- 22
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.