Quant Infos
- needs #8604 & latest master with tekken tokenizer fixes applied
- quants done with an importance matrix for improved quantization loss
- Requantized ggufs & imatrix from hf bf16
- Wide coverage of different gguf quant types from Q_8_0 down to IQ1_S
- experimental custom quant types
_L
with--output-tensor-type f16 --token-embedding-type f16
(same as bartowski's)
- experimental custom quant types
- Imatrix generated with this multi-purpose dataset by bartowski.
./imatrix -m $model_name-bf16.gguf -f calibration_datav3.txt -o $model_name.imatrix
Original Model Card:
TODO
- Downloads last month
- 77
Unable to determine this model's library. Check the
docs
.