starred/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-04-25 02:06:11 +02:00
Code Issues Packages Projects Releases Wiki Activity
2,574 Commits 389 Branches 511 Tags
d40497b9a29a17363a69534e793a364f058b5639
Commit Graph

3 Commits

Author SHA1 Message Date
Bruce MacDonald
d40497b9a2 Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL 
Co-authored-by: ManniX-ITA <20623405+mann1x@users.noreply.github.com>
 2024-05-03 14:51:07 -07:00
Michael Yang
185a927210 comments 2024-05-03 13:18:28 -07:00
Michael Yang
06b31e2e24 quantize any fp16/fp32 model 
- FROM /path/to/{safetensors,pytorch}
- FROM /path/to/fp{16,32}.bin
- FROM model:fp{16,32}
 2024-05-03 13:18:28 -07:00