MildlyAggressiveGoose1
/

ggml-oasst-sft-6-llama-30B-q4_2

Model card Files Files and versions Community

ggml-oasst-sft-6-llama-30B-q4_2 / README.md

MildlyAggressiveGoose1's picture

MildlyAggressiveGoose1

Create README.md

15a359d almost 2 years ago

|

143 Bytes

(q4_2) GGML Open-Assistant SFT-6 LLaMa 30B 4-bit Quantized

4 bit version of Open-Assistant SFT-6 LLaMa 30B for llama.cpp quantized with q4_2