TOFU-SFT/Meta-Llama-3-70B-Instruct-4bit
Text Generation • 71B • Updated • 100
Quantized Models
Quantized versions of models used in the experiments.
-
-
TOFU-SFT/Mistral-Nemo-Base-2407-4bit
12B • Updated • 85 -
TOFU-SFT/OLMo-2-1124-13B-4bit
14B • Updated • 62 -
TOFU-SFT/pythia-12b-4bit
12B • Updated • 78 -
TOFU-SFT/Llama-3.1-8B-4bit
Text Generation • 8B • Updated • 57 -
TOFU-SFT/Qwen3-8B-4bit
Text Generation • 8B • Updated • 91 -
TOFU-SFT/phi-4-4bit
Text Generation • 15B • Updated • 59 -
TOFU-SFT/Qwen2.5-Math-1.5B-4bit
Text Generation • 2B • Updated • 59 -
TOFU-SFT/Qwen2.5-Math-7B-4bit
Text Generation • 8B • Updated • 59 -
TOFU-SFT/deepseek-math-7b-base-4bit
7B • Updated • 57