predibase/Mistral-7B-Instruct-v0.3-dequantized
Text Generation
•
Updated
•
178
Dequantized Base Models
Dequantized (fp16) versions of nf4 quantized base models for faster inference.
-
-
predibase/Mistral-7B-Instruct-v0.2-dequantized
Text Generation • Updated • 87 • 1 -
predibase/Mistral-7B-Instruct-v0.1-dequantized
Text Generation • Updated • 10 -
predibase/Mistral-7B-v0.1-dequantized
Text Generation • Updated • 97 -
predibase/NousResearch-Yarn-Mistral-7b-128k-dequantized
Text Generation • Updated -
predibase/Llama-2-7b-hf-dequantized
Text Generation • Updated • 5 -
predibase/Llama-2-7b-chat-hf-dequantized
Text Generation • Updated • 25 -
predibase/Llama-2-13b-chat-hf-dequantized
Text Generation • Updated • 3 -
predibase/Llama-2-70b-chat-hf-dequantized
Text Generation • Updated • 3 -
predibase/CodeLlama-7b-hf-dequantized
Text Generation • Updated • 196 -
predibase/CodeLlama-7b-Instruct-hf-dequantized
Text Generation • Updated • 183 -
predibase/CodeLlama-13b-Instruct-hf-dequantized
Text Generation • Updated • 15 -
predibase/CodeLlama-70B-Instruct-hf-dequantized
Text Generation • Updated • 4 -
predibase/zephyr-7b-beta-dequantized
Text Generation • Updated • 1 • 1 -
predibase/phi-2-dequantized
Text Generation • Updated • 1 -
predibase/Meta-Llama-3-8B-dequantized
Text Generation • Updated • 420 -
predibase/Meta-Llama-3-8B-Instruct-dequantized
Text Generation • Updated • 804 -
predibase/Meta-Llama-3-70B-dequantized
Text Generation • Updated • 152 -
predibase/Meta-Llama-3-70B-Instruct-dequantized
Text Generation • Updated • 1.57k