Searched around in a few other repos, and could only find F16 versions of it, but not the original unquantized, so:
This is the unquantized BF16 version of the model Mistral-7B-Instruct-v0.3 that is the same as the safetensors with no quality loss.
- Downloads last month
- 24
Hardware compatibility
Log In
to view the estimation
16-bit
Model tree for noctrex/Mistral-7B-Instruct-v0.3-BF16-GGUF
Base model
mistralai/Mistral-7B-v0.3
Finetuned
mistralai/Mistral-7B-Instruct-v0.3