- imx_plus quants are experimental full bf16 precision on the entirety of layer 0 as well as the output.
- https://arxiv.org/html/2408.15301v1
- I made a mistake on my 'plus' quanting, and overweighted every tenth layer instead of just layer 0. I will change this note once I have rectified the issue.
- imx quants are normally formulated with a model specific custom imatrix dataset.
- Downloads last month
- 21
Hardware compatibility
Log In
to view the estimation
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for schonsense/70B_llama312_rp_GGUF
Base model
meta-llama/Llama-3.1-70B
Finetuned
schonsense/70B_llama312_RP_ft