|
--- |
|
tags: |
|
- gguf |
|
- llama3 |
|
- iMat |
|
--- |
|
<img src="https://i.imgur.com/P68dXux.png" width="400"/> |
|
|
|
# llama3-42b-v0-iMat-GGUF |
|
|
|
|
|
Quantized from fp32 with love. All credits to [Charles Goddard](https://huggingface.co/chargoddard) for the original model. |
|
* Weighted quantizations were calculated using groups_merged.txt with 105 chunks (recommended amount for this file) and n_ctx=512. Special thanks to jukofyork for sharing [this process](https://huggingface.co/jukofyork/WizardLM-2-8x22B-imatrix) |
|
|
|
For more information on the pruning technique utilized in this model: https://arxiv.org/abs/2403.17887 |
|
|
|
Brief rundown of [iMatrix quant performance](https://github.com/ggerganov/llama.cpp/pull/5747) |
|
|
|
<i>All quants are verified working prior to uploading to repo for your safety and convenience. </i> |
|
|
|
|
|
|
|
<b>Tip:</b> Pick a size that can fit in your GPU while still allowing some room for context for best speed. You may need to pad this further depending on if you are running image gen or TTS as well. |
|
|
|
FP16 model card can be found [here](https://huggingface.co/chargoddard/llama3-42b-v0) |
