Update README.md
Browse files
README.md
CHANGED
|
@@ -27,12 +27,17 @@ PROUDLY PRESENTS
|
|
| 27 |
|
| 28 |
# Phainesthesia-8x7B-iMat-GGUF
|
| 29 |
|
|
|
|
|
|
|
|
|
|
| 30 |
Quantized from fp16 with love.
|
| 31 |
* Quantizations made possible using mixtral-8x7b-instruct-v0.1.imatrix file from [this](https://huggingface.co/datasets/ikawrakow/imatrix-from-wiki-train) repo (special thanks to [ikawrakow](https://huggingface.co/ikawrakow) again)
|
| 32 |
|
| 33 |
For a brief rundown of iMatrix quant performance please see this [PR](https://github.com/ggerganov/llama.cpp/pull/5747)
|
| 34 |
|
| 35 |
-
<i>All quants are verified working prior to uploading to repo for your safety and convenience.
|
|
|
|
|
|
|
| 36 |
|
| 37 |
Please note importance matrix quantizations are a work in progress, IQ3 and above is recommended for best results.
|
| 38 |
|
|
|
|
| 27 |
|
| 28 |
# Phainesthesia-8x7B-iMat-GGUF
|
| 29 |
|
| 30 |
+
|
| 31 |
+
<b>Update 4/28 This specific model was retested once more after llama.cpp [PR 6884](https://github.com/ggerganov/llama.cpp/issues/6841) was merged. It has been confirmed to pass the recently added --check-tensors test.</b>
|
| 32 |
+
|
| 33 |
Quantized from fp16 with love.
|
| 34 |
* Quantizations made possible using mixtral-8x7b-instruct-v0.1.imatrix file from [this](https://huggingface.co/datasets/ikawrakow/imatrix-from-wiki-train) repo (special thanks to [ikawrakow](https://huggingface.co/ikawrakow) again)
|
| 35 |
|
| 36 |
For a brief rundown of iMatrix quant performance please see this [PR](https://github.com/ggerganov/llama.cpp/pull/5747)
|
| 37 |
|
| 38 |
+
<i>All quants are verified working prior to uploading to repo for your safety and convenience. </i>
|
| 39 |
+
|
| 40 |
+
|
| 41 |
|
| 42 |
Please note importance matrix quantizations are a work in progress, IQ3 and above is recommended for best results.
|
| 43 |
|