Update README.md
Browse files
README.md
CHANGED
@@ -22,9 +22,9 @@ tags:
|
|
22 |
|
23 |
- Not supported in llama.cpp master; Requires the latest version of the phi3 128k [branch](https://github.com/ggerganov/llama.cpp/pull/7225)
|
24 |
- quants & imatrix are still in the oven will follow soon TM
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
- Quantized with [llama.cpp](https://github.com/ggerganov/llama.cpp) WIP [branch](https://github.com/ggerganov/llama.cpp/pull/7225)
|
29 |
- Imatrix generated with [this](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) multi-purpose dataset.
|
30 |
```
|
|
|
22 |
|
23 |
- Not supported in llama.cpp master; Requires the latest version of the phi3 128k [branch](https://github.com/ggerganov/llama.cpp/pull/7225)
|
24 |
- quants & imatrix are still in the oven will follow soon TM
|
25 |
+
<!-- - quants done with an importance matrix for improved quantization loss -->
|
26 |
+
<!-- - gguf & imatrix generated from bf16 for "optimal" accuracy loss (some say this is snake oil, but it can't hurt) -->
|
27 |
+
<!-- - Wide coverage of different gguf quant types from Q\_8\_0 down to IQ1\_S -->
|
28 |
- Quantized with [llama.cpp](https://github.com/ggerganov/llama.cpp) WIP [branch](https://github.com/ggerganov/llama.cpp/pull/7225)
|
29 |
- Imatrix generated with [this](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) multi-purpose dataset.
|
30 |
```
|