qwp4w3hyb commited on
Commit
6f9815b
1 Parent(s): 0767b5b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -23,7 +23,7 @@ base_model: google/gemma-2-27b-it
23
  - Wide coverage of different gguf quant types from Q\_8\_0 down to IQ1\_S
24
  - experimental custom quant types
25
  - `_L` with `--output-tensor-type f16 --token-embedding-type f16` (same as bartowski's)
26
- - Quantized with [llama.cpp](https://github.com/ggerganov/llama.cpp) commit [5fac350b9cc49d0446fc291b9c4ad53666c77591](https://github.com/ggerganov/llama.cpp/commit/5fac350b9cc49d0446fc291b9c4ad53666c77591://github.com/ggerganov/llama.cpp/releases/tag/5fac350b9cc49d0446fc291b9c4ad53666c77591) (master from 2024-07-02)
27
  - Imatrix generated with [this](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) multi-purpose dataset by [bartowski](https://huggingface.co/bartowski).
28
  ```
29
  ./imatrix -m $model_name-bf16.gguf -f calibration_datav3.txt -o $model_name.imatrix
 
23
  - Wide coverage of different gguf quant types from Q\_8\_0 down to IQ1\_S
24
  - experimental custom quant types
25
  - `_L` with `--output-tensor-type f16 --token-embedding-type f16` (same as bartowski's)
26
+ - Quantized with [llama.cpp](https://github.com/ggerganov/llama.cpp) commit [5fac350b9cc49d0446fc291b9c4ad53666c77591](https://github.com/ggerganov/llama.cpp/commit/5fac350b9cc49d0446fc291b9c4ad53666c77591) (master from 2024-07-02)
27
  - Imatrix generated with [this](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) multi-purpose dataset by [bartowski](https://huggingface.co/bartowski).
28
  ```
29
  ./imatrix -m $model_name-bf16.gguf -f calibration_datav3.txt -o $model_name.imatrix