qwp4w3hyb
/

Meta-Llama-3.1-70B-Instruct-iMat-GGUF

Text Generation

Inference Endpoints

Model card Files Files and versions Community

qwp4w3hyb commited on Jul 25

Commit

084af02

•

1 Parent(s): 3c0fecc

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -32,7 +32,7 @@ base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
 - Wide coverage of different gguf quant types from Q\_8\_0 down to IQ1\_S
   - still WIP
   - experimental custom quant types
-    - `_L` with `--output-tensor-type f16 --token-embedding-type f16`, which supposedly have better accuracy.
 - Imatrix generated with [this](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) multi-purpose dataset by [bartowski](https://huggingface.co/bartowski).
   ```
   ./imatrix -m $model_name-bf16.gguf -f calibration_datav3.txt -o $model_name.imatrix

 - Wide coverage of different gguf quant types from Q\_8\_0 down to IQ1\_S
   - still WIP
   - experimental custom quant types
+    - `_L` with `--output-tensor-type f16 --token-embedding-type f16`, which supposedly leads to better accuracy.
 - Imatrix generated with [this](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) multi-purpose dataset by [bartowski](https://huggingface.co/bartowski).
   ```
   ./imatrix -m $model_name-bf16.gguf -f calibration_datav3.txt -o $model_name.imatrix