Rename files to match mlabonne

README.md

@@ -1,20 +1,20 @@
 ---
-base_model: mlabonne/Llama-3.1-70B-Instruct-abliterated
+base_model: mlabonne/Llama-3.1-70B-Instruct-lorablated
 library_name: transformers
 license: llama3.1
 pipeline_tag: text-generation
 tags:
-- abliterated
+- lorablated
 - uncensored
 - mergekit
 quantized_by: bartowski
 ---
 
-## Llamacpp imatrix Quantizations of Llama-3.1-70B-Instruct-abliterated
+## Llamacpp imatrix Quantizations of Llama-3.1-70B-Instruct-lorablated
 
 Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3496">b3496</a> for quantization.
 
-Original model: https://huggingface.co/mlabonne/Llama-3.1-70B-Instruct-abliterated
+Original model: https://huggingface.co/mlabonne/Llama-3.1-70B-Instruct-lorablated
 
 All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
 
@@ -35,6 +35,9 @@ Today Date: 26 Jul 2024
 
 ```
 
+What's new:
+- Just renaming files since mlabonne renamed his
+
 ## Download a file (not the whole branch) from below:
 
 | Filename | Quant type | File Size | Split | Description |
@@ -43,22 +46,22 @@ Today Date: 26 Jul 2024
 
 | Filename | Quant type | File Size | Split | Description |
 | -------- | ---------- | --------- | ----- | ----------- |
-| [Llama-3.1-70B-Instruct-abliterated-Q8_0.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF/tree/main/Llama-3.1-70B-Instruct-abliterated-Q8_0) | Q8_0 | 74.98GB | true | Extremely high quality, generally unneeded but max available quant. |
-| [Llama-3.1-70B-Instruct-abliterated-Q6_K.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF/tree/main/Llama-3.1-70B-Instruct-abliterated-Q6_K) | Q6_K | 57.89GB | true | Very high quality, near perfect, *recommended*. |
-| [Llama-3.1-70B-Instruct-abliterated-Q5_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF/tree/main/Llama-3.1-70B-Instruct-abliterated-Q5_K_M) | Q5_K_M | 49.95GB | true | High quality, *recommended*. |
-| [Llama-3.1-70B-Instruct-abliterated-Q4_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF/blob/main/Llama-3.1-70B-Instruct-abliterated-Q4_K_L.gguf) | Q4_K_L | 43.30GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
-| [Llama-3.1-70B-Instruct-abliterated-Q4_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF/blob/main/Llama-3.1-70B-Instruct-abliterated-Q4_K_M.gguf) | Q4_K_M | 42.52GB | false | Good quality, default size for must use cases, *recommended*. |
-| [Llama-3.1-70B-Instruct-abliterated-Q3_K_XL.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF/blob/main/Llama-3.1-70B-Instruct-abliterated-Q3_K_XL.gguf) | Q3_K_XL | 38.06GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
-| [Llama-3.1-70B-Instruct-abliterated-IQ4_XS.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF/blob/main/Llama-3.1-70B-Instruct-abliterated-IQ4_XS.gguf) | IQ4_XS | 37.90GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
-| [Llama-3.1-70B-Instruct-abliterated-Q3_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF/blob/main/Llama-3.1-70B-Instruct-abliterated-Q3_K_L.gguf) | Q3_K_L | 37.14GB | false | Lower quality but usable, good for low RAM availability. |
-| [Llama-3.1-70B-Instruct-abliterated-Q3_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF/blob/main/Llama-3.1-70B-Instruct-abliterated-Q3_K_M.gguf) | Q3_K_M | 34.27GB | false | Low quality. |
-| [Llama-3.1-70B-Instruct-abliterated-IQ3_M.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF/blob/main/Llama-3.1-70B-Instruct-abliterated-IQ3_M.gguf) | IQ3_M | 31.94GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
-| [Llama-3.1-70B-Instruct-abliterated-IQ3_XXS.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF/blob/main/Llama-3.1-70B-Instruct-abliterated-IQ3_XXS.gguf) | IQ3_XXS | 27.47GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
-| [Llama-3.1-70B-Instruct-abliterated-Q2_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF/blob/main/Llama-3.1-70B-Instruct-abliterated-Q2_K_L.gguf) | Q2_K_L | 27.40GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
-| [Llama-3.1-70B-Instruct-abliterated-Q2_K.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF/blob/main/Llama-3.1-70B-Instruct-abliterated-Q2_K.gguf) | Q2_K | 26.38GB | false | Very low quality but surprisingly usable. |
-| [Llama-3.1-70B-Instruct-abliterated-IQ2_M.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF/blob/main/Llama-3.1-70B-Instruct-abliterated-IQ2_M.gguf) | IQ2_M | 24.12GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
-| [Llama-3.1-70B-Instruct-abliterated-IQ2_XS.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF/blob/main/Llama-3.1-70B-Instruct-abliterated-IQ2_XS.gguf) | IQ2_XS | 21.14GB | false | Low quality, uses SOTA techniques to be usable. |
-| [Llama-3.1-70B-Instruct-abliterated-IQ2_XXS.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF/blob/main/Llama-3.1-70B-Instruct-abliterated-IQ2_XXS.gguf) | IQ2_XXS | 19.10GB | false | Very low quality, uses SOTA techniques to be usable. |
+| [Llama-3.1-70B-Instruct-lorablated-Q8_0.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF/tree/main/Llama-3.1-70B-Instruct-lorablated-Q8_0) | Q8_0 | 74.98GB | true | Extremely high quality, generally unneeded but max available quant. |
+| [Llama-3.1-70B-Instruct-lorablated-Q6_K.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF/tree/main/Llama-3.1-70B-Instruct-lorablated-Q6_K) | Q6_K | 57.89GB | true | Very high quality, near perfect, *recommended*. |
+| [Llama-3.1-70B-Instruct-lorablated-Q5_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF/tree/main/Llama-3.1-70B-Instruct-lorablated-Q5_K_M) | Q5_K_M | 49.95GB | true | High quality, *recommended*. |
+| [Llama-3.1-70B-Instruct-lorablated-Q4_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF/blob/main/Llama-3.1-70B-Instruct-lorablated-Q4_K_L.gguf) | Q4_K_L | 43.30GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
+| [Llama-3.1-70B-Instruct-lorablated-Q4_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF/blob/main/Llama-3.1-70B-Instruct-lorablated-Q4_K_M.gguf) | Q4_K_M | 42.52GB | false | Good quality, default size for must use cases, *recommended*. |
+| [Llama-3.1-70B-Instruct-lorablated-Q3_K_XL.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF/blob/main/Llama-3.1-70B-Instruct-lorablated-Q3_K_XL.gguf) | Q3_K_XL | 38.06GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
+| [Llama-3.1-70B-Instruct-lorablated-IQ4_XS.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF/blob/main/Llama-3.1-70B-Instruct-lorablated-IQ4_XS.gguf) | IQ4_XS | 37.90GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [Llama-3.1-70B-Instruct-lorablated-Q3_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF/blob/main/Llama-3.1-70B-Instruct-lorablated-Q3_K_L.gguf) | Q3_K_L | 37.14GB | false | Lower quality but usable, good for low RAM availability. |
+| [Llama-3.1-70B-Instruct-lorablated-Q3_K_M.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF/blob/main/Llama-3.1-70B-Instruct-lorablated-Q3_K_M.gguf) | Q3_K_M | 34.27GB | false | Low quality. |
+| [Llama-3.1-70B-Instruct-lorablated-IQ3_M.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF/blob/main/Llama-3.1-70B-Instruct-lorablated-IQ3_M.gguf) | IQ3_M | 31.94GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
+| [Llama-3.1-70B-Instruct-lorablated-IQ3_XXS.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF/blob/main/Llama-3.1-70B-Instruct-lorablated-IQ3_XXS.gguf) | IQ3_XXS | 27.47GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. |
+| [Llama-3.1-70B-Instruct-lorablated-Q2_K_L.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF/blob/main/Llama-3.1-70B-Instruct-lorablated-Q2_K_L.gguf) | Q2_K_L | 27.40GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [Llama-3.1-70B-Instruct-lorablated-Q2_K.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF/blob/main/Llama-3.1-70B-Instruct-lorablated-Q2_K.gguf) | Q2_K | 26.38GB | false | Very low quality but surprisingly usable. |
+| [Llama-3.1-70B-Instruct-lorablated-IQ2_M.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF/blob/main/Llama-3.1-70B-Instruct-lorablated-IQ2_M.gguf) | IQ2_M | 24.12GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
+| [Llama-3.1-70B-Instruct-lorablated-IQ2_XS.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF/blob/main/Llama-3.1-70B-Instruct-lorablated-IQ2_XS.gguf) | IQ2_XS | 21.14GB | false | Low quality, uses SOTA techniques to be usable. |
+| [Llama-3.1-70B-Instruct-lorablated-IQ2_XXS.gguf](https://huggingface.co/bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF/blob/main/Llama-3.1-70B-Instruct-lorablated-IQ2_XXS.gguf) | IQ2_XXS | 19.10GB | false | Very low quality, uses SOTA techniques to be usable. |
 
 ## Embed/output weights
 
@@ -85,16 +88,16 @@ pip install -U "huggingface_hub[cli]"
 Then, you can target the specific file you want:
 
 ```
-huggingface-cli download bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF --include "Llama-3.1-70B-Instruct-abliterated-Q4_K_M.gguf" --local-dir ./
+huggingface-cli download bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF --include "Llama-3.1-70B-Instruct-lorablated-Q4_K_M.gguf" --local-dir ./
 ```
 
 If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:
 
 ```
-huggingface-cli download bartowski/Llama-3.1-70B-Instruct-abliterated-GGUF --include "Llama-3.1-70B-Instruct-abliterated-Q8_0/*" --local-dir ./
+huggingface-cli download bartowski/Llama-3.1-70B-Instruct-lorablated-GGUF --include "Llama-3.1-70B-Instruct-lorablated-Q8_0/*" --local-dir ./
 ```
 
-You can either specify a new local-dir (Llama-3.1-70B-Instruct-abliterated-Q8_0) or download them all in place (./)
+You can either specify a new local-dir (Llama-3.1-70B-Instruct-lorablated-Q8_0) or download them all in place (./)
 
 ## Which file should I choose?