Upload README.md with huggingface_hub

README.md

@@ -1,25 +1,11 @@
 ---
-base_model: mistralai/Mistral-Nemo-Instruct-2407
-language:
-- en
-- fr
-- de
-- es
-- it
-- pt
-- ru
-- zh
-- ja
-license: apache-2.0
-pipeline_tag: text-generation
 quantized_by: bartowski
-extra_gated_description: If you want to learn more about how we process your personal
-  data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
+pipeline_tag: text-generation
 ---
 
 ## Llamacpp imatrix Quantizations of Mistral-Nemo-Instruct-2407
 
-Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3634">b3634</a> for quantization.
+Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b4014">b4014</a> for quantization.
 
 Original model: https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407
 
@@ -33,11 +19,14 @@ Run them in [LM Studio](https://lmstudio.ai/)
 <s>[INST]{prompt}[/INST]
 ```
 
+## What's new:
+
+Update chat template
+
 ## Download a file (not the whole branch) from below:
 
 | Filename | Quant type | File Size | Split | Description |
 | -------- | ---------- | --------- | ----- | ----------- |
-| [Mistral-Nemo-Instruct-2407-f32.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-f32.gguf) | f32 | 49.00GB | false | Full F32 weights. |
 | [Mistral-Nemo-Instruct-2407-f16.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-f16.gguf) | f16 | 24.50GB | false | Full F16 weights. |
 | [Mistral-Nemo-Instruct-2407-Q8_0.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q8_0.gguf) | Q8_0 | 13.02GB | false | Extremely high quality, generally unneeded but max available quant. |
 | [Mistral-Nemo-Instruct-2407-Q6_K_L.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q6_K_L.gguf) | Q6_K_L | 10.38GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
@@ -50,9 +39,9 @@ Run them in [LM Studio](https://lmstudio.ai/)
 | [Mistral-Nemo-Instruct-2407-Q3_K_XL.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q3_K_XL.gguf) | Q3_K_XL | 7.15GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
 | [Mistral-Nemo-Instruct-2407-Q4_K_S.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_K_S.gguf) | Q4_K_S | 7.12GB | false | Slightly lower quality with more space savings, *recommended*. |
 | [Mistral-Nemo-Instruct-2407-Q4_0.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_0.gguf) | Q4_0 | 7.09GB | false | Legacy format, generally not worth using over similarly sized formats |
-| [Mistral-Nemo-Instruct-2407-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_0_8_8.gguf) | Q4_0_8_8 | 7.07GB | false | Optimized for ARM and CPU inference, much faster than Q4_0 at similar quality. |
-| [Mistral-Nemo-Instruct-2407-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_0_4_8.gguf) | Q4_0_4_8 | 7.07GB | false | Optimized for ARM and CPU inference, much faster than Q4_0 at similar quality. |
-| [Mistral-Nemo-Instruct-2407-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_0_4_4.gguf) | Q4_0_4_4 | 7.07GB | false | Optimized for ARM and CPU inference, much faster than Q4_0 at similar quality. |
+| [Mistral-Nemo-Instruct-2407-Q4_0_8_8.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_0_8_8.gguf) | Q4_0_8_8 | 7.07GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). *Don't use on Mac or Windows*. |
+| [Mistral-Nemo-Instruct-2407-Q4_0_4_8.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_0_4_8.gguf) | Q4_0_4_8 | 7.07GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). *Don't use on Mac or Windows*. |
+| [Mistral-Nemo-Instruct-2407-Q4_0_4_4.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q4_0_4_4.gguf) | Q4_0_4_4 | 7.07GB | false | Optimized for ARM inference. Should work well on all ARM chips, pick this if you're unsure. *Don't use on Mac or Windows*. |
 | [Mistral-Nemo-Instruct-2407-IQ4_XS.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-IQ4_XS.gguf) | IQ4_XS | 6.74GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
 | [Mistral-Nemo-Instruct-2407-Q3_K_L.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q3_K_L.gguf) | Q3_K_L | 6.56GB | false | Lower quality but usable, good for low RAM availability. |
 | [Mistral-Nemo-Instruct-2407-Q3_K_M.gguf](https://huggingface.co/bartowski/Mistral-Nemo-Instruct-2407-GGUF/blob/main/Mistral-Nemo-Instruct-2407-Q3_K_M.gguf) | Q3_K_M | 6.08GB | false | Low quality. |
@@ -71,12 +60,6 @@ Some say that this improves the quality, others don't notice any difference. If
 
 Thanks!
 
-## Credits
-
-Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset
-
-Thank you ZeroWw for the inspiration to experiment with embed/output
-
 ## Downloading using huggingface-cli
 
 First, make sure you have hugginface-cli installed:
@@ -99,6 +82,14 @@ huggingface-cli download bartowski/Mistral-Nemo-Instruct-2407-GGUF --include "Mi
 
 You can either specify a new local-dir (Mistral-Nemo-Instruct-2407-Q8_0) or download them all in place (./)
 
+## Q4_0_X_X
+
+These are *NOT* for Metal (Apple) offloading, only ARM chips.
+
+If you're using an ARM chip, the Q4_0_X_X quants will have a substantial speedup. Check out Q4_0_4_4 speed comparisons [on the original pull request](https://github.com/ggerganov/llama.cpp/pull/5780#pullrequestreview-21657544660)
+
+To check which one would work best for your ARM chip, you can check [AArch64 SoC features](https://gpages.juszkiewicz.com.pl/arm-socs-table/arm-socs.html) (thanks EloyOn!).
+
 ## Which file should I choose?
 
 A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9)
@@ -123,5 +114,10 @@ These I-quants can also be used on CPU and Apple Metal, but will be slower than
 
 The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm.
 
-Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
+## Credits
 
+Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset
+
+Thank you ZeroWw for the inspiration to experiment with embed/output
+
+Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski