auto-patch README.md

README.md

@@ -1,5 +1,69 @@
+---
+exported_from: mlx-community/Llama-3-8B-Instruct-262k-unquantized
+language:
+- en
+library_name: transformers
+quantized_by: mradermacher
+tags:
+- meta
+- llama-3
+- mlx
+---
+## About
+
 <!-- ### quantize_version: 1 -->
 <!-- ### output_tensor_quantised: 1 -->
 <!-- ### convert_type:  -->
 <!-- ### vocab_type:  -->
 weighted/imatrix quants of https://huggingface.co/mlx-community/Llama-3-8B-Instruct-262k-unquantized
+
+
+<!-- provided-files -->
+static quants are available at https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-GGUF
+## Usage
+
+If you are unsure how to use GGUF files, refer to one of [TheBloke's
+READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
+more details, including on how to concatenate multi-part files.
+
+## Provided Quants
+
+(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
+
+| Link | Type | Size/GB | Notes |
+|:-----|:-----|--------:|:------|
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 |  |
+| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Instruct-262k-unquantized-i1-GGUF/resolve/main/Llama-3-8B-Instruct-262k-unquantized.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K |
+
+
+Here is a handy graph by ikawrakow comparing some lower-quality quant
+types (lower is better):
+
+![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)
+
+And here are Artefact2's thoughts on the matter:
+https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
+
+## Thanks
+
+I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
+me use its servers and providing upgrades to my workstation to enable
+this work in my free time.
+
+<!-- end -->