Upload README.md with huggingface_hub

README.md

@@ -1,12 +1,11 @@
 ---
-base_model: fblgit/TheBeagle-v2beta-32B-MGS
-pipeline_tag: text-generation
 quantized_by: bartowski
+pipeline_tag: text-generation
 ---
 
 ## Llamacpp imatrix Quantizations of TheBeagle-v2beta-32B-MGS
 
-Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3930">b3930</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/b3972">b3972</a> for quantization.
 
 Original model: https://huggingface.co/fblgit/TheBeagle-v2beta-32B-MGS
 
@@ -24,6 +23,10 @@ Run them in [LM Studio](https://lmstudio.ai/)
 <|im_start|>assistant
 ```
 
+## What's new:
+
+Update tokenizer
+
 ## Download a file (not the whole branch) from below:
 
 | Filename | Quant type | File Size | Split | Description |
@@ -39,6 +42,9 @@ Run them in [LM Studio](https://lmstudio.ai/)
 | [TheBeagle-v2beta-32B-MGS-Q4_K_M.gguf](https://huggingface.co/bartowski/TheBeagle-v2beta-32B-MGS-GGUF/blob/main/TheBeagle-v2beta-32B-MGS-Q4_K_M.gguf) | Q4_K_M | 19.85GB | false | Good quality, default size for must use cases, *recommended*. |
 | [TheBeagle-v2beta-32B-MGS-Q4_K_S.gguf](https://huggingface.co/bartowski/TheBeagle-v2beta-32B-MGS-GGUF/blob/main/TheBeagle-v2beta-32B-MGS-Q4_K_S.gguf) | Q4_K_S | 18.78GB | false | Slightly lower quality with more space savings, *recommended*. |
 | [TheBeagle-v2beta-32B-MGS-Q4_0.gguf](https://huggingface.co/bartowski/TheBeagle-v2beta-32B-MGS-GGUF/blob/main/TheBeagle-v2beta-32B-MGS-Q4_0.gguf) | Q4_0 | 18.71GB | false | Legacy format, generally not worth using over similarly sized formats |
+| [TheBeagle-v2beta-32B-MGS-Q4_0_8_8.gguf](https://huggingface.co/bartowski/TheBeagle-v2beta-32B-MGS-GGUF/blob/main/TheBeagle-v2beta-32B-MGS-Q4_0_8_8.gguf) | Q4_0_8_8 | 18.64GB | false | Optimized for ARM inference. Requires 'sve' support (see link below). *Don't use on Mac or Windows*. |
+| [TheBeagle-v2beta-32B-MGS-Q4_0_4_8.gguf](https://huggingface.co/bartowski/TheBeagle-v2beta-32B-MGS-GGUF/blob/main/TheBeagle-v2beta-32B-MGS-Q4_0_4_8.gguf) | Q4_0_4_8 | 18.64GB | false | Optimized for ARM inference. Requires 'i8mm' support (see link below). *Don't use on Mac or Windows*. |
+| [TheBeagle-v2beta-32B-MGS-Q4_0_4_4.gguf](https://huggingface.co/bartowski/TheBeagle-v2beta-32B-MGS-GGUF/blob/main/TheBeagle-v2beta-32B-MGS-Q4_0_4_4.gguf) | Q4_0_4_4 | 18.64GB | 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*. |
 | [TheBeagle-v2beta-32B-MGS-Q3_K_XL.gguf](https://huggingface.co/bartowski/TheBeagle-v2beta-32B-MGS-GGUF/blob/main/TheBeagle-v2beta-32B-MGS-Q3_K_XL.gguf) | Q3_K_XL | 17.93GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
 | [TheBeagle-v2beta-32B-MGS-IQ4_XS.gguf](https://huggingface.co/bartowski/TheBeagle-v2beta-32B-MGS-GGUF/blob/main/TheBeagle-v2beta-32B-MGS-IQ4_XS.gguf) | IQ4_XS | 17.69GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
 | [TheBeagle-v2beta-32B-MGS-Q3_K_L.gguf](https://huggingface.co/bartowski/TheBeagle-v2beta-32B-MGS-GGUF/blob/main/TheBeagle-v2beta-32B-MGS-Q3_K_L.gguf) | Q3_K_L | 17.25GB | false | Lower quality but usable, good for low RAM availability. |