Upload README.md with huggingface_hub

README.md

@@ -1,29 +1,18 @@
 ---
-base_model: openbmb/MiniCPM-V-2_6
-datasets:
-- openbmb/RLAIF-V-Dataset
-language:
-- multilingual
-library_name: transformers
-pipeline_tag: image-text-to-text
-tags:
-- minicpm-v
-- vision
-- ocr
-- multi-image
-- video
-- custom_code
 quantized_by: bartowski
+pipeline_tag: text-generation
 ---
 
-# This is my first vision model, it *may be broken*, I will attempt to test but making public so others can too
+## Llamacpp imatrix Quantizations of MiniCPM-V-2_6
 
-## Llamacpp Static Quantizations of MiniCPM-V-2_6
-
-Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3600">b3600</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/b3615">b3615</a> for quantization.
 
 Original model: https://huggingface.co/openbmb/MiniCPM-V-2_6
 
+All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
+
+Run them in [LM Studio](https://lmstudio.ai/)
+
 ## Prompt format
 
 ```
@@ -34,6 +23,10 @@ Original model: https://huggingface.co/openbmb/MiniCPM-V-2_6
 <|im_start|>assistant
 ```
 
+## What's new:
+
+Applying imatrix, should improve the text portion of the model
+
 ## Download a file (not the whole branch) from below:
 
 | Filename | Quant type | File Size | Split | Description |
@@ -49,12 +42,15 @@ Original model: https://huggingface.co/openbmb/MiniCPM-V-2_6
 | [MiniCPM-V-2_6-Q4_K_M.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-Q4_K_M.gguf) | Q4_K_M | 4.68GB | false | Good quality, default size for must use cases, *recommended*. |
 | [MiniCPM-V-2_6-Q3_K_XL.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-Q3_K_XL.gguf) | Q3_K_XL | 4.56GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. |
 | [MiniCPM-V-2_6-Q4_K_S.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-Q4_K_S.gguf) | Q4_K_S | 4.46GB | false | Slightly lower quality with more space savings, *recommended*. |
-| [MiniCPM-V-2_6-IQ4_XS.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-IQ4_XS.gguf) | IQ4_XS | 4.25GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
+| [MiniCPM-V-2_6-IQ4_XS.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-IQ4_XS.gguf) | IQ4_XS | 4.22GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
 | [MiniCPM-V-2_6-Q3_K_L.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-Q3_K_L.gguf) | Q3_K_L | 4.09GB | false | Lower quality but usable, good for low RAM availability. |
 | [MiniCPM-V-2_6-Q3_K_M.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-Q3_K_M.gguf) | Q3_K_M | 3.81GB | false | Low quality. |
 | [MiniCPM-V-2_6-IQ3_M.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-IQ3_M.gguf) | IQ3_M | 3.57GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
 | [MiniCPM-V-2_6-Q2_K_L.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-Q2_K_L.gguf) | Q2_K_L | 3.55GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. |
+| [MiniCPM-V-2_6-Q3_K_S.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-Q3_K_S.gguf) | Q3_K_S | 3.49GB | false | Low quality, not recommended. |
+| [MiniCPM-V-2_6-IQ3_XS.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-IQ3_XS.gguf) | IQ3_XS | 3.34GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
 | [MiniCPM-V-2_6-Q2_K.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-Q2_K.gguf) | Q2_K | 3.01GB | false | Very low quality but surprisingly usable. |
+| [MiniCPM-V-2_6-IQ2_M.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-IQ2_M.gguf) | IQ2_M | 2.78GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. |
 
 ## Embed/output weights