Update README.md

README.md

@@ -13,108 +13,55 @@ tags:
 - multi-image
 - video
 - custom_code
-quantized_by: bartowski
+lm_studio:
+  param_count: 8b
+  use_case: image
+  release_date: 05-08-2024
+  model_creator: OpenBMB
+  prompt_template: ChatML
+  system_prompt: You are a helpful assistant.
+  base_model: MiniCPM-V
+  original_repo: openbmb/MiniCPM-V-2_6
 ---
+## 💫 Community Model> MiniCPM-V 2.6 by OpenBMB
 
-# This is my first vision model, it *may be broken*, I will attempt to test but making public so others can too
+*👾 [LM Studio](https://lmstudio.ai) Community models highlights program. Highlighting new & noteworthy models by the community. Join the conversation on [Discord](https://discord.gg/aPQfnNkxGC)*.
 
-## Llamacpp Static Quantizations of MiniCPM-V-2_6
+**Model creator:** [OpenBMB](https://huggingface.co/OpenBMB)<br>
+**Original model**: [MiniCPM-V-2_6](https://huggingface.co/openbmb/MiniCPM-V-2_6)<br>
+**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b3600](https://github.com/ggerganov/llama.cpp/releases/tag/b3600)<br>
 
-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.
+* Requires LM Studio version 0.3.0 and up, please check for updates
 
-Original model: https://huggingface.co/openbmb/MiniCPM-V-2_6
+## Model Summary:
+MiniCPM-V 2.6 is the latest and most capable model in the MiniCPM-V series. The model is built on SigLip-400M and Qwen2-7B with a total of 8B parameters.<br>
+It exhibits a significant performance improvement over MiniCPM-Llama3-V 2.5, and introduces new features for multi-image and video understanding.
 
-## Prompt format
+## Prompt Template:
+
+Choose the `ChatML` preset in your LM Studio.
+Under the hood, the model will see a prompt that's formatted like so:
 
 ```
 <|im_start|>system
-{system_prompt}<|im_end|>
+You are a helpful assistant.<|im_end|>
 <|im_start|>user
 {prompt}<|im_end|>
 <|im_start|>assistant
-```
-
-## Download a file (not the whole branch) from below:
-
-| Filename | Quant type | File Size | Split | Description |
-| -------- | ---------- | --------- | ----- | ----------- |
-| [MiniCPM-V-2_6-f16.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-f16.gguf) | f16 | 15.23GB | false | Full F16 weights. |
-| [MiniCPM-V-2_6-Q8_0.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-Q8_0.gguf) | Q8_0 | 8.10GB | false | Extremely high quality, generally unneeded but max available quant. |
-| [MiniCPM-V-2_6-Q6_K_L.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-Q6_K_L.gguf) | Q6_K_L | 6.52GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |
-| [MiniCPM-V-2_6-Q6_K.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-Q6_K.gguf) | Q6_K | 6.25GB | false | Very high quality, near perfect, *recommended*. |
-| [MiniCPM-V-2_6-Q5_K_L.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-Q5_K_L.gguf) | Q5_K_L | 5.78GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. |
-| [MiniCPM-V-2_6-Q5_K_M.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-Q5_K_M.gguf) | Q5_K_M | 5.44GB | false | High quality, *recommended*. |
-| [MiniCPM-V-2_6-Q5_K_S.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-Q5_K_S.gguf) | Q5_K_S | 5.31GB | false | High quality, *recommended*. |
-| [MiniCPM-V-2_6-Q4_K_L.gguf](https://huggingface.co/bartowski/MiniCPM-V-2_6-GGUF/blob/main/MiniCPM-V-2_6-Q4_K_L.gguf) | Q4_K_L | 5.08GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. |
-| [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-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-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. |
-
-## Embed/output weights
-
-Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.
-
-Some say that this improves the quality, others don't notice any difference. If you use these models PLEASE COMMENT with your findings. I would like feedback that these are actually used and useful so I don't keep uploading quants no one is using.
-
-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:
-
-```
-pip install -U "huggingface_hub[cli]"
-```
-
-Then, you can target the specific file you want:
-
-```
-huggingface-cli download bartowski/MiniCPM-V-2_6-GGUF --include "MiniCPM-V-2_6-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/MiniCPM-V-2_6-GGUF --include "MiniCPM-V-2_6-Q8_0/*" --local-dir ./
-```
-
-You can either specify a new local-dir (MiniCPM-V-2_6-Q8_0) or download them all in place (./)
-
-## 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)
-
-The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.
-
-If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.
-
-If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.
-
-Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
-
-If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.
 
-If you want to get more into the weeds, you can check out this extremely useful feature chart:
+## Technical Details
+MiniCPM-V 2.6 manages to beat widely used proprietary models like GPT-4o mini, GPT-4V, Gemini 1.5 Pro, and Claude 3.5 Sonnet for single image understanding.
 
-[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
+MiniCPM-V 2.6 is capable of performing conversation and reasoning over multiple images, and is also able to accept video inputs 
 
-But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.
+This model can process images with any aspect ratio and up to 1.8 million pixels (e.g., 1344x1344) and perform state of the art OCR on them. 
 
-These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.
+## Special thanks
 
-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.
+🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.
 
-Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
+## Disclaimers
 
+LM Studio is not the creator, originator, or owner of any Model featured in the Community Model Program. Each Community Model is created and provided by third parties. LM Studio does not endorse, support, represent or guarantee the completeness, truthfulness, accuracy, or reliability of any Community Model.  You understand that Community Models can produce content that might be offensive, harmful, inaccurate or otherwise inappropriate, or deceptive. Each Community Model is the sole responsibility of the person or entity who originated such Model. LM Studio may not monitor or control the Community Models and cannot, and does not, take responsibility for any such Model. LM Studio disclaims all warranties or guarantees about the accuracy, reliability or benefits of the Community Models.  LM Studio further disclaims any warranty that the Community Model will meet your requirements, be secure, uninterrupted or available at any time or location, or error-free, viruses-free, or that any errors will be corrected, or otherwise. You will be solely responsible for any damage resulting from your use of or access to the Community Models, your downloading of any Community Model, or use of any other Community Model provided by or through LM Studio.