Update README.md

README.md

@@ -4,96 +4,61 @@ license_name: deepseek-license
 license_link: LICENSE
 quantized_by: bartowski
 pipeline_tag: text-generation
+lm_studio:
+ param_count: 16b
+ use_case: coding
+ release_date: 17-06-2024
+ model_creator: DeepSeek
+ prompt_template: DeepSeek Chat 
+ system_prompt: none
+ base_model: DeepSeek
+ original_repo: deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
+base_model: deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
 ---
+## 💫 Community Model> DeepSeek-Coder-V2-Lite-Instruct by DeepSeek
 
-## Llamacpp imatrix Quantizations of DeepSeek-Coder-V2-Lite-Instruct
+*👾 [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)*.
 
-Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b3166">b3166</a> for quantization.
+**Model creator:** [DeepSeek](https://huggingface.co/deepseek-ai)<br>
+**Original model**: [DeepSeek-Coder-V2-Lite-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct)<br>
+**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b3166](https://github.com/ggerganov/llama.cpp/releases/tag/b3166)<br>
 
-Original model: https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct
+## Model Summary:
 
-All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)
+This is a brand new Mixture of Export (MoE) model from DeepSeek, specializing in coding instructions.<br>
+This model performs well across a series of coding benchmarks and should be used for both instruction following and code completion.
 
-## Prompt format
+## Prompt template:
 
-```
-<｜begin▁of▁sentence｜>{system_prompt}
-
-User: {prompt}
-
-Assistant: <｜end▁of▁sentence｜>Assistant:
-```
-
-## Download a file (not the whole branch) from below:
-
-| Filename | Quant type | File Size | Description |
-| -------- | ---------- | --------- | ----------- |
-| [DeepSeek-Coder-V2-Lite-Instruct-Q8_1.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q8_1.gguf) | Q8_1 | 17.09GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Extremely high quality, generally unneeded but max available quant. |
-| [DeepSeek-Coder-V2-Lite-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q8_0.gguf) | Q8_0 | 16.70GB | Extremely high quality, generally unneeded but max available quant. |
-| [DeepSeek-Coder-V2-Lite-Instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF//main/DeepSeek-Coder-V2-Lite-Instruct-Q6_K_L.gguf) | Q6_K_L | 14.56GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Very high quality, near perfect, *recommended*. |
-| [DeepSeek-Coder-V2-Lite-Instruct-Q6_K.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q6_K.gguf) | Q6_K | 14.06GB | Very high quality, near perfect, *recommended*. |
-| [DeepSeek-Coder-V2-Lite-Instruct-Q5_K_L.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q5_K_L.gguf) | Q5_K_L | 12.37GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. High quality, *recommended*. |
-| [DeepSeek-Coder-V2-Lite-Instruct-Q5_K_M.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q5_K_M.gguf) | Q5_K_M | 11.85GB | High quality, *recommended*. |
-| [DeepSeek-Coder-V2-Lite-Instruct-Q5_K_S.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q5_K_S.gguf) | Q5_K_S | 11.14GB | High quality, *recommended*. |
-| [DeepSeek-Coder-V2-Lite-Instruct-Q4_K_L.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q4_K_L.gguf) | Q4_K_L | 10.91GB | *Experimental*, uses f16 for embed and output weights. Please provide any feedback of differences. Good quality, uses about 4.83 bits per weight, *recommended*. |
-| [DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf) | Q4_K_M | 10.36GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
-| [DeepSeek-Coder-V2-Lite-Instruct-Q4_K_S.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q4_K_S.gguf) | Q4_K_S | 9.53GB | Slightly lower quality with more space savings, *recommended*. |
-| [DeepSeek-Coder-V2-Lite-Instruct-IQ4_XS.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-IQ4_XS.gguf) | IQ4_XS | 8.57GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
-| [DeepSeek-Coder-V2-Lite-Instruct-Q3_K_L.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q3_K_L.gguf) | Q3_K_L | 8.45GB | Lower quality but usable, good for low RAM availability. |
-| [DeepSeek-Coder-V2-Lite-Instruct-Q3_K_M.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q3_K_M.gguf) | Q3_K_M | 8.12GB | Even lower quality. |
-| [DeepSeek-Coder-V2-Lite-Instruct-IQ3_M.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-IQ3_M.gguf) | IQ3_M | 7.55GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
-| [DeepSeek-Coder-V2-Lite-Instruct-Q3_K_S.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q3_K_S.gguf) | Q3_K_S | 7.48GB | Low quality, not recommended. |
-| [DeepSeek-Coder-V2-Lite-Instruct-IQ3_XS.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-IQ3_XS.gguf) | IQ3_XS | 7.12GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
-| [DeepSeek-Coder-V2-Lite-Instruct-IQ3_XXS.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-IQ3_XXS.gguf) | IQ3_XXS | 6.96GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
-| [DeepSeek-Coder-V2-Lite-Instruct-Q2_K.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-Q2_K.gguf) | Q2_K | 6.43GB | Very low quality but surprisingly usable. |
-| [DeepSeek-Coder-V2-Lite-Instruct-IQ2_M.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-IQ2_M.gguf) | IQ2_M | 6.32GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
-| [DeepSeek-Coder-V2-Lite-Instruct-IQ2_S.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-IQ2_S.gguf) | IQ2_S | 6.00GB | Very low quality, uses SOTA techniques to be usable. |
-| [DeepSeek-Coder-V2-Lite-Instruct-IQ2_XS.gguf](https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF/blob/main/DeepSeek-Coder-V2-Lite-Instruct-IQ2_XS.gguf) | IQ2_XS | 5.96GB | Very low quality, uses SOTA techniques to be usable. |
-
-## Downloading using huggingface-cli
-
-First, make sure you have hugginface-cli installed:
-
-```
-pip install -U "huggingface_hub[cli]"
-```
+Choose the `LM Studio Blank Preset` preset in your LM Studio.
 
-Then, you can target the specific file you want:
+Set your User Message Prefix to `User: `
 
-```
-huggingface-cli download bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF --include "DeepSeek-Coder-V2-Lite-Instruct-Q4_K_M.gguf" --local-dir ./
-```
+Set your User Message Suffix to `\n\nAssistant: `
 
-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:
+This will format the prompt as follows:
 
 ```
-huggingface-cli download bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF --include "DeepSeek-Coder-V2-Lite-Instruct-Q8_0.gguf/*" --local-dir DeepSeek-Coder-V2-Lite-Instruct-Q8_0
-```
-
-You can either specify a new local-dir (DeepSeek-Coder-V2-Lite-Instruct-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)
+User: {user_message}
 
-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.
+Assistant: {assistant_message}
 
-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.
+## Technical Details
 
-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.
+This model is an MoE architecture, using 16B total weights with only 2.4B activated to achieve excellent inference speed.
 
-Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.
+DeepSeek-Coder-V2 is based on the DeepSeek-V2 model, further trained on 6 trillion high quality coding tokens to enhance coding and mathematical reasoning. 
 
-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.
+It supports an incredible 128k context length.
 
-If you want to get more into the weeds, you can check out this extremely useful feature chart:
+For more details, read their paper here: https://github.com/deepseek-ai/DeepSeek-Coder-V2/blob/main/paper.pdf
 
-[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
+## Special thanks
 
-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.
+🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) 
 
-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 to [Kalomaze](https://github.com/kalomaze) and [Dampf](https://github.com/Dampfinchen) for their work on the dataset (linked [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8)) that was used for calculating the imatrix for all sizes.
 
-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.
+## Disclaimers
 
-Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
+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.