Update README.md

README.md

@@ -2,7 +2,6 @@
 license: apache-2.0
 datasets:
 - JetBrains/KExercises
-base_model: deepseek-ai/deepseek-coder-1.3b-base
 results:
 - task:
     type: text-generation
@@ -17,99 +16,46 @@ tags:
 - code
 quantized_by: bartowski
 pipeline_tag: text-generation
+lm_studio:
+  param_count: 1.3b
+  use_case: code completion
+  release_date: 21-05-2024
+  model_creator: JetBrains
+  prompt_template: none
+  system_prompt: none
+  base_model: deepseek-coder
+  original_repo: JetBrains/deepseek-coder-1.3B-kexer
+base_model: JetBrains/deepseek-coder-1.3B-kexer
 ---
+## 💫 Community Model> DeepSeek Coder 1.3B Kexer by JetBrains
 
-## Llamacpp imatrix Quantizations of deepseek-coder-1.3B-kexer
+*👾 [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/b2965">b2965</a> for quantization.
+**Model creator:** [JetBrains](https://huggingface.co/JetBrains)<br>
+**Original model**: [deepseek-coder-1.3B-kexer](https://huggingface.co/JetBrains/deepseek-coder-1.3B-kexer)<br>
+**GGUF quantization:** provided by [bartowski](https://huggingface.co/bartowski) based on `llama.cpp` release [b2965](https://github.com/ggerganov/llama.cpp/releases/tag/b2965)<br>
 
-Original model: https://huggingface.co/JetBrains/deepseek-coder-1.3B-kexer
+## Model Summary:
 
-All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/b6ac44691e994344625687afe3263b3a)
+This model is designed to be used exclusive for code completion and tuned specifically for Kotlin.<br>
+Use this model as a coding assistant and for completion in your IDE to generate strong Kotlin code.
 
-## Prompt format
+## Prompt template:
 
-No chat template specified so default is used. This may be incorrect, check original model card for details.
+There is no prompt template for this model, it should be used for completion.
 
-```
-<｜begin▁of▁sentence｜>[INST] <<SYS>>
-{system_prompt}
-<</SYS>>
+## Technical Details
 
-{prompt} [/INST]  <｜end▁of▁sentence｜>
-```
+This model is based on the Deepseek-coder-1.3b and trained on 15k synthetically generated Kotlin Exercises, dataset found here: https://huggingface.co/datasets/JetBrains/KExercises<br>
+It supports FIM tokens:
+ - `'<｜fim▁begin｜>' + prefix + '<｜fim▁hole｜>' + suffix + '<｜fim▁end｜>'`
 
-## Download a file (not the whole branch) from below:
+## Special thanks
 
-| Filename | Quant type | File Size | Description |
-| -------- | ---------- | --------- | ----------- |
-| [deepseek-coder-1.3B-kexer-Q8_0.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-Q8_0.gguf) | Q8_0 | 1.43GB | Extremely high quality, generally unneeded but max available quant. |
-| [deepseek-coder-1.3B-kexer-Q6_K.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-Q6_K.gguf) | Q6_K | 1.17GB | Very high quality, near perfect, *recommended*. |
-| [deepseek-coder-1.3B-kexer-Q5_K_M.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-Q5_K_M.gguf) | Q5_K_M | 1.00GB | High quality, *recommended*. |
-| [deepseek-coder-1.3B-kexer-Q5_K_S.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-Q5_K_S.gguf) | Q5_K_S | .95GB | High quality, *recommended*. |
-| [deepseek-coder-1.3B-kexer-Q4_K_M.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-Q4_K_M.gguf) | Q4_K_M | .87GB | Good quality, uses about 4.83 bits per weight, *recommended*. |
-| [deepseek-coder-1.3B-kexer-Q4_K_S.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-Q4_K_S.gguf) | Q4_K_S | .81GB | Slightly lower quality with more space savings, *recommended*. |
-| [deepseek-coder-1.3B-kexer-IQ4_NL.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-IQ4_NL.gguf) | IQ4_NL | .77GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. |
-| [deepseek-coder-1.3B-kexer-IQ4_XS.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-IQ4_XS.gguf) | IQ4_XS | .74GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. |
-| [deepseek-coder-1.3B-kexer-Q3_K_L.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-Q3_K_L.gguf) | Q3_K_L | .74GB | Lower quality but usable, good for low RAM availability. |
-| [deepseek-coder-1.3B-kexer-Q3_K_M.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-Q3_K_M.gguf) | Q3_K_M | .70GB | Even lower quality. |
-| [deepseek-coder-1.3B-kexer-IQ3_M.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-IQ3_M.gguf) | IQ3_M | .67GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. |
-| [deepseek-coder-1.3B-kexer-IQ3_S.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-IQ3_S.gguf) | IQ3_S | .64GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. |
-| [deepseek-coder-1.3B-kexer-Q3_K_S.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-Q3_K_S.gguf) | Q3_K_S | .64GB | Low quality, not recommended. |
-| [deepseek-coder-1.3B-kexer-IQ3_XS.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-IQ3_XS.gguf) | IQ3_XS | .61GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. |
-| [deepseek-coder-1.3B-kexer-IQ3_XXS.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-IQ3_XXS.gguf) | IQ3_XXS | .58GB | Lower quality, new method with decent performance, comparable to Q3 quants. |
-| [deepseek-coder-1.3B-kexer-Q2_K.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-Q2_K.gguf) | Q2_K | .55GB | Very low quality but surprisingly usable. |
-| [deepseek-coder-1.3B-kexer-IQ2_M.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-IQ2_M.gguf) | IQ2_M | .55GB | Very low quality, uses SOTA techniques to also be surprisingly usable. |
-| [deepseek-coder-1.3B-kexer-IQ2_S.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-IQ2_S.gguf) | IQ2_S | .52GB | Very low quality, uses SOTA techniques to be usable. |
-| [deepseek-coder-1.3B-kexer-IQ2_XS.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-IQ2_XS.gguf) | IQ2_XS | .49GB | Very low quality, uses SOTA techniques to be usable. |
-| [deepseek-coder-1.3B-kexer-IQ2_XXS.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-IQ2_XXS.gguf) | IQ2_XXS | .47GB | Lower quality, uses SOTA techniques to be usable. |
-| [deepseek-coder-1.3B-kexer-IQ1_M.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-IQ1_M.gguf) | IQ1_M | .44GB | Extremely low quality, *not* recommended. |
-| [deepseek-coder-1.3B-kexer-IQ1_S.gguf](https://huggingface.co/bartowski/deepseek-coder-1.3B-kexer-GGUF/blob/main/deepseek-coder-1.3B-kexer-IQ1_S.gguf) | IQ1_S | .42GB | Extremely low quality, *not* recommended. |
+🙏 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.
 
-## Downloading using huggingface-cli
+🙏 Special thanks to [Kalomaze](https://github.com/kalomaze), [Dampf](https://github.com/Dampfinchen) and [turboderp](https://github.com/turboderp/) for their work on the dataset (linked [here](https://gist.github.com/bartowski1182/b6ac44691e994344625687afe3263b3a)) that was used for calculating the imatrix for all sizes.
 
-First, make sure you have hugginface-cli installed:
+## Disclaimers
 
-```
-pip install -U "huggingface_hub[cli]"
-```
-
-Then, you can target the specific file you want:
-
-```
-huggingface-cli download bartowski/deepseek-coder-1.3B-kexer-GGUF --include "deepseek-coder-1.3B-kexer-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/deepseek-coder-1.3B-kexer-GGUF --include "deepseek-coder-1.3B-kexer-Q8_0.gguf/*" --local-dir deepseek-coder-1.3B-kexer-Q8_0
-```
-
-You can either specify a new local-dir (deepseek-coder-1.3B-kexer-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:
-
-[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix)
-
-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.
-
-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.
-
-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.
-
-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.