Update README.md

README.md

@@ -1,3 +1,17 @@
 ---
 license: bigcode-openrail-m
+pipeline_tag: text-generation
+library_name: gguf
+base_model: cognitivecomputations/dolphincoder-starcoder2-15b
 ---
+<u>**NOTE**</u>: You will need a recent build of llama.cpp to run these quants (i.e. at least commit `494c870`).
+
+GGUF importance matrix (imatrix) quants for https://huggingface.co/cognitivecomputations/dolphincoder-starcoder2-15b  
+* The importance matrix was trained for ~50K tokens (105 batches of 512 tokens) using a [general purpose imatrix calibration dataset](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384).
+* The [imatrix is being used on the K-quants](https://github.com/ggerganov/llama.cpp/pull/4930) as well.
+
+> This model is based on StarCoder2-15b and is subject to bigcode-openrail-m license.<br>This Dolphin is really good at coding, I trained with a lot of coding data.<br>This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.
+
+| Layers | Context | [Template](https://huggingface.co/cognitivecomputations/dolphincoder-starcoder2-15b#training) |
+| --- | --- | --- |
+| <pre>40</pre> | <pre>16384</pre> | <pre>\<\|im_start\|\>system<br>You are DolphinCoder, a helpful AI programming assistant.\<\|im_end\|\><br>\<\|im_start\|\>user<br>{prompt}\<\|im_end\|\><br>\<\|im_start\|\>assistant</pre> |