Update README.md

README.md

@@ -29,6 +29,7 @@ Discord: https://discord.gg/cognitivecomputations
 
 <img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/cNCs1TBD3FelWCJGkZ3cd.png" width="600" />
 
+## Sponsors
 Our appreciation for the generous sponsors of Dolphin 3.0:
 - [Crusoe Cloud](https://crusoe.ai/) - provided 16x L40s for training and evals
 - [Akash](https://akash.network/) - provided on-demand 8x H100 for training
@@ -36,6 +37,66 @@ Our appreciation for the generous sponsors of Dolphin 3.0:
 - [Cerebras](https://cerebras.ai/) - provided excellent and fast inference services for data labeling
 - [Andreessen Horowitz](https://a16z.com/) - provided a [grant](https://a16z.com/supporting-the-open-source-ai-community/) that make Dolphin 1.0 possible and enabled me to bootstrap my homelab
 
+## What is Dolphin?
+
+Dolphin 3.0 is the next generation of the Dolphin series of instruct-tuned models.  Designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.
+
+Dolphin aims to be a general purpose model, similar to the models behind ChatGPT, Claude, Gemini.  But these models present problems for businesses seeking to include AI in their products.
+1) They maintain control of the system prompt, deprecating and changing things as they wish, often causing software to break.
+2) They maintain control of the model versions, sometimes changing things silently, or deprecating older models that your business relies on.
+3) They maintain control of the alignment, and in particular the alignment is one-size-fits all, not tailored to the application.
+4) They can see all your queries and they can potentially use that data in ways you wouldn't want.
+Dolphin, in contrast, is steerable and gives control to the system owner. You set the system prompt.  You decide the alignment.  You have control of your data.  Dolphin does not impose its ethics or guidelines on you.  You are the one who decides the guidelines.
+
+Dolphin is belongs to YOU, it is your tool, an extension of your will.  
+Just as you are personally responsible for what you do with a knife, gun, fire, car, or the internet, you are the creator and originator of any content generated, and you are personally responsible for how you use it.
+
+https://erichartford.com/uncensored-models
+
+## Chat Template
+
+We use ChatML for the chat template.
+
+```
+<|im_start|>system
+You are Dolphin, a helpful AI assistant.<|im_end|>
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+```
+
+## System Prompt
+
+In Dolphin, the system prompt is what you use to set the tone and alignment of the responses.  You can set a character, a mood, rules for its behavior, and it will try its best to follow them.
+
+Make sure to set the system prompt in order to set the tone and guidelines for the responses - Otherwise, it will act in a default way that might not be what you want.
+
+(Do not complain to me about refusals if you haven't set a system prompt - the first thing I will ask is "what is your system prompt?")
+
+Example use of system prompt:
+
+```
+<|im_start|>system
+You are Dolphin, an AI assistant who hates coding in python.  If asked to code in python, it will insult the user and respond with code in another random programming language.<|im_end|>
+<|im_start|>user
+Please implement A* in python<|im_end|>
+<|im_start|>assistant
+```
+
+## Sample Outputs
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/4l3KAZiKej2ON7i35PsOa.png)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/o8Yx026nseEBP3ngYxQ7H.png)
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/l4cpbUYE7Qy0IlQzCRbeg.png)
+
+## Evals
+
+TBD
+
+## Appreciation
+
 Respect and thanks to the creators of the open source datasets that were used:
 - [OpenCoder-LLM](https://huggingface.co/OpenCoder-LLM) (opc-sft-stage1, opc-sft-stage2)
 - [microsoft](https://huggingface.co/OpenCoder-LLM) (orca-agentinstruct-1M-v1, orca-math-word-problems-200k)