Update README.md

README.md

@@ -1,29 +1,46 @@
 ---
 license: llama3.1
+datasets:
+- OpenCoder-LLM/opc-sft-stage1
+- OpenCoder-LLM/opc-sft-stage2
+- microsoft/orca-agentinstruct-1M-v1
+- microsoft/orca-math-word-problems-200k
+- NousResearch/hermes-function-calling-v1
+- AI-MO/NuminaMath-CoT
+- AI-MO/NuminaMath-TIR
+- allenai/tulu-3-sft-mixture
+- cognitivecomputations/dolphin-coder
+- HuggingFaceTB/smoltalk
+- cognitivecomputations/samantha-data
+- m-a-p/CodeFeedback-Filtered-Instruction
+- m-a-p/Code-Feedback
 language:
 - en
 base_model:
-- meta-llama/Llama-3.1-8B-Instruct
+- meta-llama/Llama-3.1-8B
 ---
 
-# Dolphin Llama 3.1 8B Instruct 🐬
+# Dolphin 3.0 Llama 3.1 8B 🐬
+Part of the [Dolphin 3.0 Collection](https://huggingface.co/collections/cognitivecomputations/dolphin-30-677ab47f73d7ff66743979a3)
+
+Curated and trained by [Eric Hartford](https://huggingface.co/ehartford), [Ben Gitter](https://huggingface.co/bigstorm), [BlouseJury](https://huggingface.co/BlouseJury) and [Cognitive Computations](https://huggingface.co/cognitivecomputations)
 
 [![Discord](https://img.shields.io/discord/1156064224225808488?logo=Discord&logoColor=%23ffffff&label=Discord&link=https%3A%2F%2Fdiscord.gg%2FtCMkMDDHwm)](https://discord.gg/cognitivecomputations)
 Discord: https://discord.gg/cognitivecomputations
 
-<img src="https://i.postimg.cc/bvWXwnz7/dolphin.webp" width="600" />
+<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/cNCs1TBD3FelWCJGkZ3cd.png" width="600" />
 
 ## Sponsors
-Our appreciation for the generous sponsors of Dolphin:
+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
 - [Lazarus](https://www.lazarusai.com/) - provided 16x H100 for training
 - [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 Llama 3.1 8B Instruct?
+## What is Dolphin?
 
-Dolphin Llama 3.1 8B Instruct is a result of our effort to directly uncensor Llama's 3.1 8B instruct-tuned model.
+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.
@@ -39,7 +56,15 @@ https://erichartford.com/uncensored-models
 
 ## Chat Template
 
-We maintained the default Llama chat template for this model.
+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
 
@@ -59,7 +84,9 @@ Please implement A* using python<|im_end|>
 
 ## Sample Outputs
 
-**add sample outputs here**
+<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/C-r1X13UBjnUUNb0q2JLV.png" width="600" />
+<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/4l3KAZiKej2ON7i35PsOa.png" width="600" />
+<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/1ZalmR66LnwhEQQEFttlu.png" width="600" />
 
 ## How to use
 
@@ -71,6 +98,29 @@ There are many ways to use a huggingface model including:
 - sglang
 - tgi
 
+### ollama
+- [Install ollama](https://ollama.com/download)
+- ```ollama run hf.co/cognitivecomputations/Dolphin3.0-Llama3.1-8B-GGUF:Q4_0```
+- ```/set system <your system prompt>```
+
 ## Evals
 
-TBD
+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)
+- [NousResearch](https://huggingface.co/NousResearch) (hermes-function-calling-v1)
+- [AI-MO](https://huggingface.co/AI-MO) (NuminaMath-CoT, NuminaMath-TIR)
+- [allenai](https://huggingface.co/allenai) (tulu-3-sft-mixture)
+- [HuggingFaceTB](https://huggingface.co/HuggingFaceTB) (smoltalk)
+- [m-a-p](https://huggingface.co/m-a-p) (CodeFeedback-Filtered-Instruction, Code-Feedback)
+
+Special thanks to 
+- Meta, Qwen, and OpenCoder, who wrote papers and published models that were instrumental in creating Dolphin 3.0.
+- [RLHFlow](https://huggingface.co/RLHFlow) for the excellent reward model used to filter the datasets
+- Deepseek, for the ridiculously fast Deepseek-V3 that we used to augment the data.
+
+