Update README.md

README.md

@@ -8,7 +8,7 @@ pipeline_tag: text-generation
 license: apache-2.0
 ---
 
-<p><h1>🐋 TBD 🐋</h1></p>
+<p><h1>🐋 Mistral-7B-OpenOrca 🐋</h1></p>
 
 
 ![OpenOrca Logo](https://huggingface.co/datasets/Open-Orca/OpenOrca/resolve/main/OpenOrcaLogo.png "OpenOrca Logo")
@@ -26,7 +26,8 @@ It is the same subset of our data as was used in our [OpenOrcaxOpenChat-Preview2
 
 HF Leaderboard evals place this model as #2 for all models smaller than 30B at release time, outperforming all but one 13B model.
 
-TBD
+This release provides a first: a fully open model with class-breaking performance, capable of running fully accelerated on even moderate consumer GPUs.
+Our thanks to the Mistral team for leading the way here. 
 
 Want to visualize our full (pre-filtering) dataset? Check out our [Nomic Atlas Map](https://atlas.nomic.ai/map/c1b88b47-2d9b-47e0-9002-b80766792582/2560fd25-52fe-42f1-a58f-ff5eccc890d2).
 
@@ -39,31 +40,68 @@ We will also give sneak-peak announcements on our Discord, which you can find he
 
 https://AlignmentLab.ai
 
-or on the OpenAccess AI Collective Discord for more information about Axolotl trainer here:
+or check the OpenAccess AI Collective Discord for more information about Axolotl trainer here:
 
 https://discord.gg/5y8STgB3P3
 
+
 # Prompt Template
 
 We used [OpenAI's Chat Markup Language (ChatML)](https://github.com/openai/openai-python/blob/main/chatml.md) format, with `<|im_start|>` and `<|im_end|>` tokens added to support this.
 
 ## Example Prompt Exchange
 
-TBD
+```
+<|im_start|>system
+You are MistralOrca, a large language model trained by Alignment Lab AI. Write out your reasoning step-by-step to be sure you get the right answers!
+<|im_end|>
+<|im_start|>user
+How are you<|im_end|>
+<|im_start|>assistant
+I am doing well!<|im_end|>
+<|im_start|>user
+Please tell me about how mistral winds have attracted super-orcas.<|im_end|>
+```
+
 
 # Evaluation
 
-We have evaluated using the methodology and tools for the HuggingFace Leaderboard, and find that we have significantly improved upon the base model.
+## HuggingFace Leaderboard Performance
+
+We have evaluated using the methodology and tools for the HuggingFace Leaderboard, and find that we have dramatically improved upon the base model.
+We find **105%** of the base model's performance on HF Leaderboard evals, averaging **65.33**.
+
+![HF Leaderboard](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca/resolve/main/Images/MistralOrca7BHFLeaderboard.png)
+
+
+| Metric | Value |
+|-----------------------|-------|
+| MMLU (5-shot)         | 61.73 |
+| ARC (25-shot)         | 63.57 |
+| HellaSwag (10-shot)   | 83.79 |
+| TruthfulQA (0-shot)   | 52.24 |
+| Avg.                  | 65.33 |
+
+We use [Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness) to run the benchmark tests above, using the same version as the HuggingFace LLM Leaderboard.
 
-TBD
 
-## HuggingFaceH4 Open LLM Leaderboard Performance
+## AGIEval Performance
 
-TBD
+We compare our results to our base Preview2 model (using LM Evaluation Harness).
 
-## GPT4ALL Leaderboard Performance
+We find **129%** of the base model's performance on AGI Eval, averaging **0.397**.
+As well, we significantly improve upon the official `mistralai/Mistral-7B-Instruct-v0.1` finetuning, achieving **119%** of their performance.
+
+![OpenOrca-Platypus2-13B AGIEval Performance](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca/resolve/main/Images/MistralOrca7BAGIEval.png "AGIEval Performance")
+
+## BigBench-Hard Performance
+
+We compare our results to our base Preview2 model (using LM Evaluation Harness).
+
+We find **119%** of the base model's performance on BigBench-Hard, averaging **0.416**.
+
+![OpenOrca-Platypus2-13B BigBench-Hard Performance](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca/resolve/main/Images/MistralOrca7BBigBenchHard.png "BigBench-Hard Performance")
 
-TBD
 
 # Dataset
 
@@ -75,6 +113,7 @@ We used a curated, filtered selection of most of the GPT-4 augmented data from o
 We trained with 8x A6000 GPUs for 62 hours, completing 4 epochs of full fine tuning on our dataset in one training run.
 Commodity cost was ~$400.
 
+
 # Citation
 
 ```bibtex