Update README.md

README.md

@@ -13,14 +13,15 @@ tags:
 - dpo
 - preference
 - ultrafeedback
-license: apache-2.0
+license: mit
 ---
+<div align="center">
+  <img src="https://cdn-uploads.huggingface.co/production/uploads/60420dccc15e823a685f2b03/CuMO3IjJfymC94_5qd15T.png" alt="Image was artificially generated by Dalle-3 via ChatGPT Pro" width="50%"/>
+</div>
 
 # Model Card for Notus 7B v1
 
-<div align="center">
-  <img src="https://cdn-uploads.huggingface.co/production/uploads/60f0608166e5701b80ed3f02/LU-vKiC0R7UxxITrwE1F_.png" alt="Image was artificially generated by Dalle-3 via ChatGPT Pro"/>
-</div>
+
 
 Notus is a collection of fine-tuned models using Direct Preference Optimization (DPO) and related RLHF techniques. This model is version 1, fine-tuned with DPO starting with zephyr-7b-beta's SFT model. 
 
@@ -41,7 +42,7 @@ with the original Zephyr dDPO model and other 7B models.
 - **Shared by:** Argilla
 - **Model type:** GPT-like 7B model DPO fine-tuned
 - **Language(s) (NLP):** Mainly English
-- **License:** Apache 2.0 (same as Zephyr 7B SFT and Mistral 7B v0.1)
+- **License:** MIT (same as Zephyr 7B-beta)
 - **Finetuned from model:** [`alignment-handbook/zephyr-7b-sft-full`](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full)
 
 ### Model Sources
@@ -53,18 +54,18 @@ with the original Zephyr dDPO model and other 7B models.
 ## Performance
 
 ### Chat benchmarks
-This shows the updated table, based on Zephyr-7b-β original table for [MT-Bench](https://huggingface.co/spaces/lmsys/mt-bench) and [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmarks:
+Table adapted from Zephyr-7b-β original table for [MT-Bench](https://huggingface.co/spaces/lmsys/mt-bench) and [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmarks. Notus stays on par with Zephyr on MT-Bench, while surpassing Zephyr, Claude 2, and Cohere Command on AlpacaEval. Making Notus the most-competitive 7B commercial model on AlpacaEval.
 
 | Model | Size | Alignment | MT-Bench (score) | AlpacaEval (win rate %) |
 |-------------|-----|----|---------------|--------------|
 | MPT-Chat |  7B |dSFT |5.42| -|
 | Xwin-LMv0.1 | 7B| dPPO| 6.19| 87.83|
 | Mistral-Instructv0.1 | 7B|  - | 6.84 |-|
-| Zephyr-7b-β 🪁 | 7B | **dDPO** | **7.34** | 90.60 |
-| **Notus-7b-v1** | 7B | **dDPO** | 7.30 | **91.42** |
+| Zephyr-7b-β 🪁 | 7B | dDPO | **7.34** | 90.60 |
+| **Notus-7b-v1** | 7B | dDPO | 7.30 | **91.42** |
 | GPT-3.5-turbo | - |RLHF |7.94 |89.37|
 | Claude 2 |  - |RLHF |8.06| 91.36|
-| Cohere Command 2 |  - |RLHF |-| 90.62|
+| Cohere Command |  - |RLHF |-| 90.62|
 | GPT-4 |  -| RLHF |8.99| 95.28|
 | Falcon-Instruct |  40B |dSFT |5.17 |45.71|
 | Guanaco | 65B |  SFT |6.41| 71.80|
@@ -75,6 +76,8 @@ This shows the updated table, based on Zephyr-7b-β original table for [MT-Bench
 
 ## Academic benchmarks
 
+Results from [OpenLLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard):
+
 | Model                                         | Average | ARC   | HellaSwag | MMLU  | TruthfulQA | Winogrande | GSM8K | DROP  |
 |-----------------------------------------------|---------|-------|-----------|-------|------------|------------|-------|-------|
 | Zephyr 7B dDPO (HuggingFaceH4/zephyr-7b-beta) | 52.15   | 62.03 | 84.36      | 61.07 | **57.45**  | 77.74      | 12.74 | **9.66**  |