Update README.md

README.md

@@ -1,3 +1,80 @@
----
-license: cc-by-nc-nd-3.0
----
+---
+license: cc-by-nc-nd-3.0
+---
+# SFR-Iterative-DPO-Llama-3-8B-R
+
+## Introduction
+We release a state-of-the-art instruct model of its class, **SFR-Iterative-DPO-LLaMA-3-8B-R**.
+On all three widely-used instruct model benchmarks: **Alpaca-Eval-V2**, **MT-Bench**, **Chat-Arena-Hard**, our model outperforms all models of similar size (e.g., LLaMA-3-8B-it), most large open-sourced models (e.g., Mixtral-8x7B-it),
+and strong proprietary models (e.g., GPT-3.5-turbo-0613). The model is trained with open-sourced datasets without any additional human- or GPT4-labeling.
+
+## Model Releases
+- SFT model
+- Reward model
+- RLHF model
+
+## Dataset Releases
+- Preference data mix
+- Prompt collection for RLHF training
+
+## Training methods
+The key to our training is iterative RLHF.
+
+
+## Chat Benchmarks
+
+| **Model**               | **Size** | **Method**        | **LC Alpaca-Eval-V2** | **MT-Bench** | **Chat-Arena-Hard** |
+|-------------------------|----------|-------------------|-----------------------|--------------|---------------------|
+| **Small Open-Sourced Models**           |          |                   |                       |              |                     |
+| Gemma-7B-it             | 7B       | SFT               | 10.4                  | 6.38         | 7.5                 |
+| Zephyr-7B-beta          | 7B       | Vanilla DPO       | 13.1                  | 7.34         | -                   |
+| Mistral-7B-v0.2-it      | 7B       | SFT               | 17.1                  | 7.51         | 12.6                |
+| Open-Chat-0106          | 7B       | SFT               | 15.6                  | 7.8          | -                   |
+| Starling-7B-beta        | 7B       | PPO               | 25.8                  | 8.12         | 23.0                |
+| LLaMA-3-8B-it           | 8B       | RS+DPO+PPO        | 22.9                  | 8.16         | 20.6                |
+| **Ours**                |          |                   |                       |              |                     |
+| Ours (SFT baseline)     | 8B       | SFT               | 10.2                  | 7.69         | 5.6                 |
+| Ours (DPO baseline)     | 8B       | Vanilla DPO       | 22.5                  | 8.17         | 22.4                |
+| Ours (Online RLHF)      | 8B       | Iterative DPO     | **37.2**              | **8.46**     | **29.1**            |
+| **Large Open-Sourced Models**       |          |                   |                       |              |                     |
+| Vicuna-33b-v1.3         | 33B      | SFT               | 17.6                  | 7.12         | 8.6                 |
+| Yi-34B-Chat             | 34B      | SFT               | 27.2                  | -            | 23.1                |
+| Mixtral-8x7B-it         | 45B*     | SFT               | 23.7                  | 8.30         | 23.4                |
+| Tulu-2-DPO-70B          | 70B      | Vanilla DPO       | 21.2                  | 7.89         | 15.0                |
+| LLaMA-3-70B-it          | 70B      | RS+DPO+PPO        | 34.4                  | 8.95         | 41.1                |
+| Mixtral-8x22B-it        | 141B*    | SFT               | 30.9                  | 8.66         | 36.4                |
+| **Proprietary Models**  |       |                   |                       |              |                     |
+| GPT-3.5-turbo-1106      | -        | -                 | 19.3                  | 8.35         | 18.9                |
+| GPT-3.5-turbo-0613      | -        | -                 | 22.7                  | 8.39         | 24.8                |
+| GPT-4-0613              | -        | -                 | 30.2                  | 9.18         | 37.9                |
+| Claude-3-Opus           | -        | -                 | 40.5                  | 9.00         | 60.4                |
+| GPT-4 Turbo (04/09)     | -        | -                 | 55.0                  | -            | 82.6                |
+
+
+## Academic Benchmarks
+
+| **Model**              | **Size** | **Method**    | **GSM-8K** | **MMLU** | **HumanEval** | **TruthfulQA** | **ARC** | **MBPP** |
+|------------------------|----------|---------------|------------|----------|---------------|----------------|---------|----------|
+| LLaMA-3-8B-it          | 8B       | RS+DPO+PPO    | 79.6       | 66.0     | 61.6          | 43.9           | 59.5    | 61.1     |
+| Ours (SFT baseline)    | 8B       | SFT           | 76.7       |          | 61.0          |                |         | 63.5     |
+| Ours (Offline baseline)| 8B       | Vanilla DPO   | 79.8       |          | 63.4          |                |         | 60.3     |
+| Ours (Online RLHF)     | 8B       | Iterative DPO | 80.7       | 65.3     | 64.6          | 60.4           | 64.3    | 60.8     |
+
+
+## Usage
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model = AutoModelForCausalLM.from_pretrained("Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R")
+tokenizer = AutoTokenizer.from_pretrained("Salesforce/SFR-Iterative-DPO-LLaMA-3-8B-R")
+
+```
+
+
+## Limitations
+SFR-Iterative-DPO-LLaMA-3-8B-R is a reseach model as a result on our RLHF research at Salesforce.  
+
+## Citation
+Please cite our techical report if you find our model is useful for your research or product.
+```
+@article{}
+```