uploaded readme

README.md

@@ -0,0 +1,160 @@
+Quantization made by Richard Erkhov.
+
+[Github](https://github.com/RichardErkhov)
+
+[Discord](https://discord.gg/pvy7H8DZMG)
+
+[Request more models](https://github.com/RichardErkhov/quant_request)
+
+
+Storm-7B - GGUF
+- Model creator: https://huggingface.co/jieliu/
+- Original model: https://huggingface.co/jieliu/Storm-7B/
+
+
+| Name | Quant method | Size |
+| ---- | ---- | ---- |
+| [Storm-7B.Q2_K.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.Q2_K.gguf) | Q2_K | 2.53GB |
+| [Storm-7B.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.IQ3_XS.gguf) | IQ3_XS | 2.81GB |
+| [Storm-7B.IQ3_S.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.IQ3_S.gguf) | IQ3_S | 2.96GB |
+| [Storm-7B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.Q3_K_S.gguf) | Q3_K_S | 2.95GB |
+| [Storm-7B.IQ3_M.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.IQ3_M.gguf) | IQ3_M | 3.06GB |
+| [Storm-7B.Q3_K.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.Q3_K.gguf) | Q3_K | 3.28GB |
+| [Storm-7B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.Q3_K_M.gguf) | Q3_K_M | 3.28GB |
+| [Storm-7B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.Q3_K_L.gguf) | Q3_K_L | 3.56GB |
+| [Storm-7B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.IQ4_XS.gguf) | IQ4_XS | 3.67GB |
+| [Storm-7B.Q4_0.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.Q4_0.gguf) | Q4_0 | 3.83GB |
+| [Storm-7B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.IQ4_NL.gguf) | IQ4_NL | 3.87GB |
+| [Storm-7B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.Q4_K_S.gguf) | Q4_K_S | 3.86GB |
+| [Storm-7B.Q4_K.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.Q4_K.gguf) | Q4_K | 4.07GB |
+| [Storm-7B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.Q4_K_M.gguf) | Q4_K_M | 4.07GB |
+| [Storm-7B.Q4_1.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.Q4_1.gguf) | Q4_1 | 4.24GB |
+| [Storm-7B.Q5_0.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.Q5_0.gguf) | Q5_0 | 4.65GB |
+| [Storm-7B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.Q5_K_S.gguf) | Q5_K_S | 4.65GB |
+| [Storm-7B.Q5_K.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.Q5_K.gguf) | Q5_K | 4.78GB |
+| [Storm-7B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.Q5_K_M.gguf) | Q5_K_M | 4.78GB |
+| [Storm-7B.Q5_1.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.Q5_1.gguf) | Q5_1 | 5.07GB |
+| [Storm-7B.Q6_K.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.Q6_K.gguf) | Q6_K | 5.53GB |
+| [Storm-7B.Q8_0.gguf](https://huggingface.co/RichardErkhov/jieliu_-_Storm-7B-gguf/blob/main/Storm-7B.Q8_0.gguf) | Q8_0 | 7.17GB |
+
+
+
+
+Original model description:
+---
+license: apache-2.0
+library_name: transformers
+tags:
+- storm
+- mistral
+- openchat
+- RLAIF
+- reward model
+language:
+- en
+base_model: openchat/openchat-3.5-0106
+datasets:
+- berkeley-nest/Nectar
+---
+
+# Storm-7B
+- **Developed by**: [Jie Liu](https://jieliu.site/) \\(^{*1,2}\\), [Zhanhui Zhou](https://scholar.google.com/citations?user=SbACfYQAAAAJ&hl=zh-CN) \\(^{*2}\\), [Jiaheng Liu](https://liujiaheng.github.io/) \\(^{2}\\), [Xingyuan Bu](https://scholar.google.com.hk/citations?user=cqYaRhUAAAAJ&hl=zh-CN) \\(^{2}\\), [Chao Yang](https://scholar.google.com/citations?user=5KRbHPMAAAAJ&hl=zh-CN) \\(^{2}\\), [Han-Sen Zhong](https://scholar.google.com.hk/citations?user=X_ZfX8sAAAAJ&hl=zh-CN) \\(^{\dag 2}\\), [Wanli Ouyang](https://wlouyang.github.io/) \\(^{1,2}\\).
+- \\(^{1}\\)MMLab, The Chinese University of Hong Kong    \\(^{2}\\)Shanghai AI Laboratory
+- Paper: [Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level](https://arxiv.org/pdf/2406.11817)
+- Finetuned from the model: [openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
+- Dataset: [berkeley-nest/Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar)
+- Reward Model: [Starling-RM-34B](https://huggingface.co/Nexusflow/Starling-RM-34B)
+
+Please see our paper for more details.
+
+## Introduction
+
+We released Storm-7B, the first open-source language model comparable to the GPT-4 series on the [AlpacaEval 2.0](https://tatsu-lab.github.io/alpaca_eval/) leaderboard.
+
+Recent studies show that DPO benefits from iterative training with online preferences labeled by a trained reward model. In this work, we identify a pitfall of vanilla iterative DPO - improved response quality can lead to increased verbosity. To address this, we introduce iterative length-regularized DPO (iLR-DPO) to penalize response length. Our empirical results show that iLR-DPO can enhance a 7B model to perform on par with GPT-4 **without increasing verbosity**. 
+
+## Performance
+Our 7B model achieves a **50.5%** length-controlled win rate against GPT-4 Preview on AlpacaEval 2.0.
+<p align="center">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/639be86b59473c6ae02ef9c4/Tj_a1QntAxkhy2SXbOdmT.png" width="60%">
+</p>
+Our model's LC win rate improves over iterations without significantly changing the response length, indicating better alignment with human values without length bias. The final trained model (iteration 3) achieves a 50.5% LC win rate, making it the first open-source model to surpass the baseline model GPT-4 Preview.
+
+In addition to regular decoding, we also test beam search and best-of-n sampling on top of our trained model. Beam search over our trained model shows a 5% improvement over regular decoding, Best-of-n sampling with Starling-RM-34B achieves 61.6% LC Win rate and outperforms GPT-4 Omni.
+<p align="center">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/639be86b59473c6ae02ef9c4/GGa28vaREaVq099MPdqcP.png" width="100%">
+</p>
+
+We observe no significant degradation in traditional NLP tasks from the Huggingface Open LLM Leaderboard.
+<p align="center">
+    <img src="https://cdn-uploads.huggingface.co/production/uploads/639be86b59473c6ae02ef9c4/8KEm_Ladg7Kqko8mC63SN.png" width="100%">
+</p>
+
+
+## Uses
+
+Our model uses the same chat template as [Openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106). A sample code snippet for inference using our model is provided below.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+device = "cuda"
+
+model = AutoModelForCausalLM.from_pretrained("jieliu/Storm-7B").to(device)
+tokenizer = AutoTokenizer.from_pretrained("jieliu/Storm-7B")
+model.eval().requires_grad_(False)
+
+def generate_response(prompt):
+    input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(device)
+    outputs = model.generate(
+        input_ids,
+        max_length=2048,
+        do_sample=True,
+        temperature=1.0,
+        pad_token_id=tokenizer.pad_token_id,
+        eos_token_id=tokenizer.eos_token_id,
+    )
+    response_ids = outputs[0]
+    response_text = tokenizer.decode(response_ids, skip_special_tokens=True)
+    return response_text
+
+prompt = "How does a telescope work?"
+input_prompt = f"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:"
+response_text = generate_response(input_prompt)
+print("Response:", response_text)
+```
+
+## Scripts
+You can reproduce our results on AlphaEval 2.0 using the script provided below.
+```bash
+git clone https://github.com/tatsu-lab/alpaca_eval.git
+cd alpaca_eval
+pip install -e .
+export OPENAI_API_KEY=<your_api_key>
+alpaca_eval evaluate_from_model --model_configs 'Storm-7B'
+```
+
+## Limitations
+
+Our work has several limitations:
+(1) We focus on aligning with human preferences but only use GPT-4 as a proxy for human judgment to evaluate language models. 
+(2) We reduce verbosity with a length penalty, though verbosity and length are not necessarily correlated. Future work could train a specific reward model to directly penalize verbosity, replacing the length margin with a verbosity margin, following the standard [MODPO pipeline](https://github.com/ZHZisZZ/modpo).
+
+## Citation
+
+```
+@article{liu2024iterative,
+    title = {Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level},
+    author = {Liu, Jie and Zhou, Zhanhui and Liu, Jiaheng and Bu, Xingyuan and Yang, Chao and Zhong Han-Sen and Ouyang, Wanli},
+    journal={arXiv preprint arXiv:2406.11817},
+    year={2024}
+}
+
+@article{zhou2023beyond,
+  title={Beyond one-preference-for-all: Multi-objective direct preference optimization},
+  author={Zhou, Zhanhui and Liu, Jie and Yang, Chao and Shao, Jing and Liu, Yu and Yue, Xiangyu and Ouyang, Wanli and Qiao, Yu},
+  journal={arXiv preprint arXiv:2310.03708},
+  year={2023}
+}
+```
+