uploaded readme

README.md

@@ -0,0 +1,117 @@
+Quantization made by Richard Erkhov.
+
+[Github](https://github.com/RichardErkhov)
+
+[Discord](https://discord.gg/pvy7H8DZMG)
+
+[Request more models](https://github.com/RichardErkhov/quant_request)
+
+
+Qwen2-0.5B-XPO - EXL2
+- Model creator: https://huggingface.co/trl-lib/
+- Original model: https://huggingface.co/trl-lib/Qwen2-0.5B-XPO/
+
+
+## Available sizes
+
+| Branch | Bits | Description |
+| ----- | ---- | ------------ |
+| [8_0](https://huggingface.co/trl-lib_-_Qwen2-0.5B-XPO-exl2/tree/8_0) | 8.0 | Maximum quality that ExLlamaV2 can produce, near unquantized performance. |
+| [6_5](https://huggingface.co/trl-lib_-_Qwen2-0.5B-XPO-exl2/tree/6_5) | 6.5 | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. |
+| [5_0](https://huggingface.co/trl-lib_-_Qwen2-0.5B-XPO-exl2/tree/5_0) | 5.0 | Slightly lower quality vs 6.5, but usable |
+| [4_25](https://huggingface.co/trl-lib_-_Qwen2-0.5B-XPO-exl2/tree/4_25) | 4.25 | GPTQ equivalent bits per weight, slightly higher quality. |
+| [3_5](https://huggingface.co/trl-lib_-_Qwen2-0.5B-XPO-exl2/tree/3_5) | 3.5 | Lower quality, only use if you have to. |
+
+
+## Download instructions
+With git:
+```shell
+git clone --single-branch --branch 6_5 https://huggingface.co/trl-lib_-_Qwen2-0.5B-XPO-exl2 Qwen2-0.5B-XPO-6_5
+```
+With huggingface hub:
+```shell
+pip3 install huggingface-hub
+```
+To download a specific branch, use the `--revision` parameter. For example, to download the 6.5 bpw branch:
+Linux:
+```shell
+huggingface-cli download trl-lib_-_Qwen2-0.5B-XPO-exl2 --revision 6_5 --local-dir Qwen2-0.5B-XPO-6_5 --local-dir-use-symlinks False
+```
+Windows (which apparently doesn't like _ in folders sometimes?):
+
+```shell
+huggingface-cli download trl-lib_-_Qwen2-0.5B-XPO-exl2 --revision 6_5 --local-dir Qwen2-0.5B-XPO-6.5 --local-dir-use-symlinks False
+```
+    
+
+
+
+  Original model description:
+  ---
+base_model: Qwen/Qwen2-0.5B-Instruct
+library_name: transformers
+model_name: Qwen2-0.5B-XPO
+tags:
+- generated_from_trainer
+- trl
+- xpo
+licence: license
+---
+
+# Model Card for Qwen2-0.5B-XPO
+
+This model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="qgallouedec/Qwen2-0.5B-XPO", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/huggingface/trl/runs/458cjtdo)
+
+This model was trained with XPO, a method introduced in [Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF](https://huggingface.co/papers/2405.21046).
+
+### Framework versions
+
+- TRL: 0.12.0.dev0
+- Transformers: 4.46.0.dev0
+- Pytorch: 2.4.1
+- Datasets: 3.0.1
+- Tokenizers: 0.20.0
+
+## Citations
+
+Cite XPO as:
+
+```bibtex
+@article{jung2024binary,
+    title        = {{Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF}},
+    author       = {Tengyang Xie and Dylan J. Foster and Akshay Krishnamurthy and Corby Rosset and Ahmed Awadallah and Alexander Rakhlin},
+    year         = 2024,
+    eprint       = {arXiv:2405.21046}
+}
+```
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```
+
+