初始化项目，由ModelHub XC社区提供模型

Model: qwp4w3hyb/Gemma-2-9B-It-SPPO-Iter3-iMat-GGUF Source: Original Platform
2026-09-16 18:18:16 +08:00
commit 8d34615f48
12 changed files with 176 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,101 @@
+---
+license: gemma
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- gemma
+- gguf
+- SPPO
+- imatrix
+base_model: UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3
+---
+
+# Quant Infos
+
+## Updated for all recent llama.cpp fixes (final logit soft capping+sliding window+tokenizer)
+
+- quants done with an importance matrix for improved quantization loss
+- Requantized ggufs & imatrix from hf bf16
+  - initial version was based on f32 gguf provided by google, which had various issues
+  - also updated for all recent llama.cpp fixes (final logit soft capping+sliding window+tokenizer)
+- Wide coverage of different gguf quant types from Q\_8\_0 down to IQ1\_S
+  - experimental custom quant types
+    - `_L` with `--output-tensor-type f16 --token-embedding-type f16` (same as bartowski's)
+- Quantized with [llama.cpp](https://github.com/ggerganov/llama.cpp) commit [5fac350b9cc49d0446fc291b9c4ad53666c77591](https://github.com/ggerganov/llama.cpp/commit/5fac350b9cc49d0446fc291b9c4ad53666c77591) (master from 2024-07-02)
+- Imatrix generated with [this](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) multi-purpose dataset by [bartowski](https://huggingface.co/bartowski).
+  ```
+  ./imatrix -m $model_name-bf16.gguf -f calibration_datav3.txt -o $model_name.imatrix
+  ```
+
+
+
+---
+# Original Model Card:
+
+Self-Play Preference Optimization for Language Model Alignment (https://arxiv.org/abs/2405.00675)
+
+# Gemma-2-9B-It-SPPO-Iter3
+
+This model was developed using [Self-Play Preference Optimization](https://arxiv.org/abs/2405.00675) at iteration 3, based on the [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) architecture as starting point. We utilized the prompt sets from the [openbmb/UltraFeedback](https://huggingface.co/datasets/openbmb/UltraFeedback) dataset, splited to 3 parts for 3 iterations by [snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset](https://huggingface.co/datasets/snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset). All responses used are synthetic.
+
+**Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent/verify/huggingface?returnModelRepoId=google/gemma-2-9b-it)
+
+
+## Links to Other Models
+- [Gemma-2-9B-It-SPPO-Iter1](https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter1)
+- [Gemma-2-9B-It-SPPO-Iter2](https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2)
+- [Gemma-2-9B-It-SPPO-Iter3](https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3)
+
+### Model Description
+
+- Model type: A 8B parameter GPT-like model fine-tuned on synthetic datasets.
+- Language(s) (NLP): Primarily English
+- License: Apache-2.0
+- Finetuned from model: google/gemma-2-9b-it
+
+
+## [AlpacaEval Leaderboard Evaluation Results](https://tatsu-lab.github.io/alpaca_eval/)
+
+
+|                Model                           | LC. Win Rate | Win Rate | Avg. Length |
+|-------------------------------------------|:------------:|:--------:|:-----------:|
+|[Gemma-2-9B-SPPO Iter1](https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter1) |48.70 |40.76 | 1669
+|[Gemma-2-9B-SPPO Iter2](https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter2) |50.93 | 44.64 | 1759
+|[Gemma-2-9B-SPPO Iter3](https://huggingface.co/UCLA-AGI/Gemma-2-9B-It-SPPO-Iter3) |**53.27** |**47.74** | 1803
+
+
+
+
+
+
+### Training hyperparameters
+The following hyperparameters were used during training:
+
+- learning_rate: 5e-07
+- eta: 1000
+- per_device_train_batch_size: 8
+- gradient_accumulation_steps: 1
+- seed: 42
+- distributed_type: deepspeed_zero3
+- num_devices: 8
+- optimizer: RMSProp 
+- lr_scheduler_type: linear 
+- lr_scheduler_warmup_ratio: 0.1
+- num_train_epochs: 1.0
+
+
+
+  
+## Citation
+```
+@misc{wu2024self,
+      title={Self-Play Preference Optimization for Language Model Alignment}, 
+      author={Wu, Yue and Sun, Zhiqing and Yuan, Huizhuo and Ji, Kaixuan and Yang, Yiming and Gu, Quanquan},
+      year={2024},
+      eprint={2405.00675},
+      archivePrefix={arXiv},
+      primaryClass={cs.LG}
+}
+```
+