commit 8d34615f485ee4d5e10b9552c05467f426021d79 Author: ModelHub XC Date: Wed Sep 16 18:18:16 2026 +0800 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 diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..92d36ff --- /dev/null +++ b/.gitattributes @@ -0,0 +1,45 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-sppo-iter3-imat-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-sppo-iter3-imat-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-sppo-iter3-imat-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-sppo-iter3-imat-Q8_0_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-sppo-iter3-bf16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-sppo-iter3-imat-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-sppo-iter3-imat-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-sppo-iter3-imat-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-sppo-iter3-imat-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-sppo-iter3.imatrix filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b114d4d --- /dev/null +++ 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} +} +``` + diff --git a/gemma-2-9b-it-sppo-iter3-bf16.gguf b/gemma-2-9b-it-sppo-iter3-bf16.gguf new file mode 100644 index 0000000..f98db01 --- /dev/null +++ b/gemma-2-9b-it-sppo-iter3-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86c08ca2fb9baed8b7ae3ea3aed35951e8dd4ca98d0b1ee9d202795445cba3bf +size 18490680992 diff --git a/gemma-2-9b-it-sppo-iter3-imat-IQ1_S.gguf b/gemma-2-9b-it-sppo-iter3-imat-IQ1_S.gguf new file mode 100644 index 0000000..9239fbf --- /dev/null +++ b/gemma-2-9b-it-sppo-iter3-imat-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:203ac5233221219292b68d77072e54ef25235ee558a127e40d5bf1415a186433 +size 2378565600 diff --git a/gemma-2-9b-it-sppo-iter3-imat-IQ2_XXS.gguf b/gemma-2-9b-it-sppo-iter3-imat-IQ2_XXS.gguf new file mode 100644 index 0000000..822a4cd --- /dev/null +++ b/gemma-2-9b-it-sppo-iter3-imat-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7e2db7eab4ba387360a59dcf9d2aae745c30e97e4c20fd9d4118426f8135f53 +size 2824931296 diff --git a/gemma-2-9b-it-sppo-iter3-imat-IQ3_XXS.gguf b/gemma-2-9b-it-sppo-iter3-imat-IQ3_XXS.gguf new file mode 100644 index 0000000..68c946b --- /dev/null +++ b/gemma-2-9b-it-sppo-iter3-imat-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d57f04ef302ba5898cd562ad22655032baf86a2aeff548f4e0e31678e3524fc +size 3796740064 diff --git a/gemma-2-9b-it-sppo-iter3-imat-IQ4_XS.gguf b/gemma-2-9b-it-sppo-iter3-imat-IQ4_XS.gguf new file mode 100644 index 0000000..f29b865 --- /dev/null +++ b/gemma-2-9b-it-sppo-iter3-imat-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92780e82f3c667070b30cfb234a97c60a64ec7896465ad74e79f33d81d627320 +size 5183031264 diff --git a/gemma-2-9b-it-sppo-iter3-imat-Q4_K_L.gguf b/gemma-2-9b-it-sppo-iter3-imat-Q4_K_L.gguf new file mode 100644 index 0000000..12e2f71 --- /dev/null +++ b/gemma-2-9b-it-sppo-iter3-imat-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c584065aec30e0d7b8f3383043e9426833f8a45e4cb2940ba64c2868fa3b907c +size 6843426784 diff --git a/gemma-2-9b-it-sppo-iter3-imat-Q5_K_L.gguf b/gemma-2-9b-it-sppo-iter3-imat-Q5_K_L.gguf new file mode 100644 index 0000000..e0a1592 --- /dev/null +++ b/gemma-2-9b-it-sppo-iter3-imat-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ddbcf74f23a9cdc1e3c146b994e3199840454cf9a70f2b2ca40dd5e515f1f2 +size 7729735648 diff --git a/gemma-2-9b-it-sppo-iter3-imat-Q6_K_L.gguf b/gemma-2-9b-it-sppo-iter3-imat-Q6_K_L.gguf new file mode 100644 index 0000000..0896e1a --- /dev/null +++ b/gemma-2-9b-it-sppo-iter3-imat-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:113ca0927174bb22e04fbad7bdc8726bfaac8c5c0eb70b52300578d9ee26f8e8 +size 8671438816 diff --git a/gemma-2-9b-it-sppo-iter3-imat-Q8_0_L.gguf b/gemma-2-9b-it-sppo-iter3-imat-Q8_0_L.gguf new file mode 100644 index 0000000..cffd6f5 --- /dev/null +++ b/gemma-2-9b-it-sppo-iter3-imat-Q8_0_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcdab78578f0c08ab7e105b29634504002b8e5b3fe0e4a83dccf9f7de45df1e5 +size 10687309792 diff --git a/gemma-2-9b-it-sppo-iter3.imatrix b/gemma-2-9b-it-sppo-iter3.imatrix new file mode 100644 index 0000000..2ab4e34 --- /dev/null +++ b/gemma-2-9b-it-sppo-iter3.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ead9558c540026224a5a13848efd80656d71928a48579421ba6c704427793ea +size 6116920