commit 1d3bd1ab7d1c957c2a816f2af6707d74a23899be Author: ModelHub XC Date: Sun Jun 14 16:52:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gemma-2-9b-it-WPO-HB-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2c310b7 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-WPO-HB.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-WPO-HB.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-WPO-HB.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-WPO-HB.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-WPO-HB.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-WPO-HB.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-WPO-HB.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-WPO-HB.f16.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-WPO-HB.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-WPO-HB.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-WPO-HB.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-WPO-HB.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-WPO-HB.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-WPO-HB.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +gemma-2-9b-it-WPO-HB.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..cd5f0d7 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: wzhouad/gemma-2-9b-it-WPO-HB +datasets: +- wzhouad/gemma-2-ultrafeedback-hybrid +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- alignment-handbook +- gemma +--- +## About + + + + + + +static quants of https://huggingface.co/wzhouad/gemma-2-9b-it-WPO-HB + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/gemma-2-9b-it-WPO-HB-i1-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-WPO-HB-GGUF/resolve/main/gemma-2-9b-it-WPO-HB.Q2_K.gguf) | Q2_K | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-WPO-HB-GGUF/resolve/main/gemma-2-9b-it-WPO-HB.IQ3_XS.gguf) | IQ3_XS | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-WPO-HB-GGUF/resolve/main/gemma-2-9b-it-WPO-HB.IQ3_S.gguf) | IQ3_S | 4.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-WPO-HB-GGUF/resolve/main/gemma-2-9b-it-WPO-HB.Q3_K_S.gguf) | Q3_K_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-WPO-HB-GGUF/resolve/main/gemma-2-9b-it-WPO-HB.IQ3_M.gguf) | IQ3_M | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-WPO-HB-GGUF/resolve/main/gemma-2-9b-it-WPO-HB.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-WPO-HB-GGUF/resolve/main/gemma-2-9b-it-WPO-HB.Q3_K_L.gguf) | Q3_K_L | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-WPO-HB-GGUF/resolve/main/gemma-2-9b-it-WPO-HB.IQ4_XS.gguf) | IQ4_XS | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-WPO-HB-GGUF/resolve/main/gemma-2-9b-it-WPO-HB.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-WPO-HB-GGUF/resolve/main/gemma-2-9b-it-WPO-HB.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-WPO-HB-GGUF/resolve/main/gemma-2-9b-it-WPO-HB.Q5_K_S.gguf) | Q5_K_S | 6.6 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-WPO-HB-GGUF/resolve/main/gemma-2-9b-it-WPO-HB.Q5_K_M.gguf) | Q5_K_M | 6.7 | | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-WPO-HB-GGUF/resolve/main/gemma-2-9b-it-WPO-HB.Q6_K.gguf) | Q6_K | 7.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-WPO-HB-GGUF/resolve/main/gemma-2-9b-it-WPO-HB.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-WPO-HB-GGUF/resolve/main/gemma-2-9b-it-WPO-HB.f16.gguf) | f16 | 18.6 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + + diff --git a/gemma-2-9b-it-WPO-HB.IQ3_M.gguf b/gemma-2-9b-it-WPO-HB.IQ3_M.gguf new file mode 100644 index 0000000..e965df1 --- /dev/null +++ b/gemma-2-9b-it-WPO-HB.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abb1e2b103af5a06cb985770642443ec96db89120514222c8068d8e011b308f2 +size 4494616000 diff --git a/gemma-2-9b-it-WPO-HB.IQ3_S.gguf b/gemma-2-9b-it-WPO-HB.IQ3_S.gguf new file mode 100644 index 0000000..3083991 --- /dev/null +++ b/gemma-2-9b-it-WPO-HB.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:877f35ce7dc4245b34e24cab8f8040089bbd04e355976a1a91b734cb95dd1ae8 +size 4337665472 diff --git a/gemma-2-9b-it-WPO-HB.IQ3_XS.gguf b/gemma-2-9b-it-WPO-HB.IQ3_XS.gguf new file mode 100644 index 0000000..b7cfa5b --- /dev/null +++ b/gemma-2-9b-it-WPO-HB.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:112f1a294c3bb5afc0776dca4d450085814bb099dc574473915ad1e3ff74124d +size 4144989632 diff --git a/gemma-2-9b-it-WPO-HB.IQ4_XS.gguf b/gemma-2-9b-it-WPO-HB.IQ4_XS.gguf new file mode 100644 index 0000000..d9b0646 --- /dev/null +++ b/gemma-2-9b-it-WPO-HB.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afcca084876cbe4f87b2096ecc69adafc745cedf007b145ceb227485e6245791 +size 5223171520 diff --git a/gemma-2-9b-it-WPO-HB.Q2_K.gguf b/gemma-2-9b-it-WPO-HB.Q2_K.gguf new file mode 100644 index 0000000..37d5ba3 --- /dev/null +++ b/gemma-2-9b-it-WPO-HB.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25112e01d7fda41ded0ee9220d65653a77bd9244c29b1f5fb2609564e02f6be7 +size 3805398464 diff --git a/gemma-2-9b-it-WPO-HB.Q3_K_L.gguf b/gemma-2-9b-it-WPO-HB.Q3_K_L.gguf new file mode 100644 index 0000000..85eba1f --- /dev/null +++ b/gemma-2-9b-it-WPO-HB.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fed79de619cead92d0c1d00d1b1853c62c41c5a3d809b6aa562fcf460b8a0455 +size 5132453312 diff --git a/gemma-2-9b-it-WPO-HB.Q3_K_M.gguf b/gemma-2-9b-it-WPO-HB.Q3_K_M.gguf new file mode 100644 index 0000000..deb50ee --- /dev/null +++ b/gemma-2-9b-it-WPO-HB.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75a16ebec61f4cc57dc007e5d53fdb3d27380aace7fc84aa5a1709bc645c9b7e +size 4761781696 diff --git a/gemma-2-9b-it-WPO-HB.Q3_K_S.gguf b/gemma-2-9b-it-WPO-HB.Q3_K_S.gguf new file mode 100644 index 0000000..7c4b08e --- /dev/null +++ b/gemma-2-9b-it-WPO-HB.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a19aa5fe5068635a95d32e92a9dc0eb803fdb443f96c09d7eb8865e8b54635f +size 4337665472 diff --git a/gemma-2-9b-it-WPO-HB.Q4_K_M.gguf b/gemma-2-9b-it-WPO-HB.Q4_K_M.gguf new file mode 100644 index 0000000..daf99dd --- /dev/null +++ b/gemma-2-9b-it-WPO-HB.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f366c8acf2bfc37c1f40328ed0dc9ede028bfd5941257684d616c025957c0e24 +size 5761058240 diff --git a/gemma-2-9b-it-WPO-HB.Q4_K_S.gguf b/gemma-2-9b-it-WPO-HB.Q4_K_S.gguf new file mode 100644 index 0000000..d17851b --- /dev/null +++ b/gemma-2-9b-it-WPO-HB.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d34b9e8f34c900d71c7f62e3a7ac05879299f0ad7fba9ba8a802f24bffdc479 +size 5478925760 diff --git a/gemma-2-9b-it-WPO-HB.Q5_K_M.gguf b/gemma-2-9b-it-WPO-HB.Q5_K_M.gguf new file mode 100644 index 0000000..d6f6027 --- /dev/null +++ b/gemma-2-9b-it-WPO-HB.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d1b19798a7a5f3385e92f8e1743b0878180df7613e474f95b9ccae576c2ea90 +size 6647367104 diff --git a/gemma-2-9b-it-WPO-HB.Q5_K_S.gguf b/gemma-2-9b-it-WPO-HB.Q5_K_S.gguf new file mode 100644 index 0000000..9cb7a4e --- /dev/null +++ b/gemma-2-9b-it-WPO-HB.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e7769614a7beb200c47807dd8fc4fdfbf51aa03fbd0c5573b8b97be017e2284 +size 6483592640 diff --git a/gemma-2-9b-it-WPO-HB.Q6_K.gguf b/gemma-2-9b-it-WPO-HB.Q6_K.gguf new file mode 100644 index 0000000..24b04d4 --- /dev/null +++ b/gemma-2-9b-it-WPO-HB.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3700add23ce06859ddfae27be76ff1c341efd8f899e12452d40e927db8bf30a3 +size 7589070272 diff --git a/gemma-2-9b-it-WPO-HB.Q8_0.gguf b/gemma-2-9b-it-WPO-HB.Q8_0.gguf new file mode 100644 index 0000000..18d308c --- /dev/null +++ b/gemma-2-9b-it-WPO-HB.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:061e0a56498eb0b6b4864699f4bb81ccd02f0cd984bd10fed6293e2ee21c7686 +size 9827149248 diff --git a/gemma-2-9b-it-WPO-HB.f16.gguf b/gemma-2-9b-it-WPO-HB.f16.gguf new file mode 100644 index 0000000..64b3155 --- /dev/null +++ b/gemma-2-9b-it-WPO-HB.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b415292513a3886d6df7d4f97301dba299af76fa290b397fcbe3bcb637244f9 +size 18490680768