commit 8c284a123805bef3987de5640979b3847d906d5a Author: ModelHub XC Date: Mon Sep 28 09:57:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..038a930 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +Co-rewarding-II-Qwen2.5-7B-MATH.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ1_M.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ1_M.gguf new file mode 100644 index 0000000..1936b89 --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16622314a3df38d4d0f027eee29cf08249b58e1ed5655aed6a83cb879d5da9d7 +size 2042196576 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ1_S.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ1_S.gguf new file mode 100644 index 0000000..c22c79f --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8473270fa4325cd53010c218ca9c18e88d1107282e06ea9b11bf836e521a2900 +size 1903667808 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_M.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_M.gguf new file mode 100644 index 0000000..4671862 --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ea1911c53968ae0bb4d912395ba274e9d960af8f05e70bbe9c8b8ba92fe81e +size 2780342880 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_S.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_S.gguf new file mode 100644 index 0000000..8fa582c --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d38970d582cf0bec91b286d67a6a8a336113ab913dae90c2b3c40cf2c9ac9bf8 +size 2595637856 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_XS.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_XS.gguf new file mode 100644 index 0000000..2fe93fd --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:170c816c0a2a13d290c8a5eae3c83d3fbe9b7d66a33c08c1a4a8af7e5997e3ba +size 2469022304 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_XXS.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..84be2c2 --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3b548f8160122892d059fbe1a35b613dd6fd4557d0e2310460011710120a3e1 +size 2273077856 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_M.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_M.gguf new file mode 100644 index 0000000..438f13b --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5756cf369ad7418b285e02fe98f0c3715222bc3a5cc0a7862a2945b669d3b08d +size 3574012512 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_S.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_S.gguf new file mode 100644 index 0000000..b1f0496 --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38895385f7920a1ba3d279fbe394efbc6b1e987387d79e694031cad673bcfb6e +size 3499192928 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_XS.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_XS.gguf new file mode 100644 index 0000000..103b9cf --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a23329a4272fa1da9b2872e14b2ebb3966a883b3f506ee2d9c1525447ae3f406 +size 3346256480 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_XXS.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..d631e6d --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1540ff29b6e2ce311e9ab2b658993d36b7e4f3c870f5869a60328ea1258d5fcc +size 3114515040 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ4_NL.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ4_NL.gguf new file mode 100644 index 0000000..4eda2e4 --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c20cc515af0cfe5349b4a8fd0debbdc1dd039fafe26ca63986991b4741baf81 +size 4437813856 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ4_XS.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ4_XS.gguf new file mode 100644 index 0000000..02e3a3f --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75622b6e7f9c2317493d24218e24e2c992d3f5fa145e97f71de94c875fca21e3 +size 4218473056 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q2_K.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q2_K.gguf new file mode 100644 index 0000000..6bc3e7e --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9fdc00a090124a6a869e9ae2a3929682c012617027cbfb63dd9ddaef3b0857b +size 3015940704 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q2_K_S.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q2_K_S.gguf new file mode 100644 index 0000000..f876174 --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2c68b67a475c8f28e500a01eb8e9d90dd1ab0903d88e6e942cf4ae36299ec6b +size 2834074208 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q3_K_L.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q3_K_L.gguf new file mode 100644 index 0000000..9bc2da2 --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b60238ea5e5929f0a071dd4cc2ed0afec8f261eb0e691641a0ce7dce57b072d +size 4088459872 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q3_K_M.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q3_K_M.gguf new file mode 100644 index 0000000..91cc0b5 --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f02d61a5da07e54121a6052d23ae945ad1491fee0301af27d2c1b6d043459a0 +size 3808391776 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q3_K_S.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q3_K_S.gguf new file mode 100644 index 0000000..1489d28 --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b57c8d7cd0247969ca5426dee6d444a660942505b6b6c8e7a7863b72fbcfb99 +size 3492368992 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_0.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_0.gguf new file mode 100644 index 0000000..8f19bb9 --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1c38fe0861a1158ec2c80de6455af836e17b2cc96a5a3b7492febedb13e8cc5 +size 4444121696 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_1.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_1.gguf new file mode 100644 index 0000000..a471ab8 --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:158b99a6b8f8d11cd80465f330c5c822cb281cddd027af002862ac273913f18b +size 4873284192 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_K_M.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_K_M.gguf new file mode 100644 index 0000000..09d139f --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b3da385a0531808e98e921a0885a30172c63c3cfeadf479400ece0936205326 +size 4683074144 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_K_S.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_K_S.gguf new file mode 100644 index 0000000..6bd2088 --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c96149981773c45060b1e93a240d24f111ec84dda15c221e7c1a4c114b335d5 +size 4457769568 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q5_K_M.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q5_K_M.gguf new file mode 100644 index 0000000..251eb7c --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c81d6cd5c26acce006a3eae7e28783dc20cb5eb437f46b5c253adf5d363b28e6 +size 5444831840 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q5_K_S.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q5_K_S.gguf new file mode 100644 index 0000000..8cdf524 --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a74f67d0bf3909f75cb0639b8d5a3eb40c8d79fbf57898a4005176cf5753cd5 +size 5315177056 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q6_K.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q6_K.gguf new file mode 100644 index 0000000..db80117 --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e9f6402878435d07b051fb7c6e2d36b0e4013dc5690fd3e5ba47c63e8888461 +size 6254199392 diff --git a/Co-rewarding-II-Qwen2.5-7B-MATH.imatrix.gguf b/Co-rewarding-II-Qwen2.5-7B-MATH.imatrix.gguf new file mode 100644 index 0000000..df1dbda --- /dev/null +++ b/Co-rewarding-II-Qwen2.5-7B-MATH.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f860ad0ba26fbeda08cee6a69ba4bd33949da12aed138a3e7875805655f1905 +size 4560352 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5017ac1 --- /dev/null +++ b/README.md @@ -0,0 +1,85 @@ +--- +base_model: TMLR-Group-HF/Co-rewarding-II-Qwen2.5-7B-MATH +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/TMLR-Group-HF/Co-rewarding-II-Qwen2.5-7B-MATH + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-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/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Co-rewarding-II-Qwen2.5-7B-MATH-i1-GGUF/resolve/main/Co-rewarding-II-Qwen2.5-7B-MATH.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | practically like static Q6_K | + +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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +