commit 2612695929eb48b343b04426b76ecef1a615b1d7 Author: ModelHub XC Date: Mon Jul 20 03:24:11 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-ARPO-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fb848fe --- /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 +Qwen2.5-7B-ARPO.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-ARPO.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-ARPO.i1-IQ1_M.gguf b/Qwen2.5-7B-ARPO.i1-IQ1_M.gguf new file mode 100644 index 0000000..6c9165a --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e8761ece984fca1d40bb11255e160dbfa84e8f18efba23280e04bbaae17a760 +size 2256149952 diff --git a/Qwen2.5-7B-ARPO.i1-IQ1_S.gguf b/Qwen2.5-7B-ARPO.i1-IQ1_S.gguf new file mode 100644 index 0000000..cc9cef7 --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86a5afa2b1fe5556b943ddcaf47819b41fd2f34918796e2024954311d9cc1cc8 +size 2115771840 diff --git a/Qwen2.5-7B-ARPO.i1-IQ2_M.gguf b/Qwen2.5-7B-ARPO.i1-IQ2_M.gguf new file mode 100644 index 0000000..1734b6d --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d01d84ec17b10e9b32f82aaa68d62a28efcbf8d0347fe854cd2ed085b5fc0540 +size 3051916736 diff --git a/Qwen2.5-7B-ARPO.i1-IQ2_S.gguf b/Qwen2.5-7B-ARPO.i1-IQ2_S.gguf new file mode 100644 index 0000000..f8d2020 --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70bd4e537b625967c6e0b7f2ef83b95e1079458caceffa7608ab086fd0966ee0 +size 2864745920 diff --git a/Qwen2.5-7B-ARPO.i1-IQ2_XS.gguf b/Qwen2.5-7B-ARPO.i1-IQ2_XS.gguf new file mode 100644 index 0000000..5cedf2e --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ea55b141227c981deda0caccfc32c36775ae99572578455f6ce52838bb533f1 +size 2696158656 diff --git a/Qwen2.5-7B-ARPO.i1-IQ2_XXS.gguf b/Qwen2.5-7B-ARPO.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..8985a2b --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df5ce1cc7e05f3cc2ea22013d1ab11a47a1e062573b36d1f200901c39a1b7262 +size 2490113472 diff --git a/Qwen2.5-7B-ARPO.i1-IQ3_M.gguf b/Qwen2.5-7B-ARPO.i1-IQ3_M.gguf new file mode 100644 index 0000000..1c0c1d9 --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a7550f4180f78dc18ac77bcb914c2d9eff70c4892f95b22044f4e6b84aba8dd +size 3896622528 diff --git a/Qwen2.5-7B-ARPO.i1-IQ3_S.gguf b/Qwen2.5-7B-ARPO.i1-IQ3_S.gguf new file mode 100644 index 0000000..99f7f5c --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59ddac9a5761aba94fda66a915bafb7a8f963a506455f0645cfa140f4dff7f33 +size 3789667776 diff --git a/Qwen2.5-7B-ARPO.i1-IQ3_XS.gguf b/Qwen2.5-7B-ARPO.i1-IQ3_XS.gguf new file mode 100644 index 0000000..406b46e --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:392fd9c28a49eee9085d1c144a611c13896c39288b672647d2097bf9f4eb7e29 +size 3626876352 diff --git a/Qwen2.5-7B-ARPO.i1-IQ3_XXS.gguf b/Qwen2.5-7B-ARPO.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..0e9257e --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a969949d22583dae75749e1a0c667ded083da7042a6d1a77d12f71c4b9739ed9 +size 3369635264 diff --git a/Qwen2.5-7B-ARPO.i1-IQ4_NL.gguf b/Qwen2.5-7B-ARPO.i1-IQ4_NL.gguf new file mode 100644 index 0000000..4346dac --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a32c3589fb529aaf8b0404682c7bc9a311e7f1725332da39883801b0a430fbf3 +size 4793626048 diff --git a/Qwen2.5-7B-ARPO.i1-IQ4_XS.gguf b/Qwen2.5-7B-ARPO.i1-IQ4_XS.gguf new file mode 100644 index 0000000..8c97727 --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af7416d3e1e6692b7529e6f010ee5c79f86128cd8c40ac8cb34643b9242eb1e2 +size 4561841600 diff --git a/Qwen2.5-7B-ARPO.i1-Q2_K.gguf b/Qwen2.5-7B-ARPO.i1-Q2_K.gguf new file mode 100644 index 0000000..3a63026 --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2cc3b9e9b90f3b22dd13af0fd397ad4125e8d14f08c221b4a5a46fe71f390b2 +size 3281735104 diff --git a/Qwen2.5-7B-ARPO.i1-Q2_K_S.gguf b/Qwen2.5-7B-ARPO.i1-Q2_K_S.gguf new file mode 100644 index 0000000..522089e --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6857eb8cec2c618a8e6bb751768137d1a6c1d94dcb8d2b278c2cb1486ccff4d9 +size 3083554240 diff --git a/Qwen2.5-7B-ARPO.i1-Q3_K_L.gguf b/Qwen2.5-7B-ARPO.i1-Q3_K_L.gguf new file mode 100644 index 0000000..11967ab --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:011f57e5f84c1cdf6f67cf84a2f7aa100f4cd5fedaf490a2a9a12c42ce802265 +size 4431396288 diff --git a/Qwen2.5-7B-ARPO.i1-Q3_K_M.gguf b/Qwen2.5-7B-ARPO.i1-Q3_K_M.gguf new file mode 100644 index 0000000..6dee2d6 --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29f9014afdaf9b354ef8de3f1ac1a6c198fc4523781fe5fffe00663d1f3a2993 +size 4124163520 diff --git a/Qwen2.5-7B-ARPO.i1-Q3_K_S.gguf b/Qwen2.5-7B-ARPO.i1-Q3_K_S.gguf new file mode 100644 index 0000000..946b20d --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1e7673453fffef259140702858a2c9394f81d2098efd2fceeac2ff850942766 +size 3769613760 diff --git a/Qwen2.5-7B-ARPO.i1-Q4_0.gguf b/Qwen2.5-7B-ARPO.i1-Q4_0.gguf new file mode 100644 index 0000000..cbc8dac --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24cfcfa2c930f80771966ad8bfd60679c87c1cc79da1ef2d4c727e1615ef9d0b +size 4787334592 diff --git a/Qwen2.5-7B-ARPO.i1-Q4_1.gguf b/Qwen2.5-7B-ARPO.i1-Q4_1.gguf new file mode 100644 index 0000000..75263e5 --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a32413b9c26dba81af414a27c8e0c1e013943794afa60ec14fc9199da944afe +size 5247757760 diff --git a/Qwen2.5-7B-ARPO.i1-Q4_K_M.gguf b/Qwen2.5-7B-ARPO.i1-Q4_K_M.gguf new file mode 100644 index 0000000..82eb01f --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:445774cb24b44095cfda973b45282030e83efab9d6c2cf5cd250c97f9ca1eba0 +size 5027786176 diff --git a/Qwen2.5-7B-ARPO.i1-Q4_K_S.gguf b/Qwen2.5-7B-ARPO.i1-Q4_K_S.gguf new file mode 100644 index 0000000..6f72fd5 --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00896988033d9cc31378bc01f0c23971d56352051f8baf86f24d4600b4ffd802 +size 4802014656 diff --git a/Qwen2.5-7B-ARPO.i1-Q5_K_M.gguf b/Qwen2.5-7B-ARPO.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f222202 --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d79f09d62edc10a2d4306b38c3ec75689c9957eb1876f464153a5d5aa6ef79d6 +size 5851114944 diff --git a/Qwen2.5-7B-ARPO.i1-Q5_K_S.gguf b/Qwen2.5-7B-ARPO.i1-Q5_K_S.gguf new file mode 100644 index 0000000..a72c593 --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19846031c11c431740f7c5e8d5d5cc095ae071d582c226dbd3b3d8f506b00954 +size 5720763840 diff --git a/Qwen2.5-7B-ARPO.i1-Q6_K.gguf b/Qwen2.5-7B-ARPO.i1-Q6_K.gguf new file mode 100644 index 0000000..a037e45 --- /dev/null +++ b/Qwen2.5-7B-ARPO.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ee6ea420762645255b376cc1a42a4bb99af14c6c2282e206b63e05c66bad343 +size 6725901760 diff --git a/Qwen2.5-7B-ARPO.imatrix.gguf b/Qwen2.5-7B-ARPO.imatrix.gguf new file mode 100644 index 0000000..1d35a57 --- /dev/null +++ b/Qwen2.5-7B-ARPO.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6d2c7939f4ae764c7e33fea46a2f19384371e70b91ffa871c29db7f8d451915 +size 5347200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dbe6f83 --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: dongguanting/Qwen2.5-7B-ARPO +datasets: +- dongguanting/ARPO-SFT-54K +- dongguanting/ARPO-RL-Reasoning-10K +- dongguanting/ARPO-RL-DeepSearch-1K +language: en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/dongguanting/Qwen2.5-7B-ARPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-7B-ARPO-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-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/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-IQ1_S.gguf) | i1-IQ1_S | 2.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-IQ1_M.gguf) | i1-IQ1_M | 2.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-IQ2_S.gguf) | i1-IQ2_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-Q2_K.gguf) | i1-Q2_K | 3.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-IQ3_S.gguf) | i1-IQ3_S | 3.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-IQ3_M.gguf) | i1-IQ3_M | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-Q4_0.gguf) | i1-Q4_0 | 4.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-Q4_1.gguf) | i1-Q4_1 | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-ARPO-i1-GGUF/resolve/main/Qwen2.5-7B-ARPO.i1-Q6_K.gguf) | i1-Q6_K | 6.8 | 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. + +