commit 957b0bf94e1235dc7f0cb74eb86b87aef6ae6f7a Author: ModelHub XC Date: Sat Sep 5 23:24:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OpenR1-Qwen-7B-SFT2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3d9ae8f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +OpenR1-Qwen-7B-SFT2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-SFT2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-SFT2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-SFT2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-SFT2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-SFT2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-SFT2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-SFT2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-SFT2.f16.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-SFT2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-SFT2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenR1-Qwen-7B-SFT2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenR1-Qwen-7B-SFT2.IQ4_XS.gguf b/OpenR1-Qwen-7B-SFT2.IQ4_XS.gguf new file mode 100644 index 0000000..ffee3c3 --- /dev/null +++ b/OpenR1-Qwen-7B-SFT2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b90d48e8af2547f94e8b5f3d31dcff6b40987c122e3801fa943c4b09a82b1da +size 4250298720 diff --git a/OpenR1-Qwen-7B-SFT2.Q2_K.gguf b/OpenR1-Qwen-7B-SFT2.Q2_K.gguf new file mode 100644 index 0000000..015af7b --- /dev/null +++ b/OpenR1-Qwen-7B-SFT2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a810c4b1dfdd23ca44ab9fbc3d2718647fa71a44a9217e99ff10d121e7ac972 +size 3015940448 diff --git a/OpenR1-Qwen-7B-SFT2.Q3_K_L.gguf b/OpenR1-Qwen-7B-SFT2.Q3_K_L.gguf new file mode 100644 index 0000000..60232cb --- /dev/null +++ b/OpenR1-Qwen-7B-SFT2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b34e4b1f9cdda388169884111fe9315db60e36ea96d62806bc4db97edf2ab12c +size 4088459616 diff --git a/OpenR1-Qwen-7B-SFT2.Q3_K_M.gguf b/OpenR1-Qwen-7B-SFT2.Q3_K_M.gguf new file mode 100644 index 0000000..e412c0e --- /dev/null +++ b/OpenR1-Qwen-7B-SFT2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46a4ed6b453fe5276cb0a006e77234f564a2b080df0fc8027e5526faef49379b +size 3808391520 diff --git a/OpenR1-Qwen-7B-SFT2.Q3_K_S.gguf b/OpenR1-Qwen-7B-SFT2.Q3_K_S.gguf new file mode 100644 index 0000000..5a95322 --- /dev/null +++ b/OpenR1-Qwen-7B-SFT2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:242590b8cc4c4a722e7ea1f8bf472cda75a290efd94f8e9313ee4726aa922e64 +size 3492368736 diff --git a/OpenR1-Qwen-7B-SFT2.Q4_K_M.gguf b/OpenR1-Qwen-7B-SFT2.Q4_K_M.gguf new file mode 100644 index 0000000..e517e58 --- /dev/null +++ b/OpenR1-Qwen-7B-SFT2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d729543642a933efd96b95179b44f6940b3120b4d275b2247e403071d74c96e +size 4683073888 diff --git a/OpenR1-Qwen-7B-SFT2.Q4_K_S.gguf b/OpenR1-Qwen-7B-SFT2.Q4_K_S.gguf new file mode 100644 index 0000000..66e362a --- /dev/null +++ b/OpenR1-Qwen-7B-SFT2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f95b88ca4e6436cb9963efc872aefe4cd79da197eebeea31390971e452f0561 +size 4457769312 diff --git a/OpenR1-Qwen-7B-SFT2.Q5_K_M.gguf b/OpenR1-Qwen-7B-SFT2.Q5_K_M.gguf new file mode 100644 index 0000000..a79ad00 --- /dev/null +++ b/OpenR1-Qwen-7B-SFT2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b6e0d9f9d71e2114ad974e642d7f9b2ab8c5e4a66e11eb2a0aaff61f5a946dd +size 5444831584 diff --git a/OpenR1-Qwen-7B-SFT2.Q5_K_S.gguf b/OpenR1-Qwen-7B-SFT2.Q5_K_S.gguf new file mode 100644 index 0000000..4cc0d68 --- /dev/null +++ b/OpenR1-Qwen-7B-SFT2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe1cc70a8b91a801988a45b12ffd7b8022bb0ad29e16e4d644df1e70daa7ee16 +size 5315176800 diff --git a/OpenR1-Qwen-7B-SFT2.Q6_K.gguf b/OpenR1-Qwen-7B-SFT2.Q6_K.gguf new file mode 100644 index 0000000..f1db61b --- /dev/null +++ b/OpenR1-Qwen-7B-SFT2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e7cb60b0fffb957e6674e7c91116918338cdb035864a9330354ed80e5defdbd +size 6254199136 diff --git a/OpenR1-Qwen-7B-SFT2.Q8_0.gguf b/OpenR1-Qwen-7B-SFT2.Q8_0.gguf new file mode 100644 index 0000000..61b96f8 --- /dev/null +++ b/OpenR1-Qwen-7B-SFT2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90e6651f398be92a6073401992889d7a859432b18515a016e4071f42f485cf94 +size 8098525536 diff --git a/OpenR1-Qwen-7B-SFT2.f16.gguf b/OpenR1-Qwen-7B-SFT2.f16.gguf new file mode 100644 index 0000000..1ee4f24 --- /dev/null +++ b/OpenR1-Qwen-7B-SFT2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28c81a645f99aef90d2d4a61712170d1da8f61376fb53b21dc0b6bafd557f6f6 +size 15237853536 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ff8d0a3 --- /dev/null +++ b/README.md @@ -0,0 +1,63 @@ +--- +base_model: ZMC2019/OpenR1-Qwen-7B-SFT2 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/ZMC2019/OpenR1-Qwen-7B-SFT2 + + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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/OpenR1-Qwen-7B-SFT2-GGUF/resolve/main/OpenR1-Qwen-7B-SFT2.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-SFT2-GGUF/resolve/main/OpenR1-Qwen-7B-SFT2.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-SFT2-GGUF/resolve/main/OpenR1-Qwen-7B-SFT2.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-SFT2-GGUF/resolve/main/OpenR1-Qwen-7B-SFT2.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-SFT2-GGUF/resolve/main/OpenR1-Qwen-7B-SFT2.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-SFT2-GGUF/resolve/main/OpenR1-Qwen-7B-SFT2.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-SFT2-GGUF/resolve/main/OpenR1-Qwen-7B-SFT2.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-SFT2-GGUF/resolve/main/OpenR1-Qwen-7B-SFT2.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-SFT2-GGUF/resolve/main/OpenR1-Qwen-7B-SFT2.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-SFT2-GGUF/resolve/main/OpenR1-Qwen-7B-SFT2.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-SFT2-GGUF/resolve/main/OpenR1-Qwen-7B-SFT2.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OpenR1-Qwen-7B-SFT2-GGUF/resolve/main/OpenR1-Qwen-7B-SFT2.f16.gguf) | f16 | 15.3 | 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. + +