commit d8e37abac35305ecd196d4819fa20e8b7b72ca8a Author: ModelHub XC Date: Sat Aug 8 08:39:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/gpt-oss-2.5B-A1.3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6c4de40 --- /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 +gpt-oss-2.5B-A1.3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-2.5B-A1.3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-2.5B-A1.3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-2.5B-A1.3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-2.5B-A1.3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-2.5B-A1.3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-2.5B-A1.3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-2.5B-A1.3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-2.5B-A1.3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-2.5B-A1.3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-2.5B-A1.3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +gpt-oss-2.5B-A1.3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4088bb8 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: inference-optimization/gpt-oss-2.5B-A1.3B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/inference-optimization/gpt-oss-2.5B-A1.3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gpt-oss-2.5B-A1.3B-GGUF).*** + +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/gpt-oss-2.5B-A1.3B-GGUF/resolve/main/gpt-oss-2.5B-A1.3B.IQ4_XS.gguf) | IQ4_XS | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-2.5B-A1.3B-GGUF/resolve/main/gpt-oss-2.5B-A1.3B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-2.5B-A1.3B-GGUF/resolve/main/gpt-oss-2.5B-A1.3B.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-2.5B-A1.3B-GGUF/resolve/main/gpt-oss-2.5B-A1.3B.Q3_K_M.gguf) | Q3_K_M | 1.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-2.5B-A1.3B-GGUF/resolve/main/gpt-oss-2.5B-A1.3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-2.5B-A1.3B-GGUF/resolve/main/gpt-oss-2.5B-A1.3B.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-2.5B-A1.3B-GGUF/resolve/main/gpt-oss-2.5B-A1.3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-2.5B-A1.3B-GGUF/resolve/main/gpt-oss-2.5B-A1.3B.Q5_K_S.gguf) | Q5_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-2.5B-A1.3B-GGUF/resolve/main/gpt-oss-2.5B-A1.3B.Q5_K_M.gguf) | Q5_K_M | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-2.5B-A1.3B-GGUF/resolve/main/gpt-oss-2.5B-A1.3B.Q6_K.gguf) | Q6_K | 2.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-2.5B-A1.3B-GGUF/resolve/main/gpt-oss-2.5B-A1.3B.Q8_0.gguf) | Q8_0 | 2.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/gpt-oss-2.5B-A1.3B-GGUF/resolve/main/gpt-oss-2.5B-A1.3B.f16.gguf) | f16 | 5.1 | 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/gpt-oss-2.5B-A1.3B.IQ4_XS.gguf b/gpt-oss-2.5B-A1.3B.IQ4_XS.gguf new file mode 100644 index 0000000..e04ccda --- /dev/null +++ b/gpt-oss-2.5B-A1.3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dfea0bea97e2a4bd9be38fb02133f5b0809e9058d037c3c4be274e4c0a01214 +size 1735753952 diff --git a/gpt-oss-2.5B-A1.3B.Q2_K.gguf b/gpt-oss-2.5B-A1.3B.Q2_K.gguf new file mode 100644 index 0000000..a625c79 --- /dev/null +++ b/gpt-oss-2.5B-A1.3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d3b7de7b98900f5022625797422fbc8ab6fd6da935ae731189b218525c3a810 +size 1735753952 diff --git a/gpt-oss-2.5B-A1.3B.Q3_K_L.gguf b/gpt-oss-2.5B-A1.3B.Q3_K_L.gguf new file mode 100644 index 0000000..9d783f4 --- /dev/null +++ b/gpt-oss-2.5B-A1.3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2e40c8677f134c6a8a0765e4643e05fd9365cc418f77f67e47c4be1a5faabb1 +size 1792155872 diff --git a/gpt-oss-2.5B-A1.3B.Q3_K_M.gguf b/gpt-oss-2.5B-A1.3B.Q3_K_M.gguf new file mode 100644 index 0000000..0087cc8 --- /dev/null +++ b/gpt-oss-2.5B-A1.3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da768fdafc7e2698e5eacf7a47caa5d4c1c4c63ca00a6c48ae5b980c2a629738 +size 1785520352 diff --git a/gpt-oss-2.5B-A1.3B.Q3_K_S.gguf b/gpt-oss-2.5B-A1.3B.Q3_K_S.gguf new file mode 100644 index 0000000..d3b596e --- /dev/null +++ b/gpt-oss-2.5B-A1.3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:565eeedc2e2322c40c84b4c3a58efab7b06bb74aedd9e5fabf25864705f1001a +size 1735753952 diff --git a/gpt-oss-2.5B-A1.3B.Q4_K_M.gguf b/gpt-oss-2.5B-A1.3B.Q4_K_M.gguf new file mode 100644 index 0000000..9d146c8 --- /dev/null +++ b/gpt-oss-2.5B-A1.3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa3dc2b9d5d2a7de3f06d0523020f2f4cf4dd4a94faf349c60dbd5c794e1b15b +size 2016058592 diff --git a/gpt-oss-2.5B-A1.3B.Q4_K_S.gguf b/gpt-oss-2.5B-A1.3B.Q4_K_S.gguf new file mode 100644 index 0000000..39919f2 --- /dev/null +++ b/gpt-oss-2.5B-A1.3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b555b37d3c2063f7176c42fa35f97561d4f29cc77f5f27e119bfe258d5f0da23 +size 1966292192 diff --git a/gpt-oss-2.5B-A1.3B.Q5_K_M.gguf b/gpt-oss-2.5B-A1.3B.Q5_K_M.gguf new file mode 100644 index 0000000..da4201f --- /dev/null +++ b/gpt-oss-2.5B-A1.3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beb186bd3f58d30d12030b27f5acc85eced8c342fe6f4c15ac4cefd6ae64db43 +size 2123033312 diff --git a/gpt-oss-2.5B-A1.3B.Q5_K_S.gguf b/gpt-oss-2.5B-A1.3B.Q5_K_S.gguf new file mode 100644 index 0000000..8dd8ad6 --- /dev/null +++ b/gpt-oss-2.5B-A1.3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:267cb508f87c2e2a2bbc336c74fa86f104320889f6b5b872bc56dbf711d01607 +size 2081561312 diff --git a/gpt-oss-2.5B-A1.3B.Q6_K.gguf b/gpt-oss-2.5B-A1.3B.Q6_K.gguf new file mode 100644 index 0000000..687f9f6 --- /dev/null +++ b/gpt-oss-2.5B-A1.3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d002d2b2149d4d1068e80f6b2a0c3b07b88f93140bc0fd557b8e648d409ac524 +size 2667307232 diff --git a/gpt-oss-2.5B-A1.3B.Q8_0.gguf b/gpt-oss-2.5B-A1.3B.Q8_0.gguf new file mode 100644 index 0000000..8211b69 --- /dev/null +++ b/gpt-oss-2.5B-A1.3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e3bcc0a7764e69ed5b1e4c28fc318ece8a6996dd384d8da975e013139963d9f +size 2684448992 diff --git a/gpt-oss-2.5B-A1.3B.f16.gguf b/gpt-oss-2.5B-A1.3B.f16.gguf new file mode 100644 index 0000000..b716fb4 --- /dev/null +++ b/gpt-oss-2.5B-A1.3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a1d696dd4b5e22dd2c86ffac8ffb41ca3bdf5ce7f732682aa94b50170eff47f +size 5039367392