commit 3a43e7d1454d280db8bc09d1ef7c78b743025dcd Author: ModelHub XC Date: Sun May 10 08:10:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OctoThinker-3B-Hybrid-Base-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..59433d3 --- /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 +OctoThinker-3B-Hybrid-Base.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Hybrid-Base.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Hybrid-Base.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Hybrid-Base.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Hybrid-Base.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Hybrid-Base.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Hybrid-Base.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Hybrid-Base.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Hybrid-Base.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Hybrid-Base.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Hybrid-Base.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OctoThinker-3B-Hybrid-Base.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OctoThinker-3B-Hybrid-Base.IQ4_XS.gguf b/OctoThinker-3B-Hybrid-Base.IQ4_XS.gguf new file mode 100644 index 0000000..afa4505 --- /dev/null +++ b/OctoThinker-3B-Hybrid-Base.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f1e6a5c6be124efcc316aef6e803032a8ef3a433f21dbc354566587510ca33e +size 1840903776 diff --git a/OctoThinker-3B-Hybrid-Base.Q2_K.gguf b/OctoThinker-3B-Hybrid-Base.Q2_K.gguf new file mode 100644 index 0000000..44dce3d --- /dev/null +++ b/OctoThinker-3B-Hybrid-Base.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:612421332932d88f1c45adbaff724d646ef56ede572c5357f2859551b207eef0 +size 1363932768 diff --git a/OctoThinker-3B-Hybrid-Base.Q3_K_L.gguf b/OctoThinker-3B-Hybrid-Base.Q3_K_L.gguf new file mode 100644 index 0000000..a111df7 --- /dev/null +++ b/OctoThinker-3B-Hybrid-Base.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4013ec614f8c099b68b0d5e0d208290d9bc01f039cf1577b96144bbf2deb803 +size 1815344736 diff --git a/OctoThinker-3B-Hybrid-Base.Q3_K_M.gguf b/OctoThinker-3B-Hybrid-Base.Q3_K_M.gguf new file mode 100644 index 0000000..c38a559 --- /dev/null +++ b/OctoThinker-3B-Hybrid-Base.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e60fb301cf8fa8a4b9f4e78acd7966f39525823d20b13d59fbbdceb1d5339cea +size 1687156320 diff --git a/OctoThinker-3B-Hybrid-Base.Q3_K_S.gguf b/OctoThinker-3B-Hybrid-Base.Q3_K_S.gguf new file mode 100644 index 0000000..f2144b4 --- /dev/null +++ b/OctoThinker-3B-Hybrid-Base.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d2975893989d1f78c9d2a6dd514f42e12c91452e5b984f154b7ad26a70f5df7 +size 1542846048 diff --git a/OctoThinker-3B-Hybrid-Base.Q4_K_M.gguf b/OctoThinker-3B-Hybrid-Base.Q4_K_M.gguf new file mode 100644 index 0000000..2a2a5d7 --- /dev/null +++ b/OctoThinker-3B-Hybrid-Base.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daa8ea449e88a41ab960fdee79ff3903c919c09a76eff2282638aacefeaa0710 +size 2019374688 diff --git a/OctoThinker-3B-Hybrid-Base.Q4_K_S.gguf b/OctoThinker-3B-Hybrid-Base.Q4_K_S.gguf new file mode 100644 index 0000000..f861a47 --- /dev/null +++ b/OctoThinker-3B-Hybrid-Base.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c60566bbab0efdbc4930868aaddc25d9cc16a3430024373850ab8a26f7c8e51d +size 1928197728 diff --git a/OctoThinker-3B-Hybrid-Base.Q5_K_M.gguf b/OctoThinker-3B-Hybrid-Base.Q5_K_M.gguf new file mode 100644 index 0000000..1f2b672 --- /dev/null +++ b/OctoThinker-3B-Hybrid-Base.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7ce7acf05b33dc6a2b7c56510c6657840ba2ba99c3ecaa29d9e28c3961ffedf +size 2322151008 diff --git a/OctoThinker-3B-Hybrid-Base.Q5_K_S.gguf b/OctoThinker-3B-Hybrid-Base.Q5_K_S.gguf new file mode 100644 index 0000000..84e2f39 --- /dev/null +++ b/OctoThinker-3B-Hybrid-Base.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c4aa8c0d098d2f685956c817f1edfc04f8a1dd0cfa8da4f7d18a71247bf453a +size 2269509216 diff --git a/OctoThinker-3B-Hybrid-Base.Q6_K.gguf b/OctoThinker-3B-Hybrid-Base.Q6_K.gguf new file mode 100644 index 0000000..ac62097 --- /dev/null +++ b/OctoThinker-3B-Hybrid-Base.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:744c7979b45aabb5aa7ca6c0d0a9fa75c992f16eae621bc0b59bad74b5027b58 +size 2643850848 diff --git a/OctoThinker-3B-Hybrid-Base.Q8_0.gguf b/OctoThinker-3B-Hybrid-Base.Q8_0.gguf new file mode 100644 index 0000000..58be593 --- /dev/null +++ b/OctoThinker-3B-Hybrid-Base.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae0dad509ccba2af7c59588194980630cded8715649e5d20cfde07a94abf4a04 +size 3421896288 diff --git a/OctoThinker-3B-Hybrid-Base.f16.gguf b/OctoThinker-3B-Hybrid-Base.f16.gguf new file mode 100644 index 0000000..fcc767e --- /dev/null +++ b/OctoThinker-3B-Hybrid-Base.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dee76586eac7897b4cdb8f38ad3ba9550f52861411443656c3f866f21a1abf9b +size 6433685088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a56985b --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: OctoThinker/OctoThinker-3B-Hybrid-Base +datasets: +- OctoThinker/MegaMath-Web-Pro-Max +- LLM360/MegaMath +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/OctoThinker/OctoThinker-3B-Hybrid-Base + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#OctoThinker-3B-Hybrid-Base-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/OctoThinker-3B-Hybrid-Base-GGUF/resolve/main/OctoThinker-3B-Hybrid-Base.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Hybrid-Base-GGUF/resolve/main/OctoThinker-3B-Hybrid-Base.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Hybrid-Base-GGUF/resolve/main/OctoThinker-3B-Hybrid-Base.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Hybrid-Base-GGUF/resolve/main/OctoThinker-3B-Hybrid-Base.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Hybrid-Base-GGUF/resolve/main/OctoThinker-3B-Hybrid-Base.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Hybrid-Base-GGUF/resolve/main/OctoThinker-3B-Hybrid-Base.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Hybrid-Base-GGUF/resolve/main/OctoThinker-3B-Hybrid-Base.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Hybrid-Base-GGUF/resolve/main/OctoThinker-3B-Hybrid-Base.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Hybrid-Base-GGUF/resolve/main/OctoThinker-3B-Hybrid-Base.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Hybrid-Base-GGUF/resolve/main/OctoThinker-3B-Hybrid-Base.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Hybrid-Base-GGUF/resolve/main/OctoThinker-3B-Hybrid-Base.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OctoThinker-3B-Hybrid-Base-GGUF/resolve/main/OctoThinker-3B-Hybrid-Base.f16.gguf) | f16 | 6.5 | 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. + +