commit d292abfef3e6cff6969464bc8f13c6e5a5ab1e72 Author: ModelHub XC Date: Wed Jul 8 05:21:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/BoT-Marco-o1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..854338d --- /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 +BoT-Marco-o1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BoT-Marco-o1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BoT-Marco-o1.f16.gguf filter=lfs diff=lfs merge=lfs -text +BoT-Marco-o1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +BoT-Marco-o1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +BoT-Marco-o1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BoT-Marco-o1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BoT-Marco-o1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BoT-Marco-o1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BoT-Marco-o1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BoT-Marco-o1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BoT-Marco-o1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BoT-Marco-o1.IQ4_XS.gguf b/BoT-Marco-o1.IQ4_XS.gguf new file mode 100644 index 0000000..cddc2a6 --- /dev/null +++ b/BoT-Marco-o1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6450535e90035711a8a5bb7d525a936625c60fdb3f8ac2a112bad9f96b286edb +size 4250296864 diff --git a/BoT-Marco-o1.Q2_K.gguf b/BoT-Marco-o1.Q2_K.gguf new file mode 100644 index 0000000..c5cc95f --- /dev/null +++ b/BoT-Marco-o1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe214634f821aabae3ae05de363cab5cf1937adcefc768d0c839a6edb7aeee02 +size 3015938592 diff --git a/BoT-Marco-o1.Q3_K_L.gguf b/BoT-Marco-o1.Q3_K_L.gguf new file mode 100644 index 0000000..53b7894 --- /dev/null +++ b/BoT-Marco-o1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abddf5c2af3f3fd07915f3bb5424fefff8feb19100ca1cb619eb668a6a3b8fa1 +size 4088457760 diff --git a/BoT-Marco-o1.Q3_K_M.gguf b/BoT-Marco-o1.Q3_K_M.gguf new file mode 100644 index 0000000..a63c23b --- /dev/null +++ b/BoT-Marco-o1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0f7217616f608b6f59ddbf082c5e1cbc03c19d7351876c3a38640a93386b727 +size 3808389664 diff --git a/BoT-Marco-o1.Q3_K_S.gguf b/BoT-Marco-o1.Q3_K_S.gguf new file mode 100644 index 0000000..af1bae3 --- /dev/null +++ b/BoT-Marco-o1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:252caaf913cbf41895c65324d7fddb99818dc35331c60c707b0f1808339037dd +size 3492366880 diff --git a/BoT-Marco-o1.Q4_K_M.gguf b/BoT-Marco-o1.Q4_K_M.gguf new file mode 100644 index 0000000..0114563 --- /dev/null +++ b/BoT-Marco-o1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33258bf0bf851a5ae17f6eb5b7ea6be81d661dcc0621c080c94d8889e65a74f4 +size 4683072032 diff --git a/BoT-Marco-o1.Q4_K_S.gguf b/BoT-Marco-o1.Q4_K_S.gguf new file mode 100644 index 0000000..7b0341e --- /dev/null +++ b/BoT-Marco-o1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdfb79e7bb9912a1091725a2ea53737c94ade6e609cb905fcd8af1439fb63b73 +size 4457767456 diff --git a/BoT-Marco-o1.Q5_K_M.gguf b/BoT-Marco-o1.Q5_K_M.gguf new file mode 100644 index 0000000..c453965 --- /dev/null +++ b/BoT-Marco-o1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:259f2ec1cedee4e556686f60858cd2fc5a0bfc003815519d5eac9dcdc3f1c12a +size 5444829728 diff --git a/BoT-Marco-o1.Q5_K_S.gguf b/BoT-Marco-o1.Q5_K_S.gguf new file mode 100644 index 0000000..c4bc0f5 --- /dev/null +++ b/BoT-Marco-o1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e79707da3b1f2ac9b40a551c4afe5bb72a8d3fcc4ed3d1148208d38da0f87091 +size 5315174944 diff --git a/BoT-Marco-o1.Q6_K.gguf b/BoT-Marco-o1.Q6_K.gguf new file mode 100644 index 0000000..99574a1 --- /dev/null +++ b/BoT-Marco-o1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28e29118c56bff579117ff21501becc445bb812275aa0a711ed7304971f7d997 +size 6254197280 diff --git a/BoT-Marco-o1.Q8_0.gguf b/BoT-Marco-o1.Q8_0.gguf new file mode 100644 index 0000000..001e40c --- /dev/null +++ b/BoT-Marco-o1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4eed9de5ba12466e0845844612544ec7c8d8418f106f1a7f8888bd86896c1fb +size 8098523680 diff --git a/BoT-Marco-o1.f16.gguf b/BoT-Marco-o1.f16.gguf new file mode 100644 index 0000000..4eccb65 --- /dev/null +++ b/BoT-Marco-o1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d8c8b829d5aef077a24d648f2f46e2a046557fac310cfc3d49154ebf0bd986a +size 15237851680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8e7d0f6 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: ZihaoZhu/BoT-Marco-o1 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/ZihaoZhu/BoT-Marco-o1 + + +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/BoT-Marco-o1-GGUF/resolve/main/BoT-Marco-o1.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/BoT-Marco-o1-GGUF/resolve/main/BoT-Marco-o1.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/BoT-Marco-o1-GGUF/resolve/main/BoT-Marco-o1.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BoT-Marco-o1-GGUF/resolve/main/BoT-Marco-o1.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/BoT-Marco-o1-GGUF/resolve/main/BoT-Marco-o1.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/BoT-Marco-o1-GGUF/resolve/main/BoT-Marco-o1.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BoT-Marco-o1-GGUF/resolve/main/BoT-Marco-o1.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BoT-Marco-o1-GGUF/resolve/main/BoT-Marco-o1.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/BoT-Marco-o1-GGUF/resolve/main/BoT-Marco-o1.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/BoT-Marco-o1-GGUF/resolve/main/BoT-Marco-o1.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/BoT-Marco-o1-GGUF/resolve/main/BoT-Marco-o1.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/BoT-Marco-o1-GGUF/resolve/main/BoT-Marco-o1.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. + +