commit 2b75f67dc5153599025ad31d8625d92b3cdc9692 Author: ModelHub XC Date: Thu Jun 11 22:32:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Marco-o1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..405909b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Marco-o1.f16.gguf filter=lfs diff=lfs merge=lfs -text +Marco-o1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-o1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Marco-o1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Marco-o1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Marco-o1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-o1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-o1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Marco-o1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-o1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Marco-o1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Marco-o1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Marco-o1.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Marco-o1.IQ4_XS.gguf b/Marco-o1.IQ4_XS.gguf new file mode 100644 index 0000000..8ca0895 --- /dev/null +++ b/Marco-o1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6021756a6b77f361769c958b6629ea10e322601b7936ebd6f45068b93ce28a40 +size 4250296896 diff --git a/Marco-o1.Q2_K.gguf b/Marco-o1.Q2_K.gguf new file mode 100644 index 0000000..adcc249 --- /dev/null +++ b/Marco-o1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e1e38a13c6ef7b8fcf357284ddb771f6e04de843c2c4c03bbcf97b1903dc3d1 +size 3015938624 diff --git a/Marco-o1.Q3_K_L.gguf b/Marco-o1.Q3_K_L.gguf new file mode 100644 index 0000000..942f98b --- /dev/null +++ b/Marco-o1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c35be2b537ad4eb6bd824ea00a04f75d6ef89d2cf8b39a572f0493dc91d4ecd +size 4088457792 diff --git a/Marco-o1.Q3_K_M.gguf b/Marco-o1.Q3_K_M.gguf new file mode 100644 index 0000000..76fb40f --- /dev/null +++ b/Marco-o1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1cf40ac9bec94b02e7ca42061ebb960f10f00687479e20088434236a0a5679f +size 3808389696 diff --git a/Marco-o1.Q3_K_S.gguf b/Marco-o1.Q3_K_S.gguf new file mode 100644 index 0000000..12b4bd6 --- /dev/null +++ b/Marco-o1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38e064885ef8a125c6fd65aa21913079923956375b3b5e13b51e56ceeecbdfd9 +size 3492366912 diff --git a/Marco-o1.Q4_0_4_4.gguf b/Marco-o1.Q4_0_4_4.gguf new file mode 100644 index 0000000..03834fc --- /dev/null +++ b/Marco-o1.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d0fe2139b69aba031a075c2505df31e5de4ecbf31fcb336743df4a75e5e0880 +size 4431389248 diff --git a/Marco-o1.Q4_K_M.gguf b/Marco-o1.Q4_K_M.gguf new file mode 100644 index 0000000..f654eee --- /dev/null +++ b/Marco-o1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9e841c55076cb0cde0af7ccc8244e1c42a57898ddf5f63e654a67d83136b5e0 +size 4683072064 diff --git a/Marco-o1.Q4_K_S.gguf b/Marco-o1.Q4_K_S.gguf new file mode 100644 index 0000000..257cd90 --- /dev/null +++ b/Marco-o1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:519c1e377923007bffcd62cb160608648d2d1df445f6e24404de0900217cc8f6 +size 4457767488 diff --git a/Marco-o1.Q5_K_M.gguf b/Marco-o1.Q5_K_M.gguf new file mode 100644 index 0000000..9bfd8e4 --- /dev/null +++ b/Marco-o1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98547a9d9cc0bf7b583006deaa4ffe92fffb8bb703d0e60daed4d2f2212268c6 +size 5444829760 diff --git a/Marco-o1.Q5_K_S.gguf b/Marco-o1.Q5_K_S.gguf new file mode 100644 index 0000000..717dbf2 --- /dev/null +++ b/Marco-o1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19bd2bbff6fc482db31cb83aa0709d8e0fdd10c9ade92467b18d957e557294ab +size 5315174976 diff --git a/Marco-o1.Q6_K.gguf b/Marco-o1.Q6_K.gguf new file mode 100644 index 0000000..b4e3deb --- /dev/null +++ b/Marco-o1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba1c25cb868707745978e49ea0eb565e1297de372d411dc64f6da478c160f6d2 +size 6254197312 diff --git a/Marco-o1.Q8_0.gguf b/Marco-o1.Q8_0.gguf new file mode 100644 index 0000000..d85c5ab --- /dev/null +++ b/Marco-o1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f239ae4ab5f0591228308bf5cc30b789a428eaff38b7570600e9ac161b556e84 +size 8098523712 diff --git a/Marco-o1.f16.gguf b/Marco-o1.f16.gguf new file mode 100644 index 0000000..e9e29fa --- /dev/null +++ b/Marco-o1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17db45828ebb7ecf772d3fed63e4a7e020d3629033677eed6f3c85dca6db6166 +size 15237851712 diff --git a/README.md b/README.md new file mode 100644 index 0000000..33376e4 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: AIDC-AI/Marco-o1 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/AIDC-AI/Marco-o1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Marco-o1-i1-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/Marco-o1-GGUF/resolve/main/Marco-o1.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-o1-GGUF/resolve/main/Marco-o1.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-o1-GGUF/resolve/main/Marco-o1.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-o1-GGUF/resolve/main/Marco-o1.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-o1-GGUF/resolve/main/Marco-o1.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-o1-GGUF/resolve/main/Marco-o1.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-o1-GGUF/resolve/main/Marco-o1.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Marco-o1-GGUF/resolve/main/Marco-o1.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Marco-o1-GGUF/resolve/main/Marco-o1.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-o1-GGUF/resolve/main/Marco-o1.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Marco-o1-GGUF/resolve/main/Marco-o1.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-o1-GGUF/resolve/main/Marco-o1.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Marco-o1-GGUF/resolve/main/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. + +