commit 0074ae682c5effebc4cf33cd48513b86233ad954 Author: ModelHub XC Date: Tue May 5 14:23:46 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/O1-Llama-3.2-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2c1a6a6 --- /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 +O1-Llama-3.2-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +O1-Llama-3.2-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +O1-Llama-3.2-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text +O1-Llama-3.2-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +O1-Llama-3.2-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +O1-Llama-3.2-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +O1-Llama-3.2-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +O1-Llama-3.2-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +O1-Llama-3.2-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +O1-Llama-3.2-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +O1-Llama-3.2-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +O1-Llama-3.2-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +O1-Llama-3.2-3B.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/O1-Llama-3.2-3B.IQ4_XS.gguf b/O1-Llama-3.2-3B.IQ4_XS.gguf new file mode 100644 index 0000000..97e3fce --- /dev/null +++ b/O1-Llama-3.2-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:458c57d4a40c92f86edcbcec4cd0e48b7271e149c909035e625f2419c24a872e +size 1840906688 diff --git a/O1-Llama-3.2-3B.Q2_K.gguf b/O1-Llama-3.2-3B.Q2_K.gguf new file mode 100644 index 0000000..98855bc --- /dev/null +++ b/O1-Llama-3.2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd6d889d6d82e5f8273285a5e44e9e384b5d99dd35578a0a6efb580900ec7fcb +size 1363935680 diff --git a/O1-Llama-3.2-3B.Q3_K_L.gguf b/O1-Llama-3.2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..4422881 --- /dev/null +++ b/O1-Llama-3.2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92ea95ca328a8592203626c73e8b7a0def4065cf324603e1e519b52b7d697cad +size 1815347648 diff --git a/O1-Llama-3.2-3B.Q3_K_M.gguf b/O1-Llama-3.2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..3b28057 --- /dev/null +++ b/O1-Llama-3.2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4cb59919fe1123553e9652b06dd24b69df264674315cf97568386410c9a9fbb +size 1687159232 diff --git a/O1-Llama-3.2-3B.Q3_K_S.gguf b/O1-Llama-3.2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..bda3f55 --- /dev/null +++ b/O1-Llama-3.2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c577a4f7543e796835238b379525932e9b1aa5da39897e9c1d493954140b9821 +size 1542848960 diff --git a/O1-Llama-3.2-3B.Q4_0_4_4.gguf b/O1-Llama-3.2-3B.Q4_0_4_4.gguf new file mode 100644 index 0000000..1f6b8e6 --- /dev/null +++ b/O1-Llama-3.2-3B.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5c692bbd7a8223e3890f50e89dfdb6c05865fe5bfd5a629b8a284f582fc0a31 +size 1917190592 diff --git a/O1-Llama-3.2-3B.Q4_K_M.gguf b/O1-Llama-3.2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..4154e4a --- /dev/null +++ b/O1-Llama-3.2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:692303871f7a444c83fe28a24f760e719c32317a5031954202d78fd027bbbcb1 +size 2019377600 diff --git a/O1-Llama-3.2-3B.Q4_K_S.gguf b/O1-Llama-3.2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..5ee4f6a --- /dev/null +++ b/O1-Llama-3.2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37006e25bd0035e89aaba68f8e04c52bfd7891ab0e86540c86dfe6548a2369a1 +size 1928200640 diff --git a/O1-Llama-3.2-3B.Q5_K_M.gguf b/O1-Llama-3.2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..b9cf7db --- /dev/null +++ b/O1-Llama-3.2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3962ff22bf2e59bdc28276ed41c83384079bd9d4388f792d82df978765a9d2a7 +size 2322153920 diff --git a/O1-Llama-3.2-3B.Q5_K_S.gguf b/O1-Llama-3.2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..e73a36b --- /dev/null +++ b/O1-Llama-3.2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5bbd712b9eacbe8b34e823bc86b67ab187c65f32cd674830705eaa68478eacc +size 2269512128 diff --git a/O1-Llama-3.2-3B.Q6_K.gguf b/O1-Llama-3.2-3B.Q6_K.gguf new file mode 100644 index 0000000..3d70dba --- /dev/null +++ b/O1-Llama-3.2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe4952f83d5e99454a045672c28fed36686c44df073c5ddca9405564a165d7ec +size 2643853760 diff --git a/O1-Llama-3.2-3B.Q8_0.gguf b/O1-Llama-3.2-3B.Q8_0.gguf new file mode 100644 index 0000000..30d2357 --- /dev/null +++ b/O1-Llama-3.2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed2db65713d3582f2e9ab96238f1601d8d9afd5035abfaf6c0493a914558158a +size 3421899200 diff --git a/O1-Llama-3.2-3B.f16.gguf b/O1-Llama-3.2-3B.f16.gguf new file mode 100644 index 0000000..2e63fd0 --- /dev/null +++ b/O1-Llama-3.2-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:314271e6d9af2d5b98a6e42b65aa39df6f860c299dcf80f5967d504024485fac +size 6433688000 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ae98903 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: TamasSimonds/O1-Llama-3.2-3B +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/TamasSimonds/O1-Llama-3.2-3B + + +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/O1-Llama-3.2-3B-GGUF/resolve/main/O1-Llama-3.2-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/O1-Llama-3.2-3B-GGUF/resolve/main/O1-Llama-3.2-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/O1-Llama-3.2-3B-GGUF/resolve/main/O1-Llama-3.2-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/O1-Llama-3.2-3B-GGUF/resolve/main/O1-Llama-3.2-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/O1-Llama-3.2-3B-GGUF/resolve/main/O1-Llama-3.2-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/O1-Llama-3.2-3B-GGUF/resolve/main/O1-Llama-3.2-3B.Q4_0_4_4.gguf) | Q4_0_4_4 | 2.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/O1-Llama-3.2-3B-GGUF/resolve/main/O1-Llama-3.2-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/O1-Llama-3.2-3B-GGUF/resolve/main/O1-Llama-3.2-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/O1-Llama-3.2-3B-GGUF/resolve/main/O1-Llama-3.2-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/O1-Llama-3.2-3B-GGUF/resolve/main/O1-Llama-3.2-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/O1-Llama-3.2-3B-GGUF/resolve/main/O1-Llama-3.2-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/O1-Llama-3.2-3B-GGUF/resolve/main/O1-Llama-3.2-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/O1-Llama-3.2-3B-GGUF/resolve/main/O1-Llama-3.2-3B.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. + +