commit 286cb9df70a31b67dbc450cd788f3023d1ff2d3a Author: ModelHub XC Date: Mon Jun 1 02:47:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-CPT-Math-ThinkSFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..057c6d7 --- /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 +Llama-3.2-3B-CPT-Math-ThinkSFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CPT-Math-ThinkSFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CPT-Math-ThinkSFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CPT-Math-ThinkSFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CPT-Math-ThinkSFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CPT-Math-ThinkSFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CPT-Math-ThinkSFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CPT-Math-ThinkSFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CPT-Math-ThinkSFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CPT-Math-ThinkSFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CPT-Math-ThinkSFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-CPT-Math-ThinkSFT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-CPT-Math-ThinkSFT.IQ4_XS.gguf b/Llama-3.2-3B-CPT-Math-ThinkSFT.IQ4_XS.gguf new file mode 100644 index 0000000..767899c --- /dev/null +++ b/Llama-3.2-3B-CPT-Math-ThinkSFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09e27616167933eccf17868a026b11800052e05a1dd95591a2ec7304168ee3f +size 2050218176 diff --git a/Llama-3.2-3B-CPT-Math-ThinkSFT.Q2_K.gguf b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q2_K.gguf new file mode 100644 index 0000000..9fbe70a --- /dev/null +++ b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a861e2b65fdd5d32386183172dd1e1e5467fbca78bb89c294ee7b095817c23d7 +size 1493215424 diff --git a/Llama-3.2-3B-CPT-Math-ThinkSFT.Q3_K_L.gguf b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q3_K_L.gguf new file mode 100644 index 0000000..b97861d --- /dev/null +++ b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:491fcb12d55b768e348a55d23633b846e84480346d5f8d93182e73261b042b1c +size 1984643264 diff --git a/Llama-3.2-3B-CPT-Math-ThinkSFT.Q3_K_M.gguf b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q3_K_M.gguf new file mode 100644 index 0000000..9c00997 --- /dev/null +++ b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:379b79dd1c82c7f55746949f6c8ecf7271ad0ada7262df590c63462f569f1890 +size 1856454848 diff --git a/Llama-3.2-3B-CPT-Math-ThinkSFT.Q3_K_S.gguf b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q3_K_S.gguf new file mode 100644 index 0000000..b0cbca4 --- /dev/null +++ b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbfcb8efa6a6dfd1fff93617fed0f159d4a2f37ce72536abe9acc6fa757e4a8a +size 1712144576 diff --git a/Llama-3.2-3B-CPT-Math-ThinkSFT.Q4_K_M.gguf b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q4_K_M.gguf new file mode 100644 index 0000000..beaf9d3 --- /dev/null +++ b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f0f5a66c3ebb6275da90be7920ee0d7f95c8a953045dac250253a8fdca9228d +size 2241001664 diff --git a/Llama-3.2-3B-CPT-Math-ThinkSFT.Q4_K_S.gguf b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q4_K_S.gguf new file mode 100644 index 0000000..7879576 --- /dev/null +++ b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:154fa4d7f55aca7298b97b08051a6cb6b2c3b9debb42855bf653a747e3f46014 +size 2149824704 diff --git a/Llama-3.2-3B-CPT-Math-ThinkSFT.Q5_K_M.gguf b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q5_K_M.gguf new file mode 100644 index 0000000..0bb4fc0 --- /dev/null +++ b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d481e9371787b85e83bbf9fe6c35d686a5f9852ef5abbb1e682439ee969fa9b2 +size 2593028288 diff --git a/Llama-3.2-3B-CPT-Math-ThinkSFT.Q5_K_S.gguf b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q5_K_S.gguf new file mode 100644 index 0000000..239e8c7 --- /dev/null +++ b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f052a4d3b1cb69b8ef2542687b4998c0d9ce8f9e7821b17a22d6a071b176c51d +size 2540386496 diff --git a/Llama-3.2-3B-CPT-Math-ThinkSFT.Q6_K.gguf b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q6_K.gguf new file mode 100644 index 0000000..22c8b9a --- /dev/null +++ b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e678ee065da77c300455cf52b662392232fa3925c1368d905902fffce746e59 +size 2967056576 diff --git a/Llama-3.2-3B-CPT-Math-ThinkSFT.Q8_0.gguf b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q8_0.gguf new file mode 100644 index 0000000..8023699 --- /dev/null +++ b/Llama-3.2-3B-CPT-Math-ThinkSFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50b81b5a89e983ae8fe2cd5db09ad0dcb775911f4f44f370cdce52461804323c +size 3840524480 diff --git a/Llama-3.2-3B-CPT-Math-ThinkSFT.f16.gguf b/Llama-3.2-3B-CPT-Math-ThinkSFT.f16.gguf new file mode 100644 index 0000000..ed5b993 --- /dev/null +++ b/Llama-3.2-3B-CPT-Math-ThinkSFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07b3c661688730c6eabfde5b787f056e1dd79813b36a23459ebb9b305022dde1 +size 7221690560 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c19803e --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: pavelslab-nyu/Llama-3.2-3B-CPT-Math-ThinkSFT +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- sft +- math +- thinking +- llama +--- +## About + + + + + + + + + +static quants of https://huggingface.co/pavelslab-nyu/Llama-3.2-3B-CPT-Math-ThinkSFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-3B-CPT-Math-ThinkSFT-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-CPT-Math-ThinkSFT-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/Llama-3.2-3B-CPT-Math-ThinkSFT-GGUF/resolve/main/Llama-3.2-3B-CPT-Math-ThinkSFT.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CPT-Math-ThinkSFT-GGUF/resolve/main/Llama-3.2-3B-CPT-Math-ThinkSFT.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CPT-Math-ThinkSFT-GGUF/resolve/main/Llama-3.2-3B-CPT-Math-ThinkSFT.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CPT-Math-ThinkSFT-GGUF/resolve/main/Llama-3.2-3B-CPT-Math-ThinkSFT.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CPT-Math-ThinkSFT-GGUF/resolve/main/Llama-3.2-3B-CPT-Math-ThinkSFT.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CPT-Math-ThinkSFT-GGUF/resolve/main/Llama-3.2-3B-CPT-Math-ThinkSFT.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CPT-Math-ThinkSFT-GGUF/resolve/main/Llama-3.2-3B-CPT-Math-ThinkSFT.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CPT-Math-ThinkSFT-GGUF/resolve/main/Llama-3.2-3B-CPT-Math-ThinkSFT.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CPT-Math-ThinkSFT-GGUF/resolve/main/Llama-3.2-3B-CPT-Math-ThinkSFT.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CPT-Math-ThinkSFT-GGUF/resolve/main/Llama-3.2-3B-CPT-Math-ThinkSFT.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CPT-Math-ThinkSFT-GGUF/resolve/main/Llama-3.2-3B-CPT-Math-ThinkSFT.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-CPT-Math-ThinkSFT-GGUF/resolve/main/Llama-3.2-3B-CPT-Math-ThinkSFT.f16.gguf) | f16 | 7.3 | 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. + +