commit 57a9a052f779f76c6eeeeb991ed48905e3783ad9 Author: ModelHub XC Date: Sat May 9 02:33:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/One-Shot-CFT-Math-Llama-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1a7d460 --- /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 +One-Shot-CFT-Math-Llama-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +One-Shot-CFT-Math-Llama-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +One-Shot-CFT-Math-Llama-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +One-Shot-CFT-Math-Llama-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +One-Shot-CFT-Math-Llama-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +One-Shot-CFT-Math-Llama-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +One-Shot-CFT-Math-Llama-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +One-Shot-CFT-Math-Llama-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +One-Shot-CFT-Math-Llama-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +One-Shot-CFT-Math-Llama-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +One-Shot-CFT-Math-Llama-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +One-Shot-CFT-Math-Llama-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/One-Shot-CFT-Math-Llama-3B.IQ4_XS.gguf b/One-Shot-CFT-Math-Llama-3B.IQ4_XS.gguf new file mode 100644 index 0000000..d7797a9 --- /dev/null +++ b/One-Shot-CFT-Math-Llama-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1389bd8e222953bc5b123c2dd41fd081f84c2f55b59666f9400ea9bdb5f8b04d +size 1840907232 diff --git a/One-Shot-CFT-Math-Llama-3B.Q2_K.gguf b/One-Shot-CFT-Math-Llama-3B.Q2_K.gguf new file mode 100644 index 0000000..0bef75d --- /dev/null +++ b/One-Shot-CFT-Math-Llama-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f682a9b587bbd727eba5c751806e48075e70e5e8ae6190f2789ea33e12a7199a +size 1363936224 diff --git a/One-Shot-CFT-Math-Llama-3B.Q3_K_L.gguf b/One-Shot-CFT-Math-Llama-3B.Q3_K_L.gguf new file mode 100644 index 0000000..f0b9cec --- /dev/null +++ b/One-Shot-CFT-Math-Llama-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b964ce9821d245e0b470ff440adce6fc0395a4443c53a6bbe9fc3f09d52f50a +size 1815348192 diff --git a/One-Shot-CFT-Math-Llama-3B.Q3_K_M.gguf b/One-Shot-CFT-Math-Llama-3B.Q3_K_M.gguf new file mode 100644 index 0000000..890b8bc --- /dev/null +++ b/One-Shot-CFT-Math-Llama-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b5043ace1edcc6ee41efb60e997a41354980c1abecbfb07b66a3d137f5a8552 +size 1687159776 diff --git a/One-Shot-CFT-Math-Llama-3B.Q3_K_S.gguf b/One-Shot-CFT-Math-Llama-3B.Q3_K_S.gguf new file mode 100644 index 0000000..053c7ca --- /dev/null +++ b/One-Shot-CFT-Math-Llama-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e948a8767451611fb575f9f1043be06604fc56e84871715ae6c2f87673e77fd6 +size 1542849504 diff --git a/One-Shot-CFT-Math-Llama-3B.Q4_K_M.gguf b/One-Shot-CFT-Math-Llama-3B.Q4_K_M.gguf new file mode 100644 index 0000000..2421a81 --- /dev/null +++ b/One-Shot-CFT-Math-Llama-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbc4f5cf59c5b089dd4fbc8e481ad3ca560240d07c16ade24bbf2842d9dbadf2 +size 2019378144 diff --git a/One-Shot-CFT-Math-Llama-3B.Q4_K_S.gguf b/One-Shot-CFT-Math-Llama-3B.Q4_K_S.gguf new file mode 100644 index 0000000..f80ad3f --- /dev/null +++ b/One-Shot-CFT-Math-Llama-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2934349c2fa986b802816645d2a16ee8e9ac7f3ec3df20045af3c2b7386e3f32 +size 1928201184 diff --git a/One-Shot-CFT-Math-Llama-3B.Q5_K_M.gguf b/One-Shot-CFT-Math-Llama-3B.Q5_K_M.gguf new file mode 100644 index 0000000..a6cb5e7 --- /dev/null +++ b/One-Shot-CFT-Math-Llama-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90a8d9796625cf4e1303b32f000ffd020f075fcd47bed37acfd4f9176166f75c +size 2322154464 diff --git a/One-Shot-CFT-Math-Llama-3B.Q5_K_S.gguf b/One-Shot-CFT-Math-Llama-3B.Q5_K_S.gguf new file mode 100644 index 0000000..82ad0ca --- /dev/null +++ b/One-Shot-CFT-Math-Llama-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76df7a8462fdd55a06b7cf7a0336f1306c82c28e456e22dc1167a4621d917e13 +size 2269512672 diff --git a/One-Shot-CFT-Math-Llama-3B.Q6_K.gguf b/One-Shot-CFT-Math-Llama-3B.Q6_K.gguf new file mode 100644 index 0000000..2234dd6 --- /dev/null +++ b/One-Shot-CFT-Math-Llama-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed79f20af3f2da89ab17795772d26ce7982d0d3dae057479de3533e0e6cf602f +size 2643854304 diff --git a/One-Shot-CFT-Math-Llama-3B.Q8_0.gguf b/One-Shot-CFT-Math-Llama-3B.Q8_0.gguf new file mode 100644 index 0000000..2f6d087 --- /dev/null +++ b/One-Shot-CFT-Math-Llama-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:644bdcab0a08cd894104731ff870509f78cbcf88de139713fabf9c9f65ffbb44 +size 3421899744 diff --git a/One-Shot-CFT-Math-Llama-3B.f16.gguf b/One-Shot-CFT-Math-Llama-3B.f16.gguf new file mode 100644 index 0000000..23feabf --- /dev/null +++ b/One-Shot-CFT-Math-Llama-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c34701f8a945ff512eefaa5b8bcf59023c93639f286b92811fea0e690659bd5 +size 6433688544 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f79ff8a --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: TIGER-Lab/One-Shot-CFT-Math-Llama-3B +language: +- en +library_name: transformers +license: cc-by-4.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- One-Shot-CFT +--- +## About + + + + + + + + + +static quants of https://huggingface.co/TIGER-Lab/One-Shot-CFT-Math-Llama-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#One-Shot-CFT-Math-Llama-3B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/One-Shot-CFT-Math-Llama-3B-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/One-Shot-CFT-Math-Llama-3B-GGUF/resolve/main/One-Shot-CFT-Math-Llama-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/One-Shot-CFT-Math-Llama-3B-GGUF/resolve/main/One-Shot-CFT-Math-Llama-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/One-Shot-CFT-Math-Llama-3B-GGUF/resolve/main/One-Shot-CFT-Math-Llama-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/One-Shot-CFT-Math-Llama-3B-GGUF/resolve/main/One-Shot-CFT-Math-Llama-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/One-Shot-CFT-Math-Llama-3B-GGUF/resolve/main/One-Shot-CFT-Math-Llama-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/One-Shot-CFT-Math-Llama-3B-GGUF/resolve/main/One-Shot-CFT-Math-Llama-3B.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/One-Shot-CFT-Math-Llama-3B-GGUF/resolve/main/One-Shot-CFT-Math-Llama-3B.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/One-Shot-CFT-Math-Llama-3B-GGUF/resolve/main/One-Shot-CFT-Math-Llama-3B.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/One-Shot-CFT-Math-Llama-3B-GGUF/resolve/main/One-Shot-CFT-Math-Llama-3B.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/One-Shot-CFT-Math-Llama-3B-GGUF/resolve/main/One-Shot-CFT-Math-Llama-3B.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/One-Shot-CFT-Math-Llama-3B-GGUF/resolve/main/One-Shot-CFT-Math-Llama-3B.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/One-Shot-CFT-Math-Llama-3B-GGUF/resolve/main/One-Shot-CFT-Math-Llama-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. + +