commit 3a9f5be938648a5806b461e07da73307e8b9fb80 Author: ModelHub XC Date: Thu Jun 18 06:50:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OLMoE-1B-7B-0125-sft-math7k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ef1790d --- /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 +OLMoE-1B-7B-0125-sft-math7k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-sft-math7k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-sft-math7k.f16.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-sft-math7k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-sft-math7k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-sft-math7k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-sft-math7k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-sft-math7k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-sft-math7k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-sft-math7k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-sft-math7k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMoE-1B-7B-0125-sft-math7k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OLMoE-1B-7B-0125-sft-math7k.IQ4_XS.gguf b/OLMoE-1B-7B-0125-sft-math7k.IQ4_XS.gguf new file mode 100644 index 0000000..06841b6 --- /dev/null +++ b/OLMoE-1B-7B-0125-sft-math7k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2436a91dcca61ef86b255759f39cf574831588275781039e415d906c02ce696f +size 3757046816 diff --git a/OLMoE-1B-7B-0125-sft-math7k.Q2_K.gguf b/OLMoE-1B-7B-0125-sft-math7k.Q2_K.gguf new file mode 100644 index 0000000..91398b8 --- /dev/null +++ b/OLMoE-1B-7B-0125-sft-math7k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9984c00990a20ac7527b5da68aeb003b0e49afc465c860f042d813492d380f10 +size 2562763808 diff --git a/OLMoE-1B-7B-0125-sft-math7k.Q3_K_L.gguf b/OLMoE-1B-7B-0125-sft-math7k.Q3_K_L.gguf new file mode 100644 index 0000000..388c497 --- /dev/null +++ b/OLMoE-1B-7B-0125-sft-math7k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d11ddd3b27b108d5be7aa799b9a0672ca9a60480875ab1e05b7f63b2418018 +size 3611317280 diff --git a/OLMoE-1B-7B-0125-sft-math7k.Q3_K_M.gguf b/OLMoE-1B-7B-0125-sft-math7k.Q3_K_M.gguf new file mode 100644 index 0000000..8a7d2c4 --- /dev/null +++ b/OLMoE-1B-7B-0125-sft-math7k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66f348d28c4d183839a49a9783dd210718d0b8b6d04f6060eafc31aa3d473d53 +size 3343930400 diff --git a/OLMoE-1B-7B-0125-sft-math7k.Q3_K_S.gguf b/OLMoE-1B-7B-0125-sft-math7k.Q3_K_S.gguf new file mode 100644 index 0000000..8df1cd6 --- /dev/null +++ b/OLMoE-1B-7B-0125-sft-math7k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95bf1b49332cb52c12bff95c13ef1dbca1660cf4b6b8fb596d4395213d71f2d9 +size 3023066144 diff --git a/OLMoE-1B-7B-0125-sft-math7k.Q4_K_M.gguf b/OLMoE-1B-7B-0125-sft-math7k.Q4_K_M.gguf new file mode 100644 index 0000000..eae06d0 --- /dev/null +++ b/OLMoE-1B-7B-0125-sft-math7k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc2f604ed962d5d6a1a8ba661eb56472962d9594cf080f8c571f4c3498b37cb5 +size 4213513248 diff --git a/OLMoE-1B-7B-0125-sft-math7k.Q4_K_S.gguf b/OLMoE-1B-7B-0125-sft-math7k.Q4_K_S.gguf new file mode 100644 index 0000000..0296e17 --- /dev/null +++ b/OLMoE-1B-7B-0125-sft-math7k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cdafb7c7273d3b69cc72d937716bf781836622545add97fb525819d406a1c71 +size 3963690016 diff --git a/OLMoE-1B-7B-0125-sft-math7k.Q5_K_M.gguf b/OLMoE-1B-7B-0125-sft-math7k.Q5_K_M.gguf new file mode 100644 index 0000000..fd45e4a --- /dev/null +++ b/OLMoE-1B-7B-0125-sft-math7k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65a85678f870df1afb21999daf5e4e34c76d3f26497fac404b6ebd3022067d41 +size 4926839840 diff --git a/OLMoE-1B-7B-0125-sft-math7k.Q5_K_S.gguf b/OLMoE-1B-7B-0125-sft-math7k.Q5_K_S.gguf new file mode 100644 index 0000000..c45ad6d --- /dev/null +++ b/OLMoE-1B-7B-0125-sft-math7k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d42d8d39df3ea4e7b781a2ece0e1adbed32e00946dd36f50867d7741b16f3a5 +size 4779777056 diff --git a/OLMoE-1B-7B-0125-sft-math7k.Q6_K.gguf b/OLMoE-1B-7B-0125-sft-math7k.Q6_K.gguf new file mode 100644 index 0000000..a71e382 --- /dev/null +++ b/OLMoE-1B-7B-0125-sft-math7k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d027d5f24ed8d76076bbb3df18c5a144fccf2aee224bacb3c64aca82116fc12d +size 5684749344 diff --git a/OLMoE-1B-7B-0125-sft-math7k.Q8_0.gguf b/OLMoE-1B-7B-0125-sft-math7k.Q8_0.gguf new file mode 100644 index 0000000..e0b1f02 --- /dev/null +++ b/OLMoE-1B-7B-0125-sft-math7k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:924c0bb0e06c687dd523204026ce08a07e81cc11f597c0703458515c00db90d5 +size 7359943712 diff --git a/OLMoE-1B-7B-0125-sft-math7k.f16.gguf b/OLMoE-1B-7B-0125-sft-math7k.f16.gguf new file mode 100644 index 0000000..2549423 --- /dev/null +++ b/OLMoE-1B-7B-0125-sft-math7k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a61660c5eb8ee3f198a8cff0c852d5d770975b61517c9f7d78eb6e7280faae6a +size 13844567072 diff --git a/README.md b/README.md new file mode 100644 index 0000000..80eac1c --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: HectorHe/OLMoE-1B-7B-0125-sft-math7k +datasets: HectorHe/math7k +language: +- en +library_name: transformers +model_name: OLMoE-1B-7B-0125-sft-math7k +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- open-r1 +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/HectorHe/OLMoE-1B-7B-0125-sft-math7k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#OLMoE-1B-7B-0125-sft-math7k-GGUF).*** + +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/OLMoE-1B-7B-0125-sft-math7k-GGUF/resolve/main/OLMoE-1B-7B-0125-sft-math7k.Q2_K.gguf) | Q2_K | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-sft-math7k-GGUF/resolve/main/OLMoE-1B-7B-0125-sft-math7k.Q3_K_S.gguf) | Q3_K_S | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-sft-math7k-GGUF/resolve/main/OLMoE-1B-7B-0125-sft-math7k.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-sft-math7k-GGUF/resolve/main/OLMoE-1B-7B-0125-sft-math7k.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-sft-math7k-GGUF/resolve/main/OLMoE-1B-7B-0125-sft-math7k.IQ4_XS.gguf) | IQ4_XS | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-sft-math7k-GGUF/resolve/main/OLMoE-1B-7B-0125-sft-math7k.Q4_K_S.gguf) | Q4_K_S | 4.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-sft-math7k-GGUF/resolve/main/OLMoE-1B-7B-0125-sft-math7k.Q4_K_M.gguf) | Q4_K_M | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-sft-math7k-GGUF/resolve/main/OLMoE-1B-7B-0125-sft-math7k.Q5_K_S.gguf) | Q5_K_S | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-sft-math7k-GGUF/resolve/main/OLMoE-1B-7B-0125-sft-math7k.Q5_K_M.gguf) | Q5_K_M | 5.0 | | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-sft-math7k-GGUF/resolve/main/OLMoE-1B-7B-0125-sft-math7k.Q6_K.gguf) | Q6_K | 5.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-sft-math7k-GGUF/resolve/main/OLMoE-1B-7B-0125-sft-math7k.Q8_0.gguf) | Q8_0 | 7.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OLMoE-1B-7B-0125-sft-math7k-GGUF/resolve/main/OLMoE-1B-7B-0125-sft-math7k.f16.gguf) | f16 | 13.9 | 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. + +