commit 04d806b2e1b343ea726aa6a5cc87248c84a7fb4b Author: ModelHub XC Date: Tue Jun 16 02:04:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Olmo-3-7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0b23b77 --- /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 +Olmo-3-7B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Olmo-3-7B-Instruct.IQ4_XS.gguf b/Olmo-3-7B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..9dfe8e7 --- /dev/null +++ b/Olmo-3-7B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72ed0b5a97ac78420a38c57438b92405a9de0073f3bcaf11e64b989a8b3cb27c +size 4029374496 diff --git a/Olmo-3-7B-Instruct.Q2_K.gguf b/Olmo-3-7B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..592fe6e --- /dev/null +++ b/Olmo-3-7B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da4e09953e1a4645d59964bbef514faee9f05bb3c204ade28b997b941a9817a0 +size 2857914528 diff --git a/Olmo-3-7B-Instruct.Q3_K_L.gguf b/Olmo-3-7B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..c990662 --- /dev/null +++ b/Olmo-3-7B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b47fb97775033691810259e2303bcb7b8b8622b922dd0262d77745f44b0656 +size 3950565472 diff --git a/Olmo-3-7B-Instruct.Q3_K_M.gguf b/Olmo-3-7B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..4e51642 --- /dev/null +++ b/Olmo-3-7B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cef7e95534aedd97223d9a8c46949727efb715eb49c214c24ecc96081a175211 +size 3651459168 diff --git a/Olmo-3-7B-Instruct.Q3_K_S.gguf b/Olmo-3-7B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..9938675 --- /dev/null +++ b/Olmo-3-7B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edf75a3ec43ca4a0c35251e11a0d278a43be5f016553546d7de99edb48741dad +size 3301759072 diff --git a/Olmo-3-7B-Instruct.Q4_K_M.gguf b/Olmo-3-7B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..207afd1 --- /dev/null +++ b/Olmo-3-7B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:345b5521084efdd2b57a8b162df88158826f3c00dccc9eb79396596ab0ed5ecb +size 4471601952 diff --git a/Olmo-3-7B-Instruct.Q4_K_S.gguf b/Olmo-3-7B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..fb5f150 --- /dev/null +++ b/Olmo-3-7B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25b67401f0f399a30e72c62b1a18a3636fd497fceb3c89467f8cee0e9611ea28 +size 4247337760 diff --git a/Olmo-3-7B-Instruct.Q5_K_M.gguf b/Olmo-3-7B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..a0bd9b2 --- /dev/null +++ b/Olmo-3-7B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8130265f5b6e919c07d425759b30f613b7df77f37a0a1cb02d301409771de3c +size 5208712992 diff --git a/Olmo-3-7B-Instruct.Q5_K_S.gguf b/Olmo-3-7B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..f4b55b6 --- /dev/null +++ b/Olmo-3-7B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b8898146edcbe13e96bbb62990ce210af8a15a1d2eb91f43e42f2b1e9ca7794 +size 5077247776 diff --git a/Olmo-3-7B-Instruct.Q6_K.gguf b/Olmo-3-7B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..20e8d86 --- /dev/null +++ b/Olmo-3-7B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2801cae16a20fb6071daaf16ee6244294668412e0f83ab4f347f9ace53b8630e +size 5991893472 diff --git a/Olmo-3-7B-Instruct.Q8_0.gguf b/Olmo-3-7B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..2188827 --- /dev/null +++ b/Olmo-3-7B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85420522a4aca323c757aea2fcdb849143911525bd49e6f83763529797f1a852 +size 7759252576 diff --git a/Olmo-3-7B-Instruct.f16.gguf b/Olmo-3-7B-Instruct.f16.gguf new file mode 100644 index 0000000..ac1d11b --- /dev/null +++ b/Olmo-3-7B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:821f48c2b14c9c620d6b5093d56d234b910b9ece652794e3c449ca6499f310eb +size 14600642656 diff --git a/README.md b/README.md new file mode 100644 index 0000000..75711b0 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: allenai/Olmo-3-7B-Instruct +datasets: +- allenai/Dolci-Instruct-RL-7B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/allenai/Olmo-3-7B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Olmo-3-7B-Instruct-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Olmo-3-7B-Instruct-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/Olmo-3-7B-Instruct-GGUF/resolve/main/Olmo-3-7B-Instruct.Q2_K.gguf) | Q2_K | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Instruct-GGUF/resolve/main/Olmo-3-7B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Instruct-GGUF/resolve/main/Olmo-3-7B-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Instruct-GGUF/resolve/main/Olmo-3-7B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Instruct-GGUF/resolve/main/Olmo-3-7B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Instruct-GGUF/resolve/main/Olmo-3-7B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Instruct-GGUF/resolve/main/Olmo-3-7B-Instruct.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Instruct-GGUF/resolve/main/Olmo-3-7B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Instruct-GGUF/resolve/main/Olmo-3-7B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Instruct-GGUF/resolve/main/Olmo-3-7B-Instruct.Q6_K.gguf) | Q6_K | 6.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Instruct-GGUF/resolve/main/Olmo-3-7B-Instruct.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Instruct-GGUF/resolve/main/Olmo-3-7B-Instruct.f16.gguf) | f16 | 14.7 | 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. + +