commit 67c740382f55a6a338031af415e98095e05855e1 Author: ModelHub XC Date: Wed Apr 22 13:49:02 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Olmo-3-7B-Think-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9669408 --- /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-Think.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Think.f16.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Think.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Think.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Think.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Think.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Think.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Think.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Think.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Think.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Think.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Olmo-3-7B-Think.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Olmo-3-7B-Think.IQ4_XS.gguf b/Olmo-3-7B-Think.IQ4_XS.gguf new file mode 100644 index 0000000..97ba3e3 --- /dev/null +++ b/Olmo-3-7B-Think.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b4dd9e39f3a9cc658e8002dbd35b92525ffbf7912b6dee21503888bfa97f787 +size 4029373536 diff --git a/Olmo-3-7B-Think.Q2_K.gguf b/Olmo-3-7B-Think.Q2_K.gguf new file mode 100644 index 0000000..ca5b694 --- /dev/null +++ b/Olmo-3-7B-Think.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bb6f529097f179df8980603f3eff6e41262fded933ca726e280eff00c9ca33e +size 2857913568 diff --git a/Olmo-3-7B-Think.Q3_K_L.gguf b/Olmo-3-7B-Think.Q3_K_L.gguf new file mode 100644 index 0000000..e8ac9ef --- /dev/null +++ b/Olmo-3-7B-Think.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe149ff46b57e66fdeac087b90ea82dac10c50f4758e90e9e3084db0357a33bc +size 3950564512 diff --git a/Olmo-3-7B-Think.Q3_K_M.gguf b/Olmo-3-7B-Think.Q3_K_M.gguf new file mode 100644 index 0000000..b352e7f --- /dev/null +++ b/Olmo-3-7B-Think.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e64b35200c4dbd74700d5e4eac7dbb091cc72959785b09fc7066d930cebf508 +size 3651458208 diff --git a/Olmo-3-7B-Think.Q3_K_S.gguf b/Olmo-3-7B-Think.Q3_K_S.gguf new file mode 100644 index 0000000..a568608 --- /dev/null +++ b/Olmo-3-7B-Think.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b951ab35dab418287aefa1250cb89317deea819f0b772e10bea4f5052fe1a796 +size 3301758112 diff --git a/Olmo-3-7B-Think.Q4_K_M.gguf b/Olmo-3-7B-Think.Q4_K_M.gguf new file mode 100644 index 0000000..3bded29 --- /dev/null +++ b/Olmo-3-7B-Think.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92ded411b8f1d52396139509c5b50bf52627e3ef74f47ea824a4fb3c4e794b3f +size 4471600992 diff --git a/Olmo-3-7B-Think.Q4_K_S.gguf b/Olmo-3-7B-Think.Q4_K_S.gguf new file mode 100644 index 0000000..cd2dcee --- /dev/null +++ b/Olmo-3-7B-Think.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c3c489fe5e5f52dec07f21a4a7b5fa48a198077f9d12ebcfc2041d4eb2740b5 +size 4247336800 diff --git a/Olmo-3-7B-Think.Q5_K_M.gguf b/Olmo-3-7B-Think.Q5_K_M.gguf new file mode 100644 index 0000000..148ec49 --- /dev/null +++ b/Olmo-3-7B-Think.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beb9d9fe4e31829d408d28fa2a7c84ace11c2c67f97c0acf331e0d9d311116a8 +size 5208712032 diff --git a/Olmo-3-7B-Think.Q5_K_S.gguf b/Olmo-3-7B-Think.Q5_K_S.gguf new file mode 100644 index 0000000..b6919f7 --- /dev/null +++ b/Olmo-3-7B-Think.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b210e57f508ddb76bc6f1e8ee631784549f96057e7c790148dbc80ef49183092 +size 5077246816 diff --git a/Olmo-3-7B-Think.Q6_K.gguf b/Olmo-3-7B-Think.Q6_K.gguf new file mode 100644 index 0000000..9a92e68 --- /dev/null +++ b/Olmo-3-7B-Think.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0faeb9e1ba6f0012887fd6601d6887a3a631e396ad60fc7f88b169aed4a488a +size 5991892512 diff --git a/Olmo-3-7B-Think.Q8_0.gguf b/Olmo-3-7B-Think.Q8_0.gguf new file mode 100644 index 0000000..ce92bbb --- /dev/null +++ b/Olmo-3-7B-Think.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a7a3fecf8d7272406c5a53affa37c0fe82b87c939b27a41c3c2db46daae65a4 +size 7759251616 diff --git a/Olmo-3-7B-Think.f16.gguf b/Olmo-3-7B-Think.f16.gguf new file mode 100644 index 0000000..e6c5cd9 --- /dev/null +++ b/Olmo-3-7B-Think.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14a47d02d73db1bee55e26ba85aa295b029a760c54cc6ba60acdcd1ca892ad89 +size 14600641696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4ad54ca --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: allenai/Olmo-3-7B-Think +datasets: +- allenai/Dolci-Think-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-Think + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Olmo-3-7B-Think-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Olmo-3-7B-Think-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-Think-GGUF/resolve/main/Olmo-3-7B-Think.Q2_K.gguf) | Q2_K | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-GGUF/resolve/main/Olmo-3-7B-Think.Q3_K_S.gguf) | Q3_K_S | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-GGUF/resolve/main/Olmo-3-7B-Think.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-GGUF/resolve/main/Olmo-3-7B-Think.Q3_K_L.gguf) | Q3_K_L | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-GGUF/resolve/main/Olmo-3-7B-Think.IQ4_XS.gguf) | IQ4_XS | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-GGUF/resolve/main/Olmo-3-7B-Think.Q4_K_S.gguf) | Q4_K_S | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-GGUF/resolve/main/Olmo-3-7B-Think.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-GGUF/resolve/main/Olmo-3-7B-Think.Q5_K_S.gguf) | Q5_K_S | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-GGUF/resolve/main/Olmo-3-7B-Think.Q5_K_M.gguf) | Q5_K_M | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-GGUF/resolve/main/Olmo-3-7B-Think.Q6_K.gguf) | Q6_K | 6.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-GGUF/resolve/main/Olmo-3-7B-Think.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Olmo-3-7B-Think-GGUF/resolve/main/Olmo-3-7B-Think.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. + +