commit a44424703ab9dfc1c6b57351fdd13147f63f7842 Author: ModelHub XC Date: Mon Jun 29 15:45:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OLMo-2-0425-1B-SFT-Think-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..096a9c7 --- /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-2-0425-1B-SFT-Think.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-0425-1B-SFT-Think.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-0425-1B-SFT-Think.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-0425-1B-SFT-Think.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-0425-1B-SFT-Think.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-0425-1B-SFT-Think.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-0425-1B-SFT-Think.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-0425-1B-SFT-Think.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-0425-1B-SFT-Think.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-0425-1B-SFT-Think.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-0425-1B-SFT-Think.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-0425-1B-SFT-Think.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OLMo-2-0425-1B-SFT-Think.IQ4_XS.gguf b/OLMo-2-0425-1B-SFT-Think.IQ4_XS.gguf new file mode 100644 index 0000000..2b67635 --- /dev/null +++ b/OLMo-2-0425-1B-SFT-Think.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd184e745cac7433170cc2b1900c9f0694182a61b541bd11837d8363ffef3401 +size 857320384 diff --git a/OLMo-2-0425-1B-SFT-Think.Q2_K.gguf b/OLMo-2-0425-1B-SFT-Think.Q2_K.gguf new file mode 100644 index 0000000..a0af863 --- /dev/null +++ b/OLMo-2-0425-1B-SFT-Think.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3db5770c9fd0379ef66bdbdc1922d5443e97b837bf979268d56afd8b9ed4001 +size 633152512 diff --git a/OLMo-2-0425-1B-SFT-Think.Q3_K_L.gguf b/OLMo-2-0425-1B-SFT-Think.Q3_K_L.gguf new file mode 100644 index 0000000..15e71cd --- /dev/null +++ b/OLMo-2-0425-1B-SFT-Think.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b3364dee2a9b39468a0035cab98a89937e38426c3ec9cfa2c3db5a509670987 +size 825976800 diff --git a/OLMo-2-0425-1B-SFT-Think.Q3_K_M.gguf b/OLMo-2-0425-1B-SFT-Think.Q3_K_M.gguf new file mode 100644 index 0000000..98b3929 --- /dev/null +++ b/OLMo-2-0425-1B-SFT-Think.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94fd8dfa855f88f73cb18b1bfcfd054ea76912817208585640f892b4f31e28eb +size 778790880 diff --git a/OLMo-2-0425-1B-SFT-Think.Q3_K_S.gguf b/OLMo-2-0425-1B-SFT-Think.Q3_K_S.gguf new file mode 100644 index 0000000..ee13843 --- /dev/null +++ b/OLMo-2-0425-1B-SFT-Think.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddf767e5113fab6700d7474f67fce9cfbf0b6231f4e6cd84da5def2f2f6fa7d1 +size 722167776 diff --git a/OLMo-2-0425-1B-SFT-Think.Q4_K_M.gguf b/OLMo-2-0425-1B-SFT-Think.Q4_K_M.gguf new file mode 100644 index 0000000..601486e --- /dev/null +++ b/OLMo-2-0425-1B-SFT-Think.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fd327693ad3969116368a209750e8d40d556db8c9841ee1928a6c8727f472ef +size 935303488 diff --git a/OLMo-2-0425-1B-SFT-Think.Q4_K_S.gguf b/OLMo-2-0425-1B-SFT-Think.Q4_K_S.gguf new file mode 100644 index 0000000..51f4eb2 --- /dev/null +++ b/OLMo-2-0425-1B-SFT-Think.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5965b20148852e63bd070ea36ebbc65f6d93b6f876f8fe54988aa1ed5e13298d +size 898341184 diff --git a/OLMo-2-0425-1B-SFT-Think.Q5_K_M.gguf b/OLMo-2-0425-1B-SFT-Think.Q5_K_M.gguf new file mode 100644 index 0000000..a57be9d --- /dev/null +++ b/OLMo-2-0425-1B-SFT-Think.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb5018154fc6e2405610615e8a5bdd3c492d640614e45e7f3b3d20ba12d87913 +size 1074220864 diff --git a/OLMo-2-0425-1B-SFT-Think.Q5_K_S.gguf b/OLMo-2-0425-1B-SFT-Think.Q5_K_S.gguf new file mode 100644 index 0000000..4417601 --- /dev/null +++ b/OLMo-2-0425-1B-SFT-Think.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8103c40eaf757f88cf93a7900a838a20f6f2f2ff5364f76f3ab5b17314869e6f +size 1051938624 diff --git a/OLMo-2-0425-1B-SFT-Think.Q6_K.gguf b/OLMo-2-0425-1B-SFT-Think.Q6_K.gguf new file mode 100644 index 0000000..dd25156 --- /dev/null +++ b/OLMo-2-0425-1B-SFT-Think.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:573349c193dcf5a83b492c041cfc3caa3fc659de143bff222d4cb661bcea368a +size 1221820576 diff --git a/OLMo-2-0425-1B-SFT-Think.Q8_0.gguf b/OLMo-2-0425-1B-SFT-Think.Q8_0.gguf new file mode 100644 index 0000000..0626209 --- /dev/null +++ b/OLMo-2-0425-1B-SFT-Think.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63ba6e1f4b85f644169dbdf5c4ab1028f40f750f089cc7b87ce7729c21c6142d +size 1581343200 diff --git a/OLMo-2-0425-1B-SFT-Think.f16.gguf b/OLMo-2-0425-1B-SFT-Think.f16.gguf new file mode 100644 index 0000000..8182b32 --- /dev/null +++ b/OLMo-2-0425-1B-SFT-Think.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab8a3fde3a4b670790448689319b463020e25d675a43afe26fd0d6960c19ad65 +size 2973043680 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8114a8d --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: hbfreed/OLMo-2-0425-1B-SFT-Think +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/hbfreed/OLMo-2-0425-1B-SFT-Think + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#OLMo-2-0425-1B-SFT-Think-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/OLMo-2-0425-1B-SFT-Think-GGUF/resolve/main/OLMo-2-0425-1B-SFT-Think.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-0425-1B-SFT-Think-GGUF/resolve/main/OLMo-2-0425-1B-SFT-Think.Q3_K_S.gguf) | Q3_K_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-0425-1B-SFT-Think-GGUF/resolve/main/OLMo-2-0425-1B-SFT-Think.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-0425-1B-SFT-Think-GGUF/resolve/main/OLMo-2-0425-1B-SFT-Think.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-0425-1B-SFT-Think-GGUF/resolve/main/OLMo-2-0425-1B-SFT-Think.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-0425-1B-SFT-Think-GGUF/resolve/main/OLMo-2-0425-1B-SFT-Think.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-0425-1B-SFT-Think-GGUF/resolve/main/OLMo-2-0425-1B-SFT-Think.Q4_K_M.gguf) | Q4_K_M | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-0425-1B-SFT-Think-GGUF/resolve/main/OLMo-2-0425-1B-SFT-Think.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-0425-1B-SFT-Think-GGUF/resolve/main/OLMo-2-0425-1B-SFT-Think.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-0425-1B-SFT-Think-GGUF/resolve/main/OLMo-2-0425-1B-SFT-Think.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-0425-1B-SFT-Think-GGUF/resolve/main/OLMo-2-0425-1B-SFT-Think.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-0425-1B-SFT-Think-GGUF/resolve/main/OLMo-2-0425-1B-SFT-Think.f16.gguf) | f16 | 3.1 | 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. + +