commit 4ade85b79fcf193a72ab2b560d479d406a47f6df Author: ModelHub XC Date: Thu Jun 4 11:30:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OLMo-2-1B-7x-WD0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d18b7dd --- /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-2-1B-7x-WD0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1B-7x-WD0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1B-7x-WD0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1B-7x-WD0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1B-7x-WD0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1B-7x-WD0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1B-7x-WD0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1B-7x-WD0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1B-7x-WD0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1B-7x-WD0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1B-7x-WD0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1B-7x-WD0.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OLMo-2-1B-7x-WD0.IQ4_XS.gguf b/OLMo-2-1B-7x-WD0.IQ4_XS.gguf new file mode 100644 index 0000000..4be9d80 --- /dev/null +++ b/OLMo-2-1B-7x-WD0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02062698883d362b989ec1a198fab6009d515d2b778c97f857746520e805dca9 +size 857526336 diff --git a/OLMo-2-1B-7x-WD0.Q2_K.gguf b/OLMo-2-1B-7x-WD0.Q2_K.gguf new file mode 100644 index 0000000..1f48a51 --- /dev/null +++ b/OLMo-2-1B-7x-WD0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:084baee781f49db9cd95a5793caa59470276d4e014f95419651072a26780c93a +size 633327680 diff --git a/OLMo-2-1B-7x-WD0.Q3_K_L.gguf b/OLMo-2-1B-7x-WD0.Q3_K_L.gguf new file mode 100644 index 0000000..0547dbd --- /dev/null +++ b/OLMo-2-1B-7x-WD0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edbd6aa911a37aebca348ae177fee5ac4e5ebeeb181be7e62231ebeb6b27e936 +size 826167360 diff --git a/OLMo-2-1B-7x-WD0.Q3_K_M.gguf b/OLMo-2-1B-7x-WD0.Q3_K_M.gguf new file mode 100644 index 0000000..f4c869e --- /dev/null +++ b/OLMo-2-1B-7x-WD0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1d1e6fe12888f842263c83a670074d057860e1eb6ea347bd01ecd17aaedd29d +size 778981440 diff --git a/OLMo-2-1B-7x-WD0.Q3_K_S.gguf b/OLMo-2-1B-7x-WD0.Q3_K_S.gguf new file mode 100644 index 0000000..cf23370 --- /dev/null +++ b/OLMo-2-1B-7x-WD0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1bfae45ebfbc8eb55a84bf2cda49758c508bc721accb4927d9202aaa232d79a +size 722358336 diff --git a/OLMo-2-1B-7x-WD0.Q4_K_M.gguf b/OLMo-2-1B-7x-WD0.Q4_K_M.gguf new file mode 100644 index 0000000..d1ed84e --- /dev/null +++ b/OLMo-2-1B-7x-WD0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c5e39175fd8ce32302d9d1a8e3eaa9812d69fcae72808f9899963c1cf5f52f1 +size 935514176 diff --git a/OLMo-2-1B-7x-WD0.Q4_K_S.gguf b/OLMo-2-1B-7x-WD0.Q4_K_S.gguf new file mode 100644 index 0000000..699096d --- /dev/null +++ b/OLMo-2-1B-7x-WD0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0c5ec109127ba149161ba2916741bb945ef10a4e564d4b2cd9ae8a7b339c4bc +size 898551872 diff --git a/OLMo-2-1B-7x-WD0.Q5_K_M.gguf b/OLMo-2-1B-7x-WD0.Q5_K_M.gguf new file mode 100644 index 0000000..c11eea9 --- /dev/null +++ b/OLMo-2-1B-7x-WD0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9d462a3c9d01270b6df10f6dd0490b6a9a18d41a589152ac8feba9eaaaa12cc +size 1074450496 diff --git a/OLMo-2-1B-7x-WD0.Q5_K_S.gguf b/OLMo-2-1B-7x-WD0.Q5_K_S.gguf new file mode 100644 index 0000000..93c3700 --- /dev/null +++ b/OLMo-2-1B-7x-WD0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:885ecb8b97c8fc68edc5d9d8e43ef5b0eac19645dc17a922a1a1b574a59ead58 +size 1052168256 diff --git a/OLMo-2-1B-7x-WD0.Q6_K.gguf b/OLMo-2-1B-7x-WD0.Q6_K.gguf new file mode 100644 index 0000000..28c9006 --- /dev/null +++ b/OLMo-2-1B-7x-WD0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aeff8375778572fe733d86f8787209ae6d5d313ecdc559bfab8d200bd852ff5 +size 1222070336 diff --git a/OLMo-2-1B-7x-WD0.Q8_0.gguf b/OLMo-2-1B-7x-WD0.Q8_0.gguf new file mode 100644 index 0000000..6ae4d9f --- /dev/null +++ b/OLMo-2-1B-7x-WD0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dbe8aa41f3cc0e3a7f308739fee4df10a8c9e63644e962818a7b9d4eb5e3505 +size 1581666368 diff --git a/OLMo-2-1B-7x-WD0.f16.gguf b/OLMo-2-1B-7x-WD0.f16.gguf new file mode 100644 index 0000000..540143a --- /dev/null +++ b/OLMo-2-1B-7x-WD0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91c9cb2cad1941a575c8a0e4350384473aff574d638992e30df230bdd6584506 +size 2973651008 diff --git a/README.md b/README.md new file mode 100644 index 0000000..59312d9 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: sbordt/OLMo-2-1B-7x-WD0 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/sbordt/OLMo-2-1B-7x-WD0 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#OLMo-2-1B-7x-WD0-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-2-1B-7x-WD0-GGUF/resolve/main/OLMo-2-1B-7x-WD0.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1B-7x-WD0-GGUF/resolve/main/OLMo-2-1B-7x-WD0.Q3_K_S.gguf) | Q3_K_S | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1B-7x-WD0-GGUF/resolve/main/OLMo-2-1B-7x-WD0.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1B-7x-WD0-GGUF/resolve/main/OLMo-2-1B-7x-WD0.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1B-7x-WD0-GGUF/resolve/main/OLMo-2-1B-7x-WD0.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1B-7x-WD0-GGUF/resolve/main/OLMo-2-1B-7x-WD0.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1B-7x-WD0-GGUF/resolve/main/OLMo-2-1B-7x-WD0.Q4_K_M.gguf) | Q4_K_M | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1B-7x-WD0-GGUF/resolve/main/OLMo-2-1B-7x-WD0.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1B-7x-WD0-GGUF/resolve/main/OLMo-2-1B-7x-WD0.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1B-7x-WD0-GGUF/resolve/main/OLMo-2-1B-7x-WD0.Q6_K.gguf) | Q6_K | 1.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1B-7x-WD0-GGUF/resolve/main/OLMo-2-1B-7x-WD0.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1B-7x-WD0-GGUF/resolve/main/OLMo-2-1B-7x-WD0.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. + +