commit 2f5173e92c1079c845e6cf54136efe457cc2e29d Author: ModelHub XC Date: Sat May 9 13:06:42 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OLMo-1B-sft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f4bea7c --- /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-1B-sft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-1B-sft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-1B-sft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-1B-sft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-1B-sft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-1B-sft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-1B-sft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-1B-sft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-1B-sft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-1B-sft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-1B-sft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-1B-sft.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OLMo-1B-sft.IQ4_XS.gguf b/OLMo-1B-sft.IQ4_XS.gguf new file mode 100644 index 0000000..049ef04 --- /dev/null +++ b/OLMo-1B-sft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4092e949fe9d7cbcc5284a01de67ccfe7d82c8517c472b7467c9d025f60d1144 +size 691845760 diff --git a/OLMo-1B-sft.Q2_K.gguf b/OLMo-1B-sft.Q2_K.gguf new file mode 100644 index 0000000..09314da --- /dev/null +++ b/OLMo-1B-sft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75c347c47b82e8d235b009f66324a5e5da41262b21ceffe1298a8ce402eefe5a +size 556317312 diff --git a/OLMo-1B-sft.Q3_K_L.gguf b/OLMo-1B-sft.Q3_K_L.gguf new file mode 100644 index 0000000..a54ea84 --- /dev/null +++ b/OLMo-1B-sft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b63b6fd0587c76aeaa25794be89a9d537a9511b379a22caba04ea3ccb7ee5160 +size 685292160 diff --git a/OLMo-1B-sft.Q3_K_M.gguf b/OLMo-1B-sft.Q3_K_M.gguf new file mode 100644 index 0000000..b831a18 --- /dev/null +++ b/OLMo-1B-sft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b634efa02859498439333d746a436b82001dc9d2815a35a473222672c2544d +size 648592000 diff --git a/OLMo-1B-sft.Q3_K_S.gguf b/OLMo-1B-sft.Q3_K_S.gguf new file mode 100644 index 0000000..e0140e3 --- /dev/null +++ b/OLMo-1B-sft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ff61427d6f009f6ce0871fd0481eff3e3df6132a9536d4efcc2f4940490e966 +size 607435392 diff --git a/OLMo-1B-sft.Q4_K_M.gguf b/OLMo-1B-sft.Q4_K_M.gguf new file mode 100644 index 0000000..284e12a --- /dev/null +++ b/OLMo-1B-sft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a5380bd61394bfd2eef9077e273e2c5a48b5c97be796e48a7dc99c6cd24c7c3 +size 746830464 diff --git a/OLMo-1B-sft.Q4_K_S.gguf b/OLMo-1B-sft.Q4_K_S.gguf new file mode 100644 index 0000000..0731e94 --- /dev/null +++ b/OLMo-1B-sft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80ab319535c7cfb01f52585c36f416cd1597bc7736bdda77485639c463e8bc2f +size 718584448 diff --git a/OLMo-1B-sft.Q5_K_M.gguf b/OLMo-1B-sft.Q5_K_M.gguf new file mode 100644 index 0000000..8207da0 --- /dev/null +++ b/OLMo-1B-sft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:190464e3f4928ce738fc818af34171eca25d293ef7f20ec09e263c5b54f6358e +size 831765120 diff --git a/OLMo-1B-sft.Q5_K_S.gguf b/OLMo-1B-sft.Q5_K_S.gguf new file mode 100644 index 0000000..a6bddf8 --- /dev/null +++ b/OLMo-1B-sft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c199f94ce5ba5876f1b3fcc6c4c285a7ff148dc54d8c6552eac856dccb1d2b13 +size 815053440 diff --git a/OLMo-1B-sft.Q6_K.gguf b/OLMo-1B-sft.Q6_K.gguf new file mode 100644 index 0000000..2245525 --- /dev/null +++ b/OLMo-1B-sft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3beff8851608a804854b32354f1ec39dd917bd82ab569624943cf29e70f0fa62 +size 922008192 diff --git a/OLMo-1B-sft.Q8_0.gguf b/OLMo-1B-sft.Q8_0.gguf new file mode 100644 index 0000000..c279c4f --- /dev/null +++ b/OLMo-1B-sft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3904c13b13eddcced33271252bc41145f5b0875ab0e2b0e7bff99fc36e35076e +size 1192467072 diff --git a/OLMo-1B-sft.f16.gguf b/OLMo-1B-sft.f16.gguf new file mode 100644 index 0000000..b0cde7c --- /dev/null +++ b/OLMo-1B-sft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d356195b43bfc195995a86574b02e7f180eb86ccaee28236f304f3628fd8cdf5 +size 2239404672 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bf49dbd --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: ShowMakerTAT/OLMo-1B-sft +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/ShowMakerTAT/OLMo-1B-sft + + +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-1B-sft-GGUF/resolve/main/OLMo-1B-sft.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-1B-sft-GGUF/resolve/main/OLMo-1B-sft.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-1B-sft-GGUF/resolve/main/OLMo-1B-sft.Q3_K_M.gguf) | Q3_K_M | 0.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-1B-sft-GGUF/resolve/main/OLMo-1B-sft.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-1B-sft-GGUF/resolve/main/OLMo-1B-sft.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-1B-sft-GGUF/resolve/main/OLMo-1B-sft.Q4_K_S.gguf) | Q4_K_S | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OLMo-1B-sft-GGUF/resolve/main/OLMo-1B-sft.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OLMo-1B-sft-GGUF/resolve/main/OLMo-1B-sft.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-1B-sft-GGUF/resolve/main/OLMo-1B-sft.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-1B-sft-GGUF/resolve/main/OLMo-1B-sft.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-1B-sft-GGUF/resolve/main/OLMo-1B-sft.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-1B-sft-GGUF/resolve/main/OLMo-1B-sft.f16.gguf) | f16 | 2.3 | 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. + +