commit fa33e8f76e330e39cd067ca1b1988dce48cd5654 Author: ModelHub XC Date: Sun Jun 14 19:42:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OLMo-2-1124-7B-Instruct_SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..33c2297 --- /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-2-1124-7B-Instruct_SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct_SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct_SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct_SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct_SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct_SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct_SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct_SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct_SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct_SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct_SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OLMo-2-1124-7B-Instruct_SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OLMo-2-1124-7B-Instruct_SFT.IQ4_XS.gguf b/OLMo-2-1124-7B-Instruct_SFT.IQ4_XS.gguf new file mode 100644 index 0000000..92725b6 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct_SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:038993c15d8968e07681836a8bd3384802eb1a7f5d94ade59f71c415c336a59d +size 4029783776 diff --git a/OLMo-2-1124-7B-Instruct_SFT.Q2_K.gguf b/OLMo-2-1124-7B-Instruct_SFT.Q2_K.gguf new file mode 100644 index 0000000..bcb41cd --- /dev/null +++ b/OLMo-2-1124-7B-Instruct_SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cca39fe23f9fa4fd9feee35dca0b85a3152944c0112a7c8b6c25875d81b4ee7 +size 2858262240 diff --git a/OLMo-2-1124-7B-Instruct_SFT.Q3_K_L.gguf b/OLMo-2-1124-7B-Instruct_SFT.Q3_K_L.gguf new file mode 100644 index 0000000..904e3da --- /dev/null +++ b/OLMo-2-1124-7B-Instruct_SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f843f232aeccb69f79132e86f3f1e56ea98ce3fc703312c889ed0211151acccf +size 3950943968 diff --git a/OLMo-2-1124-7B-Instruct_SFT.Q3_K_M.gguf b/OLMo-2-1124-7B-Instruct_SFT.Q3_K_M.gguf new file mode 100644 index 0000000..361c22f --- /dev/null +++ b/OLMo-2-1124-7B-Instruct_SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04573ad2a0fe5b5bc00f3a85a3fc993df4a02897b1c8be2a3039ffb242b45e30 +size 3651837664 diff --git a/OLMo-2-1124-7B-Instruct_SFT.Q3_K_S.gguf b/OLMo-2-1124-7B-Instruct_SFT.Q3_K_S.gguf new file mode 100644 index 0000000..9ae173e --- /dev/null +++ b/OLMo-2-1124-7B-Instruct_SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3570a6d597eeebbbc72d8eae48e47603cb3605fab50d5ffe188800f8e2a826ee +size 3302137568 diff --git a/OLMo-2-1124-7B-Instruct_SFT.Q4_K_M.gguf b/OLMo-2-1124-7B-Instruct_SFT.Q4_K_M.gguf new file mode 100644 index 0000000..fe32c7e --- /dev/null +++ b/OLMo-2-1124-7B-Instruct_SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c51ec42b7b8639a70162cd53d9b8440d113ef33f1afcda3ed7b80e3c3249e0b7 +size 4472020704 diff --git a/OLMo-2-1124-7B-Instruct_SFT.Q4_K_S.gguf b/OLMo-2-1124-7B-Instruct_SFT.Q4_K_S.gguf new file mode 100644 index 0000000..18c455c --- /dev/null +++ b/OLMo-2-1124-7B-Instruct_SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb548c4b2075df5e7283d74ff6ae683ac4dd83707fc9e93628016522729af4e9 +size 4247756512 diff --git a/OLMo-2-1124-7B-Instruct_SFT.Q5_K_M.gguf b/OLMo-2-1124-7B-Instruct_SFT.Q5_K_M.gguf new file mode 100644 index 0000000..356197c --- /dev/null +++ b/OLMo-2-1124-7B-Instruct_SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6e5450b34d35815ca69a30202434bdc56b36b452e95530b01adb3b103de638c +size 5209169632 diff --git a/OLMo-2-1124-7B-Instruct_SFT.Q5_K_S.gguf b/OLMo-2-1124-7B-Instruct_SFT.Q5_K_S.gguf new file mode 100644 index 0000000..01cc190 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct_SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a84b20882d44c4fa3f35c2c3e3217b6e657a9607f7349eb706d9c135174a6345 +size 5077704416 diff --git a/OLMo-2-1124-7B-Instruct_SFT.Q6_K.gguf b/OLMo-2-1124-7B-Instruct_SFT.Q6_K.gguf new file mode 100644 index 0000000..1b07cd6 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct_SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4f51cd478a945e11e831e7bad4f088cebd526d2c2a7133e30439646f3ead2b3 +size 5992390368 diff --git a/OLMo-2-1124-7B-Instruct_SFT.Q8_0.gguf b/OLMo-2-1124-7B-Instruct_SFT.Q8_0.gguf new file mode 100644 index 0000000..eb96ec4 --- /dev/null +++ b/OLMo-2-1124-7B-Instruct_SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7839099d0a44927e0759a56d5aad0e30e38169afad3e32e3b815da5a925d63f0 +size 7759896288 diff --git a/OLMo-2-1124-7B-Instruct_SFT.f16.gguf b/OLMo-2-1124-7B-Instruct_SFT.f16.gguf new file mode 100644 index 0000000..811180f --- /dev/null +++ b/OLMo-2-1124-7B-Instruct_SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d72c57518a15d7535a1bd16d2a55c84589d98211e221998b75894c80f15d065 +size 14601854688 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dfa9f21 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: Neelectric/OLMo-2-1124-7B-Instruct_SFT +datasets: open-r1/OpenR1-Math-220k +language: +- en +library_name: transformers +model_name: OLMo-2-1124-7B-Instruct_SFT +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- open-r1 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/Neelectric/OLMo-2-1124-7B-Instruct_SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#OLMo-2-1124-7B-Instruct_SFT-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-2-1124-7B-Instruct_SFT-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_SFT.Q2_K.gguf) | Q2_K | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_SFT-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_SFT.Q3_K_S.gguf) | Q3_K_S | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_SFT-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_SFT.Q3_K_M.gguf) | Q3_K_M | 3.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_SFT-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_SFT.Q3_K_L.gguf) | Q3_K_L | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_SFT-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_SFT.IQ4_XS.gguf) | IQ4_XS | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_SFT-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_SFT.Q4_K_S.gguf) | Q4_K_S | 4.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_SFT-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_SFT.Q4_K_M.gguf) | Q4_K_M | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_SFT-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_SFT.Q5_K_S.gguf) | Q5_K_S | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_SFT-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_SFT.Q5_K_M.gguf) | Q5_K_M | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_SFT-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_SFT.Q6_K.gguf) | Q6_K | 6.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_SFT-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_SFT.Q8_0.gguf) | Q8_0 | 7.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OLMo-2-1124-7B-Instruct_SFT-GGUF/resolve/main/OLMo-2-1124-7B-Instruct_SFT.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. + +