commit 513f9aad91cf19c7eae173d559d4be9345b7b2a4 Author: ModelHub XC Date: Tue Apr 28 14:42:32 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/SciRM-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5abe9e6 --- /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 +SciRM-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +SciRM-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SciRM-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SciRM-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SciRM-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +SciRM-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SciRM-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SciRM-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SciRM-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SciRM-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SciRM-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SciRM-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..dc62bac --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +arxiv: 2601.11374 +base_model: UKPLab/SciRM-7B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- reward-model +- scientific-writing +- evaluation +- reinforcement-learning +- text-generation +- grpo +--- +## About + + + + + + + + + +static quants of https://huggingface.co/UKPLab/SciRM-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#SciRM-7B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/SciRM-7B-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/SciRM-7B-GGUF/resolve/main/SciRM-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/SciRM-7B-GGUF/resolve/main/SciRM-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/SciRM-7B-GGUF/resolve/main/SciRM-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/SciRM-7B-GGUF/resolve/main/SciRM-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/SciRM-7B-GGUF/resolve/main/SciRM-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/SciRM-7B-GGUF/resolve/main/SciRM-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SciRM-7B-GGUF/resolve/main/SciRM-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/SciRM-7B-GGUF/resolve/main/SciRM-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/SciRM-7B-GGUF/resolve/main/SciRM-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/SciRM-7B-GGUF/resolve/main/SciRM-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/SciRM-7B-GGUF/resolve/main/SciRM-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/SciRM-7B-GGUF/resolve/main/SciRM-7B.f16.gguf) | f16 | 15.3 | 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. + + diff --git a/SciRM-7B.IQ4_XS.gguf b/SciRM-7B.IQ4_XS.gguf new file mode 100644 index 0000000..1a25ffc --- /dev/null +++ b/SciRM-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22468c27fe6aaf80364d9046b6c80c25ad9b8cbcf88af513c85f8daa0912441c +size 4250299136 diff --git a/SciRM-7B.Q2_K.gguf b/SciRM-7B.Q2_K.gguf new file mode 100644 index 0000000..a1db5a9 --- /dev/null +++ b/SciRM-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9e1d45d926c0d571f9aca9f39e67801761ab3fb6b33558ad88371599c7fcfe1 +size 3015940864 diff --git a/SciRM-7B.Q3_K_L.gguf b/SciRM-7B.Q3_K_L.gguf new file mode 100644 index 0000000..54235ce --- /dev/null +++ b/SciRM-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a02956a92613a2e7e77b92b0064e55eca074dd01d6d48a1e6e483505d0683137 +size 4088460032 diff --git a/SciRM-7B.Q3_K_M.gguf b/SciRM-7B.Q3_K_M.gguf new file mode 100644 index 0000000..73916f9 --- /dev/null +++ b/SciRM-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21e813b762027f963bbbb4a882c089af3e8594c5c3402faa98c9f923c9580ec9 +size 3808391936 diff --git a/SciRM-7B.Q3_K_S.gguf b/SciRM-7B.Q3_K_S.gguf new file mode 100644 index 0000000..c4dda2f --- /dev/null +++ b/SciRM-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1644ee0045f24582990e6bd6b804e3c0a3e1eb92899a30d7e938e8c4eb7751cc +size 3492369152 diff --git a/SciRM-7B.Q4_K_M.gguf b/SciRM-7B.Q4_K_M.gguf new file mode 100644 index 0000000..788876b --- /dev/null +++ b/SciRM-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df591c536bb9d38209fca1632671e18744724b6423a1958f2e84711ac5878a34 +size 4683074304 diff --git a/SciRM-7B.Q4_K_S.gguf b/SciRM-7B.Q4_K_S.gguf new file mode 100644 index 0000000..903a443 --- /dev/null +++ b/SciRM-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:975e5c6f830483fbe177ede2cefe937c5c2b179d00bde5b76f41b0f3b2f0c149 +size 4457769728 diff --git a/SciRM-7B.Q5_K_M.gguf b/SciRM-7B.Q5_K_M.gguf new file mode 100644 index 0000000..6723ce3 --- /dev/null +++ b/SciRM-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83819f3fcd4a71726a0d515602961959fac09e8c78eb501b30f227b162405615 +size 5444832000 diff --git a/SciRM-7B.Q5_K_S.gguf b/SciRM-7B.Q5_K_S.gguf new file mode 100644 index 0000000..0e9e4f3 --- /dev/null +++ b/SciRM-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:142f952f9b619e8d099fed0db866334b65529563ae3d80bfcb8f398af79f7183 +size 5315177216 diff --git a/SciRM-7B.Q6_K.gguf b/SciRM-7B.Q6_K.gguf new file mode 100644 index 0000000..7ea0b29 --- /dev/null +++ b/SciRM-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476c7bbe15aef1ac87a21426c109eb2b9ac94f5e1a8d47c8bf99b184cd906719 +size 6254199552 diff --git a/SciRM-7B.Q8_0.gguf b/SciRM-7B.Q8_0.gguf new file mode 100644 index 0000000..4489214 --- /dev/null +++ b/SciRM-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20ac8e5424e744724a0978f970a963824b151d9d4005f77bee568a87410b8e85 +size 8098525952 diff --git a/SciRM-7B.f16.gguf b/SciRM-7B.f16.gguf new file mode 100644 index 0000000..76bf11e --- /dev/null +++ b/SciRM-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e01cdd1b03c688d63eb7b3cbe95a83c65457a407853cd5e0f509575e558b26fb +size 15237853952