commit ff172fd825055fcd4fb8ab0df24b603dd0b789af Author: ModelHub XC Date: Tue May 26 05:10:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GRM-RL-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..73d2f8d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +GRM-RL-7B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRM-RL-7B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +GRM-RL-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GRM-RL-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRM-RL-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRM-RL-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRM-RL-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GRM-RL-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GRM-RL-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GRM-RL-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +GRM-RL-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRM-RL-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GRM-RL-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GRM-RL-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GRM-RL-7B.IQ4_XS.gguf b/GRM-RL-7B.IQ4_XS.gguf new file mode 100644 index 0000000..d038bc8 --- /dev/null +++ b/GRM-RL-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df0e730bb5c3a047c824c732a86e54cad20749f634050ce573d1ee247891df2f +size 4250297248 diff --git a/GRM-RL-7B.Q2_K.gguf b/GRM-RL-7B.Q2_K.gguf new file mode 100644 index 0000000..1dd9e85 --- /dev/null +++ b/GRM-RL-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60358e0c9167ca3b5ba5458fe5d625babab39bc8222184cab64f7b5f76a66d75 +size 3015938976 diff --git a/GRM-RL-7B.Q3_K_L.gguf b/GRM-RL-7B.Q3_K_L.gguf new file mode 100644 index 0000000..ed921d9 --- /dev/null +++ b/GRM-RL-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dde29683310ef5d5f019711838cb8cede8d83862286d38b94333868d4bd7c836 +size 4088458144 diff --git a/GRM-RL-7B.Q3_K_M.gguf b/GRM-RL-7B.Q3_K_M.gguf new file mode 100644 index 0000000..48399dd --- /dev/null +++ b/GRM-RL-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b35de31f5c733e7fb822e165cc09b5e8fca0e560dafe7e894846cf154e59f15 +size 3808390048 diff --git a/GRM-RL-7B.Q3_K_S.gguf b/GRM-RL-7B.Q3_K_S.gguf new file mode 100644 index 0000000..25f1abf --- /dev/null +++ b/GRM-RL-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c308031ee0b77afe500527ebf57e4dce5520ddf838f2f1a281cd038a7391a5ed +size 3492367264 diff --git a/GRM-RL-7B.Q4_K_M.gguf b/GRM-RL-7B.Q4_K_M.gguf new file mode 100644 index 0000000..b910b51 --- /dev/null +++ b/GRM-RL-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94edc68bae5edfe5568317f9ae443712bb0824a5e68fd91fbdfc3c10dc88eb03 +size 4683072416 diff --git a/GRM-RL-7B.Q4_K_S.gguf b/GRM-RL-7B.Q4_K_S.gguf new file mode 100644 index 0000000..f5dd4f0 --- /dev/null +++ b/GRM-RL-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27b84c2d838dc497728f42ced572f035f8b6ad1b671cd011d15eb8a41015bf33 +size 4457767840 diff --git a/GRM-RL-7B.Q5_K_M.gguf b/GRM-RL-7B.Q5_K_M.gguf new file mode 100644 index 0000000..1dc7201 --- /dev/null +++ b/GRM-RL-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4415774aee42640a7f69fa359905733309dc699d101b52b02a9c2aed2c974f17 +size 5444830112 diff --git a/GRM-RL-7B.Q5_K_S.gguf b/GRM-RL-7B.Q5_K_S.gguf new file mode 100644 index 0000000..0fb4b99 --- /dev/null +++ b/GRM-RL-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6413b08fd5186bfdcb0d5444bd25110acf237f7572cbba7c3ae5b6dcea4ebf3 +size 5315175328 diff --git a/GRM-RL-7B.Q6_K.gguf b/GRM-RL-7B.Q6_K.gguf new file mode 100644 index 0000000..f02bf87 --- /dev/null +++ b/GRM-RL-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9aab41f191ee47771cfa91219676b3beeb98ee53dc9100ce2c1af0d802d11e5 +size 6254197664 diff --git a/GRM-RL-7B.Q8_0.gguf b/GRM-RL-7B.Q8_0.gguf new file mode 100644 index 0000000..f30591b --- /dev/null +++ b/GRM-RL-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4dcb045705a33ff2ab551a7c10f0d50c269fa27f3676a6d2b7689f7e5c4fcb4 +size 8098524064 diff --git a/GRM-RL-7B.f16.gguf b/GRM-RL-7B.f16.gguf new file mode 100644 index 0000000..9e96179 --- /dev/null +++ b/GRM-RL-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75902b5ede4ebfc58c340c0873ca2227538bc186b2a4ad8d60eecab2fb78a20b +size 15237852064 diff --git a/GRM-RL-7B.mmproj-Q8_0.gguf b/GRM-RL-7B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..31143fc --- /dev/null +++ b/GRM-RL-7B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8874bba07b9807b77c5255c9521896c0a9d52766b37523c9e63dfa15f9ae44b7 +size 853119680 diff --git a/GRM-RL-7B.mmproj-f16.gguf b/GRM-RL-7B.mmproj-f16.gguf new file mode 100644 index 0000000..aee028e --- /dev/null +++ b/GRM-RL-7B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91b5812faed815a6f1ae59947522be7b8b51096d569eb290e049368b5edf1018 +size 1354162880 diff --git a/README.md b/README.md new file mode 100644 index 0000000..94e6d4f --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: generative-rlhf-v/GRM-RL-7B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/generative-rlhf-v/GRM-RL-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GRM-RL-7B-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/GRM-RL-7B-GGUF/resolve/main/GRM-RL-7B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GRM-RL-7B-GGUF/resolve/main/GRM-RL-7B.mmproj-f16.gguf) | mmproj-f16 | 1.5 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/GRM-RL-7B-GGUF/resolve/main/GRM-RL-7B.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-RL-7B-GGUF/resolve/main/GRM-RL-7B.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-RL-7B-GGUF/resolve/main/GRM-RL-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GRM-RL-7B-GGUF/resolve/main/GRM-RL-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-RL-7B-GGUF/resolve/main/GRM-RL-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-RL-7B-GGUF/resolve/main/GRM-RL-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRM-RL-7B-GGUF/resolve/main/GRM-RL-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GRM-RL-7B-GGUF/resolve/main/GRM-RL-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-RL-7B-GGUF/resolve/main/GRM-RL-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/GRM-RL-7B-GGUF/resolve/main/GRM-RL-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GRM-RL-7B-GGUF/resolve/main/GRM-RL-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GRM-RL-7B-GGUF/resolve/main/GRM-RL-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. + +