commit 0746ce4b07f8218fa306f8deb58cbe7334341a84 Author: ModelHub XC Date: Mon Jun 15 01:40:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Delphermes-8B-Math-GRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c5c7a45 --- /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 +Delphermes-8B-Math-GRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-8B-Math-GRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-8B-Math-GRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-8B-Math-GRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-8B-Math-GRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-8B-Math-GRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-8B-Math-GRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-8B-Math-GRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-8B-Math-GRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-8B-Math-GRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-8B-Math-GRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Delphermes-8B-Math-GRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Delphermes-8B-Math-GRPO.IQ4_XS.gguf b/Delphermes-8B-Math-GRPO.IQ4_XS.gguf new file mode 100644 index 0000000..0f02cc2 --- /dev/null +++ b/Delphermes-8B-Math-GRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7887909370ce836a4908c6e357b9b5173fefd6f51ecdaf26be857769d3218d72 +size 4593296704 diff --git a/Delphermes-8B-Math-GRPO.Q2_K.gguf b/Delphermes-8B-Math-GRPO.Q2_K.gguf new file mode 100644 index 0000000..12bcf3f --- /dev/null +++ b/Delphermes-8B-Math-GRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7acebc6b5e59f534338e3cfd8cd875876b135ceec9170ada857c2b4f66e0863 +size 3281732928 diff --git a/Delphermes-8B-Math-GRPO.Q3_K_L.gguf b/Delphermes-8B-Math-GRPO.Q3_K_L.gguf new file mode 100644 index 0000000..44b6720 --- /dev/null +++ b/Delphermes-8B-Math-GRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7945540b8d6cb8d83ebb5614ef3a2d2797579b6411330750c1396a4e522d0aee +size 4431394112 diff --git a/Delphermes-8B-Math-GRPO.Q3_K_M.gguf b/Delphermes-8B-Math-GRPO.Q3_K_M.gguf new file mode 100644 index 0000000..dd870aa --- /dev/null +++ b/Delphermes-8B-Math-GRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69ebc8db926a3efc4307bfc4546e5a1ac8627a5829adf73d5b5af54fdb6565af +size 4124161344 diff --git a/Delphermes-8B-Math-GRPO.Q3_K_S.gguf b/Delphermes-8B-Math-GRPO.Q3_K_S.gguf new file mode 100644 index 0000000..d91bfdb --- /dev/null +++ b/Delphermes-8B-Math-GRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e9fab1749e1b9e334ad05804ad2c9dd75c6dbd68d1b81c6ff3f3bc497212272 +size 3769611584 diff --git a/Delphermes-8B-Math-GRPO.Q4_K_M.gguf b/Delphermes-8B-Math-GRPO.Q4_K_M.gguf new file mode 100644 index 0000000..bc3ff60 --- /dev/null +++ b/Delphermes-8B-Math-GRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bf4c5c4bd1efc67490dc132fb0cea83081087187e152caa01f98091755c34cf +size 5027784000 diff --git a/Delphermes-8B-Math-GRPO.Q4_K_S.gguf b/Delphermes-8B-Math-GRPO.Q4_K_S.gguf new file mode 100644 index 0000000..6f00cdd --- /dev/null +++ b/Delphermes-8B-Math-GRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6d6ede39270a09d12baf1443506684ca9a891e1268923c097c8791cf2b18206 +size 4802012480 diff --git a/Delphermes-8B-Math-GRPO.Q5_K_M.gguf b/Delphermes-8B-Math-GRPO.Q5_K_M.gguf new file mode 100644 index 0000000..4f6a8cb --- /dev/null +++ b/Delphermes-8B-Math-GRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8c8e0870c68179c15c82cea7a9c94e0d16be4b6c4e640ac2d572a689e90d737 +size 5851112768 diff --git a/Delphermes-8B-Math-GRPO.Q5_K_S.gguf b/Delphermes-8B-Math-GRPO.Q5_K_S.gguf new file mode 100644 index 0000000..cc6951d --- /dev/null +++ b/Delphermes-8B-Math-GRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f786b5f3c9117042b83d68a0b09968d977379e464194bff93cfcf7b179d40ff +size 5720761664 diff --git a/Delphermes-8B-Math-GRPO.Q6_K.gguf b/Delphermes-8B-Math-GRPO.Q6_K.gguf new file mode 100644 index 0000000..f180db6 --- /dev/null +++ b/Delphermes-8B-Math-GRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98dae2524e641aba6746ef1b37d34fc05b55e0af513ecf929fe5c37d3eb3c564 +size 6725899584 diff --git a/Delphermes-8B-Math-GRPO.Q8_0.gguf b/Delphermes-8B-Math-GRPO.Q8_0.gguf new file mode 100644 index 0000000..04ef3fd --- /dev/null +++ b/Delphermes-8B-Math-GRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17d5d099c6f5b391d2beb58285ba81d6a75b7271178c182bf5ec7634352e6cf3 +size 8709518656 diff --git a/Delphermes-8B-Math-GRPO.f16.gguf b/Delphermes-8B-Math-GRPO.f16.gguf new file mode 100644 index 0000000..6c9cbd7 --- /dev/null +++ b/Delphermes-8B-Math-GRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c263f5eecb5cecbc63b6eb680620ce9b89ef7a35b3df3d1dd866986e9668c374 +size 16388044096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..231ed9d --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: justinj92/Delphermes-8B-Math-GRPO +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/justinj92/Delphermes-8B-Math-GRPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Delphermes-8B-Math-GRPO-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Delphermes-8B-Math-GRPO-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/Delphermes-8B-Math-GRPO-GGUF/resolve/main/Delphermes-8B-Math-GRPO.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-8B-Math-GRPO-GGUF/resolve/main/Delphermes-8B-Math-GRPO.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-8B-Math-GRPO-GGUF/resolve/main/Delphermes-8B-Math-GRPO.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-8B-Math-GRPO-GGUF/resolve/main/Delphermes-8B-Math-GRPO.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-8B-Math-GRPO-GGUF/resolve/main/Delphermes-8B-Math-GRPO.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-8B-Math-GRPO-GGUF/resolve/main/Delphermes-8B-Math-GRPO.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-8B-Math-GRPO-GGUF/resolve/main/Delphermes-8B-Math-GRPO.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-8B-Math-GRPO-GGUF/resolve/main/Delphermes-8B-Math-GRPO.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-8B-Math-GRPO-GGUF/resolve/main/Delphermes-8B-Math-GRPO.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-8B-Math-GRPO-GGUF/resolve/main/Delphermes-8B-Math-GRPO.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-8B-Math-GRPO-GGUF/resolve/main/Delphermes-8B-Math-GRPO.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Delphermes-8B-Math-GRPO-GGUF/resolve/main/Delphermes-8B-Math-GRPO.f16.gguf) | f16 | 16.5 | 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. + +