commit f4dfe294a11420ae9e7c52de5e83550334208ad7 Author: ModelHub XC Date: Mon Oct 5 20:23:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/OpenRS-TinyLlamaGRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8577f69 --- /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 +OpenRS-TinyLlamaGRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +OpenRS-TinyLlamaGRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenRS-TinyLlamaGRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +OpenRS-TinyLlamaGRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenRS-TinyLlamaGRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenRS-TinyLlamaGRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenRS-TinyLlamaGRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenRS-TinyLlamaGRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +OpenRS-TinyLlamaGRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +OpenRS-TinyLlamaGRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +OpenRS-TinyLlamaGRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +OpenRS-TinyLlamaGRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/OpenRS-TinyLlamaGRPO.IQ4_XS.gguf b/OpenRS-TinyLlamaGRPO.IQ4_XS.gguf new file mode 100644 index 0000000..f20f600 --- /dev/null +++ b/OpenRS-TinyLlamaGRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a383621e2139ba4970b5828608ee1b6271bab33a066bf461be73e5d5c4bd2de +size 609809024 diff --git a/OpenRS-TinyLlamaGRPO.Q2_K.gguf b/OpenRS-TinyLlamaGRPO.Q2_K.gguf new file mode 100644 index 0000000..6471e9d --- /dev/null +++ b/OpenRS-TinyLlamaGRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26efb095552223231cb0534c4e6b4efaf7c1b914ae3be73175e446b938e2552d +size 432132736 diff --git a/OpenRS-TinyLlamaGRPO.Q3_K_L.gguf b/OpenRS-TinyLlamaGRPO.Q3_K_L.gguf new file mode 100644 index 0000000..f69568a --- /dev/null +++ b/OpenRS-TinyLlamaGRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d0592120d368dd84d4f23aace739bb777e0b32208ba8ed280a759822c9634b4 +size 591528576 diff --git a/OpenRS-TinyLlamaGRPO.Q3_K_M.gguf b/OpenRS-TinyLlamaGRPO.Q3_K_M.gguf new file mode 100644 index 0000000..d8163e7 --- /dev/null +++ b/OpenRS-TinyLlamaGRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba754d699f59abbf565094368f52882d492296010ddcb8852227f905ff2c384a +size 548405888 diff --git a/OpenRS-TinyLlamaGRPO.Q3_K_S.gguf b/OpenRS-TinyLlamaGRPO.Q3_K_S.gguf new file mode 100644 index 0000000..15a9e47 --- /dev/null +++ b/OpenRS-TinyLlamaGRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6706add94776e04b9bfcf9ff946e56e0c33e2475ee90a76d4995b0749b8e4c5e +size 499344000 diff --git a/OpenRS-TinyLlamaGRPO.Q4_K_M.gguf b/OpenRS-TinyLlamaGRPO.Q4_K_M.gguf new file mode 100644 index 0000000..9d3970f --- /dev/null +++ b/OpenRS-TinyLlamaGRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88b3162ca31dd7ef92abe014e6df53016f9d3f0e0fefbebb56b3414d479635d8 +size 667816576 diff --git a/OpenRS-TinyLlamaGRPO.Q4_K_S.gguf b/OpenRS-TinyLlamaGRPO.Q4_K_S.gguf new file mode 100644 index 0000000..a3c2e9d --- /dev/null +++ b/OpenRS-TinyLlamaGRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eb93b502e080d7cf936d265adf7f3c7b7e6abfe64734d30ada7b526cf9fd9cc +size 639873664 diff --git a/OpenRS-TinyLlamaGRPO.Q5_K_M.gguf b/OpenRS-TinyLlamaGRPO.Q5_K_M.gguf new file mode 100644 index 0000000..2b6d14e --- /dev/null +++ b/OpenRS-TinyLlamaGRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3924567157b4c0fdc4c2b6963b95fea6e209d18bf31f3600decc9e0797147c82 +size 782045824 diff --git a/OpenRS-TinyLlamaGRPO.Q5_K_S.gguf b/OpenRS-TinyLlamaGRPO.Q5_K_S.gguf new file mode 100644 index 0000000..73edbb2 --- /dev/null +++ b/OpenRS-TinyLlamaGRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f69388df2d64995a3cd206600730474462793a5401fb1c373d0007b37da4ee2c +size 766030464 diff --git a/OpenRS-TinyLlamaGRPO.Q6_K.gguf b/OpenRS-TinyLlamaGRPO.Q6_K.gguf new file mode 100644 index 0000000..01b467f --- /dev/null +++ b/OpenRS-TinyLlamaGRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0be24020eefdda9db5a9c81bf8f1bb1a38df6f003286d6b5dea588c15a0144e2 +size 903414400 diff --git a/OpenRS-TinyLlamaGRPO.Q8_0.gguf b/OpenRS-TinyLlamaGRPO.Q8_0.gguf new file mode 100644 index 0000000..bbabc5a --- /dev/null +++ b/OpenRS-TinyLlamaGRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d40f0a293a5a46d5ce24e4261bf2e639b1efcaddbfedc603976461c66addf259 +size 1169810048 diff --git a/OpenRS-TinyLlamaGRPO.f16.gguf b/OpenRS-TinyLlamaGRPO.f16.gguf new file mode 100644 index 0000000..523368b --- /dev/null +++ b/OpenRS-TinyLlamaGRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc459d72900eb3832e568a74d9b8536438ebcb823aa797e8b079f7e93228917c +size 2201019008 diff --git a/README.md b/README.md new file mode 100644 index 0000000..af166a7 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: SomayJalan/OpenRS-TinyLlamaGRPO +datasets: knoveleng/open-rs +language: +- en +library_name: transformers +model_name: OpenRS-TinyLlamaGRPO +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- open-r1 +- trl +- grpo +--- +## About + + + + + + + + + +static quants of https://huggingface.co/SomayJalan/OpenRS-TinyLlamaGRPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#OpenRS-TinyLlamaGRPO-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/OpenRS-TinyLlamaGRPO-GGUF/resolve/main/OpenRS-TinyLlamaGRPO.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/OpenRS-TinyLlamaGRPO-GGUF/resolve/main/OpenRS-TinyLlamaGRPO.Q3_K_S.gguf) | Q3_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/OpenRS-TinyLlamaGRPO-GGUF/resolve/main/OpenRS-TinyLlamaGRPO.Q3_K_M.gguf) | Q3_K_M | 0.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/OpenRS-TinyLlamaGRPO-GGUF/resolve/main/OpenRS-TinyLlamaGRPO.Q3_K_L.gguf) | Q3_K_L | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/OpenRS-TinyLlamaGRPO-GGUF/resolve/main/OpenRS-TinyLlamaGRPO.IQ4_XS.gguf) | IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/OpenRS-TinyLlamaGRPO-GGUF/resolve/main/OpenRS-TinyLlamaGRPO.Q4_K_S.gguf) | Q4_K_S | 0.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenRS-TinyLlamaGRPO-GGUF/resolve/main/OpenRS-TinyLlamaGRPO.Q4_K_M.gguf) | Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/OpenRS-TinyLlamaGRPO-GGUF/resolve/main/OpenRS-TinyLlamaGRPO.Q5_K_S.gguf) | Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/OpenRS-TinyLlamaGRPO-GGUF/resolve/main/OpenRS-TinyLlamaGRPO.Q5_K_M.gguf) | Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/OpenRS-TinyLlamaGRPO-GGUF/resolve/main/OpenRS-TinyLlamaGRPO.Q6_K.gguf) | Q6_K | 1.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/OpenRS-TinyLlamaGRPO-GGUF/resolve/main/OpenRS-TinyLlamaGRPO.Q8_0.gguf) | Q8_0 | 1.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/OpenRS-TinyLlamaGRPO-GGUF/resolve/main/OpenRS-TinyLlamaGRPO.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. + +