commit 2b7915bf66f13799708d97828aabbffc0a1ff5f9 Author: ModelHub XC Date: Mon Jun 15 00:32:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Superoptimizer_Qwen7B_GRPO2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a78c615 --- /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 +Superoptimizer_Qwen7B_GRPO2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Superoptimizer_Qwen7B_GRPO2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Superoptimizer_Qwen7B_GRPO2.f16.gguf filter=lfs diff=lfs merge=lfs -text +Superoptimizer_Qwen7B_GRPO2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Superoptimizer_Qwen7B_GRPO2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Superoptimizer_Qwen7B_GRPO2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Superoptimizer_Qwen7B_GRPO2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Superoptimizer_Qwen7B_GRPO2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Superoptimizer_Qwen7B_GRPO2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Superoptimizer_Qwen7B_GRPO2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Superoptimizer_Qwen7B_GRPO2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Superoptimizer_Qwen7B_GRPO2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..73cfdc4 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: tarsur909/Superoptimizer_Qwen7B_GRPO2 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/tarsur909/Superoptimizer_Qwen7B_GRPO2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Superoptimizer_Qwen7B_GRPO2-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/Superoptimizer_Qwen7B_GRPO2-GGUF/resolve/main/Superoptimizer_Qwen7B_GRPO2.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Superoptimizer_Qwen7B_GRPO2-GGUF/resolve/main/Superoptimizer_Qwen7B_GRPO2.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Superoptimizer_Qwen7B_GRPO2-GGUF/resolve/main/Superoptimizer_Qwen7B_GRPO2.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Superoptimizer_Qwen7B_GRPO2-GGUF/resolve/main/Superoptimizer_Qwen7B_GRPO2.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Superoptimizer_Qwen7B_GRPO2-GGUF/resolve/main/Superoptimizer_Qwen7B_GRPO2.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Superoptimizer_Qwen7B_GRPO2-GGUF/resolve/main/Superoptimizer_Qwen7B_GRPO2.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Superoptimizer_Qwen7B_GRPO2-GGUF/resolve/main/Superoptimizer_Qwen7B_GRPO2.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Superoptimizer_Qwen7B_GRPO2-GGUF/resolve/main/Superoptimizer_Qwen7B_GRPO2.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Superoptimizer_Qwen7B_GRPO2-GGUF/resolve/main/Superoptimizer_Qwen7B_GRPO2.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Superoptimizer_Qwen7B_GRPO2-GGUF/resolve/main/Superoptimizer_Qwen7B_GRPO2.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Superoptimizer_Qwen7B_GRPO2-GGUF/resolve/main/Superoptimizer_Qwen7B_GRPO2.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Superoptimizer_Qwen7B_GRPO2-GGUF/resolve/main/Superoptimizer_Qwen7B_GRPO2.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/Superoptimizer_Qwen7B_GRPO2.IQ4_XS.gguf b/Superoptimizer_Qwen7B_GRPO2.IQ4_XS.gguf new file mode 100644 index 0000000..24770c7 --- /dev/null +++ b/Superoptimizer_Qwen7B_GRPO2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6caaf7ae8ae55fbccb85c6cae7d280a5be6d1963b525e3ff3bb22bf837644017 +size 4250298656 diff --git a/Superoptimizer_Qwen7B_GRPO2.Q2_K.gguf b/Superoptimizer_Qwen7B_GRPO2.Q2_K.gguf new file mode 100644 index 0000000..81a5da6 --- /dev/null +++ b/Superoptimizer_Qwen7B_GRPO2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd45aa30dcdd175143440fb270ac17222baa3f1b363a616b90044b2a3c21f7bb +size 3015940384 diff --git a/Superoptimizer_Qwen7B_GRPO2.Q3_K_L.gguf b/Superoptimizer_Qwen7B_GRPO2.Q3_K_L.gguf new file mode 100644 index 0000000..d43e6fc --- /dev/null +++ b/Superoptimizer_Qwen7B_GRPO2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62f02d1c32ca02562ad10bed88115539fa7f04cb6d318361af1c601280ce9b31 +size 4088459552 diff --git a/Superoptimizer_Qwen7B_GRPO2.Q3_K_M.gguf b/Superoptimizer_Qwen7B_GRPO2.Q3_K_M.gguf new file mode 100644 index 0000000..dbd95b2 --- /dev/null +++ b/Superoptimizer_Qwen7B_GRPO2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de34150da5cebedc14f6eb28d95ca2cfb510c429a67e05fd9cb36f13cb3a80ab +size 3808391456 diff --git a/Superoptimizer_Qwen7B_GRPO2.Q3_K_S.gguf b/Superoptimizer_Qwen7B_GRPO2.Q3_K_S.gguf new file mode 100644 index 0000000..5c26382 --- /dev/null +++ b/Superoptimizer_Qwen7B_GRPO2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e255e3c7b6d4b6f850b3bea9c7bfd9a09455447d25bc8b2040ae153b302a7ff +size 3492368672 diff --git a/Superoptimizer_Qwen7B_GRPO2.Q4_K_M.gguf b/Superoptimizer_Qwen7B_GRPO2.Q4_K_M.gguf new file mode 100644 index 0000000..16c7b28 --- /dev/null +++ b/Superoptimizer_Qwen7B_GRPO2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:250301dfb1128c2399b6a3e3671aac3df1b01bfcfbc3378244e36e0110e12131 +size 4683073824 diff --git a/Superoptimizer_Qwen7B_GRPO2.Q4_K_S.gguf b/Superoptimizer_Qwen7B_GRPO2.Q4_K_S.gguf new file mode 100644 index 0000000..37b80e6 --- /dev/null +++ b/Superoptimizer_Qwen7B_GRPO2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99a9daab56f94a99b94deeb2aad879c62eb31f7430db4a6a13701e47155f5d7d +size 4457769248 diff --git a/Superoptimizer_Qwen7B_GRPO2.Q5_K_M.gguf b/Superoptimizer_Qwen7B_GRPO2.Q5_K_M.gguf new file mode 100644 index 0000000..05465ba --- /dev/null +++ b/Superoptimizer_Qwen7B_GRPO2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:209acc20f77123c05d690ed1deed8185eee8e3a2e97c6d12bd3ccaa81f6198cc +size 5444831520 diff --git a/Superoptimizer_Qwen7B_GRPO2.Q5_K_S.gguf b/Superoptimizer_Qwen7B_GRPO2.Q5_K_S.gguf new file mode 100644 index 0000000..45c2995 --- /dev/null +++ b/Superoptimizer_Qwen7B_GRPO2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63980fb00951efda3936c40459e5a9c24d4dac3b2bee9b6a3c80c5cf77d12ce3 +size 5315176736 diff --git a/Superoptimizer_Qwen7B_GRPO2.Q6_K.gguf b/Superoptimizer_Qwen7B_GRPO2.Q6_K.gguf new file mode 100644 index 0000000..e587362 --- /dev/null +++ b/Superoptimizer_Qwen7B_GRPO2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c69af6f120f9169da2dac7e373228e3ab9fb53ef47671fea4164e66ec88b431 +size 6254199072 diff --git a/Superoptimizer_Qwen7B_GRPO2.Q8_0.gguf b/Superoptimizer_Qwen7B_GRPO2.Q8_0.gguf new file mode 100644 index 0000000..2435e0a --- /dev/null +++ b/Superoptimizer_Qwen7B_GRPO2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:103641579924283821a161c08428947b8216bec69364c1506625767a7ec41c2a +size 8098525472 diff --git a/Superoptimizer_Qwen7B_GRPO2.f16.gguf b/Superoptimizer_Qwen7B_GRPO2.f16.gguf new file mode 100644 index 0000000..2f17400 --- /dev/null +++ b/Superoptimizer_Qwen7B_GRPO2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b34ea11ca5d37cd7f289810f713a976b7bdad1657a2798b8f1f136c563134f4 +size 15237853472