commit fa4fb37d6e96b3244d319d5499670b1d6facfddf Author: ModelHub XC Date: Thu Jun 4 18:08:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-1.5B-Code-GRPO-dense-reward-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..14ff201 --- /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 +Qwen2.5-1.5B-Code-GRPO-dense-reward.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-dense-reward.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-dense-reward.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-dense-reward.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-dense-reward.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-dense-reward.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-dense-reward.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-dense-reward.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-dense-reward.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-dense-reward.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-dense-reward.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Code-GRPO-dense-reward.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-1.5B-Code-GRPO-dense-reward.IQ4_XS.gguf b/Qwen2.5-1.5B-Code-GRPO-dense-reward.IQ4_XS.gguf new file mode 100644 index 0000000..7c4dce2 --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-dense-reward.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eebece7ccbcabc145b7846e6702c8e6f89d2187ebca9ced374c257d627738891 +size 902183552 diff --git a/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q2_K.gguf b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q2_K.gguf new file mode 100644 index 0000000..2ceca83 --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99f61da8f77c5f214112fb960d9bbde2fb1b17d26c8b04f032e10717d184ef98 +size 676305536 diff --git a/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q3_K_L.gguf b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q3_K_L.gguf new file mode 100644 index 0000000..8c71cf5 --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e7f89723fd752090ee804da256b5cf79fef8de0654f5a71912e0a857b879590 +size 880163456 diff --git a/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q3_K_M.gguf b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q3_K_M.gguf new file mode 100644 index 0000000..8a7189c --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:544335b815fc1aa20b6264a657ff0a0a1e2b5909551b1bcd701c7cc57f5badcf +size 824179328 diff --git a/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q3_K_S.gguf b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q3_K_S.gguf new file mode 100644 index 0000000..bcaa55e --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d17337a0646e749a3da1bf7696a7d590d37bf6d8eb661cf691e403454949bdc +size 760945280 diff --git a/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q4_K_M.gguf b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q4_K_M.gguf new file mode 100644 index 0000000..136a636 --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4574a7430635231839d225b57a83a1216acf3cf9e9f202ca1034006d46c9a1a6 +size 986049152 diff --git a/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q4_K_S.gguf b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q4_K_S.gguf new file mode 100644 index 0000000..f63de51 --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1d7cf7451c36de5bdc997c47c48bf10cbb6907d38d3b2a0bbeee09664691966 +size 940313216 diff --git a/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q5_K_M.gguf b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q5_K_M.gguf new file mode 100644 index 0000000..26d2aca --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f50b78032f995d3e8507ada3de31a66e5506c5aee583cf8c0add943e6856b931 +size 1125051008 diff --git a/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q5_K_S.gguf b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q5_K_S.gguf new file mode 100644 index 0000000..8096e4e --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e93fa221a1aef6ab97737ab29d2e80bee930eabb59e27a3fbd0a83aa05175568 +size 1098730112 diff --git a/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q6_K.gguf b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q6_K.gguf new file mode 100644 index 0000000..1cd9941 --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f96a78f0155876f52160d3cf194fdbc1fe5656be3343e1b164f9382c97e2ccd +size 1272740480 diff --git a/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q8_0.gguf b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q8_0.gguf new file mode 100644 index 0000000..8d4995c --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34db1b94191aa49ab5787ee1ca20b01b20323337decb51138612f98ca05f8813 +size 1646573696 diff --git a/Qwen2.5-1.5B-Code-GRPO-dense-reward.f16.gguf b/Qwen2.5-1.5B-Code-GRPO-dense-reward.f16.gguf new file mode 100644 index 0000000..3bca6c3 --- /dev/null +++ b/Qwen2.5-1.5B-Code-GRPO-dense-reward.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1f4ed93a165a69fed0ba786ab5e10c2befbec8d6cb816ba10b59bb3655016f1 +size 3093670016 diff --git a/README.md b/README.md new file mode 100644 index 0000000..59f7d4d --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: AmberYifan/Qwen2.5-1.5B-Code-GRPO-dense-reward +datasets: open-r1/verifiable-coding-problems-python +language: +- en +library_name: transformers +model_name: Qwen2.5-1.5B-Code-GRPO-dense-reward +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- open-r1 +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Qwen2.5-1.5B-Code-GRPO-dense-reward + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-1.5B-Code-GRPO-dense-reward-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/Qwen2.5-1.5B-Code-GRPO-dense-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-dense-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-dense-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-dense-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-dense-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-dense-reward.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-dense-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-dense-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-dense-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-dense-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-dense-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-dense-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-dense-reward.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Code-GRPO-dense-reward-GGUF/resolve/main/Qwen2.5-1.5B-Code-GRPO-dense-reward.f16.gguf) | f16 | 3.2 | 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. + +