commit 8c51748484caa69992d78af46bfd95c6458b2404 Author: ModelHub XC Date: Mon Jun 15 01:28:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-2.5-1.5B-Simple-RL-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c1c95d6 --- /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 +Qwen-2.5-1.5B-Simple-RL.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-1.5B-Simple-RL.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-1.5B-Simple-RL.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-1.5B-Simple-RL.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-1.5B-Simple-RL.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-1.5B-Simple-RL.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-1.5B-Simple-RL.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-1.5B-Simple-RL.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-1.5B-Simple-RL.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-1.5B-Simple-RL.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-1.5B-Simple-RL.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-2.5-1.5B-Simple-RL.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-2.5-1.5B-Simple-RL.IQ4_XS.gguf b/Qwen-2.5-1.5B-Simple-RL.IQ4_XS.gguf new file mode 100644 index 0000000..7f291b4 --- /dev/null +++ b/Qwen-2.5-1.5B-Simple-RL.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba36adc43e6e4f8e285ff4e432794a98a2a1471e42ce2c5aa22ea4b7b14a52d2 +size 1026163040 diff --git a/Qwen-2.5-1.5B-Simple-RL.Q2_K.gguf b/Qwen-2.5-1.5B-Simple-RL.Q2_K.gguf new file mode 100644 index 0000000..4c1bd0f --- /dev/null +++ b/Qwen-2.5-1.5B-Simple-RL.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43999878302afbd3661061bf785989a34478245a000ae1f94302f593fc365136 +size 752880992 diff --git a/Qwen-2.5-1.5B-Simple-RL.Q3_K_L.gguf b/Qwen-2.5-1.5B-Simple-RL.Q3_K_L.gguf new file mode 100644 index 0000000..be645e8 --- /dev/null +++ b/Qwen-2.5-1.5B-Simple-RL.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feb9484f59574b186d6b18e7d5b0564af5e8349fa2930b74d0a245abe0e31044 +size 980440928 diff --git a/Qwen-2.5-1.5B-Simple-RL.Q3_K_M.gguf b/Qwen-2.5-1.5B-Simple-RL.Q3_K_M.gguf new file mode 100644 index 0000000..6522501 --- /dev/null +++ b/Qwen-2.5-1.5B-Simple-RL.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35e81cdc4376ee1c2a025896f64eb7577479e24325f5e282dc5a8fa610b28331 +size 924456800 diff --git a/Qwen-2.5-1.5B-Simple-RL.Q3_K_S.gguf b/Qwen-2.5-1.5B-Simple-RL.Q3_K_S.gguf new file mode 100644 index 0000000..407fb52 --- /dev/null +++ b/Qwen-2.5-1.5B-Simple-RL.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd6282669236e5a09ce438b907d379007fcd5e12417f6b31597c72f1034d9f43 +size 861222752 diff --git a/Qwen-2.5-1.5B-Simple-RL.Q4_K_M.gguf b/Qwen-2.5-1.5B-Simple-RL.Q4_K_M.gguf new file mode 100644 index 0000000..2ccd2ec --- /dev/null +++ b/Qwen-2.5-1.5B-Simple-RL.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a64f4790f3f2ff4f93df4b5e2c25c74a9b1b0626a6d17480762ab0b01c29aad +size 1117321568 diff --git a/Qwen-2.5-1.5B-Simple-RL.Q4_K_S.gguf b/Qwen-2.5-1.5B-Simple-RL.Q4_K_S.gguf new file mode 100644 index 0000000..fe754dc --- /dev/null +++ b/Qwen-2.5-1.5B-Simple-RL.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6599a3a34b7190ab5b5643a9bb287034f155957ca68c7bd481fc7f62f24448bd +size 1071585632 diff --git a/Qwen-2.5-1.5B-Simple-RL.Q5_K_M.gguf b/Qwen-2.5-1.5B-Simple-RL.Q5_K_M.gguf new file mode 100644 index 0000000..05ee78f --- /dev/null +++ b/Qwen-2.5-1.5B-Simple-RL.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c25179cced568df79eddaf27d79317a65ddcd5810834f64425d497bd1bafc73b +size 1285495136 diff --git a/Qwen-2.5-1.5B-Simple-RL.Q5_K_S.gguf b/Qwen-2.5-1.5B-Simple-RL.Q5_K_S.gguf new file mode 100644 index 0000000..aeb156d --- /dev/null +++ b/Qwen-2.5-1.5B-Simple-RL.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c81731092d8215f00b5248f388e19abeb78b492999508dd3e94d5de6af14bda8 +size 1259174240 diff --git a/Qwen-2.5-1.5B-Simple-RL.Q6_K.gguf b/Qwen-2.5-1.5B-Simple-RL.Q6_K.gguf new file mode 100644 index 0000000..cbdef5c --- /dev/null +++ b/Qwen-2.5-1.5B-Simple-RL.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:220b0cfa78c74cc47bc88d7950f15b16b7d0738794f980020d6983c16f6d64fc +size 1464179552 diff --git a/Qwen-2.5-1.5B-Simple-RL.Q8_0.gguf b/Qwen-2.5-1.5B-Simple-RL.Q8_0.gguf new file mode 100644 index 0000000..791a163 --- /dev/null +++ b/Qwen-2.5-1.5B-Simple-RL.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:329922639d5b320acbf50783b0ad516c017f288243c37ce6dfd7cde26bae77df +size 1894532960 diff --git a/Qwen-2.5-1.5B-Simple-RL.f16.gguf b/Qwen-2.5-1.5B-Simple-RL.f16.gguf new file mode 100644 index 0000000..882ce02 --- /dev/null +++ b/Qwen-2.5-1.5B-Simple-RL.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2bfaa5ad3caf22acd59a67cd5cd180fd15d30a505897d001f3ea57d41c939c0 +size 3560417120 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c2e6e99 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: superdocker/Qwen-2.5-1.5B-Simple-RL +datasets: DigitalLearningGmbH/MATH-lighteval +language: +- en +library_name: transformers +model_name: Qwen-2.5-1.5B-Simple-RL +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- open-r1 +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/superdocker/Qwen-2.5-1.5B-Simple-RL + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen-2.5-1.5B-Simple-RL-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/Qwen-2.5-1.5B-Simple-RL-GGUF/resolve/main/Qwen-2.5-1.5B-Simple-RL.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-1.5B-Simple-RL-GGUF/resolve/main/Qwen-2.5-1.5B-Simple-RL.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-1.5B-Simple-RL-GGUF/resolve/main/Qwen-2.5-1.5B-Simple-RL.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-1.5B-Simple-RL-GGUF/resolve/main/Qwen-2.5-1.5B-Simple-RL.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-1.5B-Simple-RL-GGUF/resolve/main/Qwen-2.5-1.5B-Simple-RL.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-1.5B-Simple-RL-GGUF/resolve/main/Qwen-2.5-1.5B-Simple-RL.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-1.5B-Simple-RL-GGUF/resolve/main/Qwen-2.5-1.5B-Simple-RL.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-1.5B-Simple-RL-GGUF/resolve/main/Qwen-2.5-1.5B-Simple-RL.Q5_K_S.gguf) | Q5_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-1.5B-Simple-RL-GGUF/resolve/main/Qwen-2.5-1.5B-Simple-RL.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-1.5B-Simple-RL-GGUF/resolve/main/Qwen-2.5-1.5B-Simple-RL.Q6_K.gguf) | Q6_K | 1.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-1.5B-Simple-RL-GGUF/resolve/main/Qwen-2.5-1.5B-Simple-RL.Q8_0.gguf) | Q8_0 | 2.0 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-2.5-1.5B-Simple-RL-GGUF/resolve/main/Qwen-2.5-1.5B-Simple-RL.f16.gguf) | f16 | 3.7 | 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. + +