commit 6113f1a9e825841d6d1aaef899d163f2b6893d22 Author: ModelHub XC Date: Mon Apr 20 03:31:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f6b2266 --- /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 +BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.IQ4_XS.gguf b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.IQ4_XS.gguf new file mode 100644 index 0000000..59afa72 --- /dev/null +++ b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d422893798307b788ab5520772d6f1c5e14612795af4416ba412a332b4750e7 +size 902183520 diff --git a/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q2_K.gguf b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q2_K.gguf new file mode 100644 index 0000000..90eeb74 --- /dev/null +++ b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57f285903201ba1f19dff21a0c5d708d4d4357cd94d870ff95f0afee6bbcf41c +size 676305504 diff --git a/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q3_K_L.gguf b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q3_K_L.gguf new file mode 100644 index 0000000..eac946a --- /dev/null +++ b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c2841fdc1ac352c77074cc1b0a4e3144f793455d799132a0c2c1f5d6939073a +size 880163424 diff --git a/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q3_K_M.gguf b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q3_K_M.gguf new file mode 100644 index 0000000..405d0e8 --- /dev/null +++ b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4f4a21c7f218a79dad32c9c0e3968ffec060a5469b5f590475e40ac09ea962f +size 824179296 diff --git a/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q3_K_S.gguf b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q3_K_S.gguf new file mode 100644 index 0000000..bb736d8 --- /dev/null +++ b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ce6ba7d51e3c2df2bd6e3c1e6c78bfd949063b4e0c3176f3512df99396fcd38 +size 760945248 diff --git a/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q4_K_M.gguf b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q4_K_M.gguf new file mode 100644 index 0000000..d8e7293 --- /dev/null +++ b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de513eeee702c62f630bb57f1a2a64d9fda402dbd5053ea8cb40b8588d33a510 +size 986049120 diff --git a/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q4_K_S.gguf b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q4_K_S.gguf new file mode 100644 index 0000000..e30c890 --- /dev/null +++ b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d007bc88efb3308a71326021b08362b8b1697df2be944490a7a6a50a568a9a1 +size 940313184 diff --git a/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q5_K_M.gguf b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q5_K_M.gguf new file mode 100644 index 0000000..101953b --- /dev/null +++ b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b04b1923241431d6444e91242a4975ce561ad809c2242fa63da5740c1001a5bc +size 1125050976 diff --git a/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q5_K_S.gguf b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q5_K_S.gguf new file mode 100644 index 0000000..403c932 --- /dev/null +++ b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f2fb997d3508869e8fddedad9dc2dfaf0ebe03348f7eda3968f30c0cf083603 +size 1098730080 diff --git a/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q6_K.gguf b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q6_K.gguf new file mode 100644 index 0000000..ec632f3 --- /dev/null +++ b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:043c558652c487508ed6e301c53ed42b4aceef56976309d4fc825c0fe7351ca4 +size 1272740448 diff --git a/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q8_0.gguf b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q8_0.gguf new file mode 100644 index 0000000..ec4bedd --- /dev/null +++ b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:241e080284121ea80fe3d4bb3f945a3f8161a2d95767a0b7adfec1f3d106d21f +size 1646573664 diff --git a/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.f16.gguf b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.f16.gguf new file mode 100644 index 0000000..6da4a37 --- /dev/null +++ b/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4ee2d1c80a3995176d879ee2ef4459c8793e4ef040667a72c079fec24142d7d +size 3093669984 diff --git a/README.md b/README.md new file mode 100644 index 0000000..94b2b96 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: brishtiteveja/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO +datasets: AI-MO/NuminaMath-TIR +language: +- en +library_name: transformers +model_name: BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- open-r1 +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/brishtiteveja/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO-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/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO-GGUF/resolve/main/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO-GGUF/resolve/main/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO-GGUF/resolve/main/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO-GGUF/resolve/main/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO-GGUF/resolve/main/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO-GGUF/resolve/main/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO-GGUF/resolve/main/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO-GGUF/resolve/main/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO-GGUF/resolve/main/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO-GGUF/resolve/main/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO-GGUF/resolve/main/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO-GGUF/resolve/main/BanglaLLM-Qwen2.5-1.5B-Open-R1-GRPO.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. + +