commit 3157b6a4add3fae2586654dc422be2a9377f6d98 Author: ModelHub XC Date: Sat Jul 18 03:25:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-MATH-GRPO-len-control-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bcd1b32 --- /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 +Qwen3-4B-MATH-GRPO-len-control.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MATH-GRPO-len-control.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MATH-GRPO-len-control.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MATH-GRPO-len-control.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MATH-GRPO-len-control.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MATH-GRPO-len-control.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MATH-GRPO-len-control.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MATH-GRPO-len-control.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MATH-GRPO-len-control.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MATH-GRPO-len-control.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MATH-GRPO-len-control.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-MATH-GRPO-len-control.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-MATH-GRPO-len-control.IQ4_XS.gguf b/Qwen3-4B-MATH-GRPO-len-control.IQ4_XS.gguf new file mode 100644 index 0000000..7823d39 --- /dev/null +++ b/Qwen3-4B-MATH-GRPO-len-control.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49c0b3684cb2e97fea5d15910aeb070385460a08e16c91b468d43d4a6b00d96d +size 2286316320 diff --git a/Qwen3-4B-MATH-GRPO-len-control.Q2_K.gguf b/Qwen3-4B-MATH-GRPO-len-control.Q2_K.gguf new file mode 100644 index 0000000..370ba7f --- /dev/null +++ b/Qwen3-4B-MATH-GRPO-len-control.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dca1ad1ebead660aae07bd62c26cedea12669699ddf89c18e14c721293e11f8a +size 1669499680 diff --git a/Qwen3-4B-MATH-GRPO-len-control.Q3_K_L.gguf b/Qwen3-4B-MATH-GRPO-len-control.Q3_K_L.gguf new file mode 100644 index 0000000..06271ea --- /dev/null +++ b/Qwen3-4B-MATH-GRPO-len-control.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a01e969b25b598be7dfa7226222c29d53e940fc3ab04eebe7848df936c759418 +size 2239785760 diff --git a/Qwen3-4B-MATH-GRPO-len-control.Q3_K_M.gguf b/Qwen3-4B-MATH-GRPO-len-control.Q3_K_M.gguf new file mode 100644 index 0000000..c65b22e --- /dev/null +++ b/Qwen3-4B-MATH-GRPO-len-control.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acd5e0abdfd4d84f5311dbf370d3b42677e9c26ad494116c2ab255c442eff9f1 +size 2075618080 diff --git a/Qwen3-4B-MATH-GRPO-len-control.Q3_K_S.gguf b/Qwen3-4B-MATH-GRPO-len-control.Q3_K_S.gguf new file mode 100644 index 0000000..4eadf5f --- /dev/null +++ b/Qwen3-4B-MATH-GRPO-len-control.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2df55c79e3ae4b1bd3a59e743e0b66f56df29d02ea63727aedeae8bf76fea56 +size 1886997280 diff --git a/Qwen3-4B-MATH-GRPO-len-control.Q4_K_M.gguf b/Qwen3-4B-MATH-GRPO-len-control.Q4_K_M.gguf new file mode 100644 index 0000000..82d9ffa --- /dev/null +++ b/Qwen3-4B-MATH-GRPO-len-control.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2232bdd36b5e27058bb23f0f91bf20e800ac4741e11828d683cc51f25d3f57c +size 2497280800 diff --git a/Qwen3-4B-MATH-GRPO-len-control.Q4_K_S.gguf b/Qwen3-4B-MATH-GRPO-len-control.Q4_K_S.gguf new file mode 100644 index 0000000..536ae08 --- /dev/null +++ b/Qwen3-4B-MATH-GRPO-len-control.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:458b1d1e2db051646ececf8e245bf8d01bb1f21364c5e9b1a93ebf7abe2139e4 +size 2383309600 diff --git a/Qwen3-4B-MATH-GRPO-len-control.Q5_K_M.gguf b/Qwen3-4B-MATH-GRPO-len-control.Q5_K_M.gguf new file mode 100644 index 0000000..c6030a8 --- /dev/null +++ b/Qwen3-4B-MATH-GRPO-len-control.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d45a250548224db267044897c778393d5a169183d4bbe2ddebd7a5ed2e195c36 +size 2889513760 diff --git a/Qwen3-4B-MATH-GRPO-len-control.Q5_K_S.gguf b/Qwen3-4B-MATH-GRPO-len-control.Q5_K_S.gguf new file mode 100644 index 0000000..21e797e --- /dev/null +++ b/Qwen3-4B-MATH-GRPO-len-control.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08adfc13089646053c3ef4c5c45b489160a1ddb080e815d150f76a65079ee69c +size 2823711520 diff --git a/Qwen3-4B-MATH-GRPO-len-control.Q6_K.gguf b/Qwen3-4B-MATH-GRPO-len-control.Q6_K.gguf new file mode 100644 index 0000000..62f679c --- /dev/null +++ b/Qwen3-4B-MATH-GRPO-len-control.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb633b464d1c830e58a839a6f345de25ab5ac489918f84bb49001e25af89924d +size 3306261280 diff --git a/Qwen3-4B-MATH-GRPO-len-control.Q8_0.gguf b/Qwen3-4B-MATH-GRPO-len-control.Q8_0.gguf new file mode 100644 index 0000000..0f29fcf --- /dev/null +++ b/Qwen3-4B-MATH-GRPO-len-control.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ada8510cbd8da5d9a7ce4e7cbe4f20c31db4a96d0bc9efe48db8d49d19e398ab +size 4280405280 diff --git a/Qwen3-4B-MATH-GRPO-len-control.f16.gguf b/Qwen3-4B-MATH-GRPO-len-control.f16.gguf new file mode 100644 index 0000000..833f97a --- /dev/null +++ b/Qwen3-4B-MATH-GRPO-len-control.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ec89c4bc2172c739354db31f81c5a0fb816a565049eefcadf276c30bc6d58ac +size 8051285280 diff --git a/README.md b/README.md new file mode 100644 index 0000000..11b2c33 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: AmberYifan/Qwen3-4B-MATH-GRPO-len-control +language: +- en +library_name: transformers +model_name: Qwen3-4B-MATH-GRPO-len-control +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- grpo +--- +## About + + + + + + + + + +static quants of https://huggingface.co/AmberYifan/Qwen3-4B-MATH-GRPO-len-control + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-MATH-GRPO-len-control-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/Qwen3-4B-MATH-GRPO-len-control-GGUF/resolve/main/Qwen3-4B-MATH-GRPO-len-control.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MATH-GRPO-len-control-GGUF/resolve/main/Qwen3-4B-MATH-GRPO-len-control.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MATH-GRPO-len-control-GGUF/resolve/main/Qwen3-4B-MATH-GRPO-len-control.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MATH-GRPO-len-control-GGUF/resolve/main/Qwen3-4B-MATH-GRPO-len-control.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MATH-GRPO-len-control-GGUF/resolve/main/Qwen3-4B-MATH-GRPO-len-control.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MATH-GRPO-len-control-GGUF/resolve/main/Qwen3-4B-MATH-GRPO-len-control.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MATH-GRPO-len-control-GGUF/resolve/main/Qwen3-4B-MATH-GRPO-len-control.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MATH-GRPO-len-control-GGUF/resolve/main/Qwen3-4B-MATH-GRPO-len-control.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MATH-GRPO-len-control-GGUF/resolve/main/Qwen3-4B-MATH-GRPO-len-control.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MATH-GRPO-len-control-GGUF/resolve/main/Qwen3-4B-MATH-GRPO-len-control.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MATH-GRPO-len-control-GGUF/resolve/main/Qwen3-4B-MATH-GRPO-len-control.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-MATH-GRPO-len-control-GGUF/resolve/main/Qwen3-4B-MATH-GRPO-len-control.f16.gguf) | f16 | 8.2 | 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. + +