commit c7fb52bed2e5ac802e63ebac24ff5257463c9916 Author: ModelHub XC Date: Sun Jun 14 20:38:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-Base-DeepMath10K-PPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..caca00a --- /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-Base-DeepMath10K-PPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base-DeepMath10K-PPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base-DeepMath10K-PPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base-DeepMath10K-PPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base-DeepMath10K-PPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base-DeepMath10K-PPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base-DeepMath10K-PPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base-DeepMath10K-PPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base-DeepMath10K-PPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base-DeepMath10K-PPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base-DeepMath10K-PPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-Base-DeepMath10K-PPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-Base-DeepMath10K-PPO.IQ4_XS.gguf b/Qwen3-4B-Base-DeepMath10K-PPO.IQ4_XS.gguf new file mode 100644 index 0000000..e8cfb01 --- /dev/null +++ b/Qwen3-4B-Base-DeepMath10K-PPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1efe1990811e508158d9d5150051c66fb2035de9763cde72bf03146f0e3e33f6 +size 2492949248 diff --git a/Qwen3-4B-Base-DeepMath10K-PPO.Q2_K.gguf b/Qwen3-4B-Base-DeepMath10K-PPO.Q2_K.gguf new file mode 100644 index 0000000..20c56bf --- /dev/null +++ b/Qwen3-4B-Base-DeepMath10K-PPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4f2f30107f4a427e1f743ed6f6d8eee4caa768ff4a67fa914a6759b31d2d5d4 +size 1797125888 diff --git a/Qwen3-4B-Base-DeepMath10K-PPO.Q3_K_L.gguf b/Qwen3-4B-Base-DeepMath10K-PPO.Q3_K_L.gguf new file mode 100644 index 0000000..f7e850a --- /dev/null +++ b/Qwen3-4B-Base-DeepMath10K-PPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc74b5b83e14ed7b979ffbea7ac295639cf62b3b7cb61bf5e174cb69fe98ab47 +size 2406915328 diff --git a/Qwen3-4B-Base-DeepMath10K-PPO.Q3_K_M.gguf b/Qwen3-4B-Base-DeepMath10K-PPO.Q3_K_M.gguf new file mode 100644 index 0000000..daac4a8 --- /dev/null +++ b/Qwen3-4B-Base-DeepMath10K-PPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fdb9d08f7fa6f6643eb9338a411cd63314c2615e369344e06e67fcc2581d34d +size 2242747648 diff --git a/Qwen3-4B-Base-DeepMath10K-PPO.Q3_K_S.gguf b/Qwen3-4B-Base-DeepMath10K-PPO.Q3_K_S.gguf new file mode 100644 index 0000000..f3799fc --- /dev/null +++ b/Qwen3-4B-Base-DeepMath10K-PPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cc02784995342d991624fd722e6ba1811263a3c9961d8723747d5e8c1c84546 +size 2054126848 diff --git a/Qwen3-4B-Base-DeepMath10K-PPO.Q4_K_M.gguf b/Qwen3-4B-Base-DeepMath10K-PPO.Q4_K_M.gguf new file mode 100644 index 0000000..c5af231 --- /dev/null +++ b/Qwen3-4B-Base-DeepMath10K-PPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03bbeff536ee2542d59d6cb292f8ea7588d058741a5ba1e1e92ff233942d9aad +size 2716068608 diff --git a/Qwen3-4B-Base-DeepMath10K-PPO.Q4_K_S.gguf b/Qwen3-4B-Base-DeepMath10K-PPO.Q4_K_S.gguf new file mode 100644 index 0000000..3aefd9f --- /dev/null +++ b/Qwen3-4B-Base-DeepMath10K-PPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43c2634cbdf3f7c22a3f7d6fbcbcfb42894889b4fd625d8107e3779334e339ae +size 2602097408 diff --git a/Qwen3-4B-Base-DeepMath10K-PPO.Q5_K_M.gguf b/Qwen3-4B-Base-DeepMath10K-PPO.Q5_K_M.gguf new file mode 100644 index 0000000..7359efd --- /dev/null +++ b/Qwen3-4B-Base-DeepMath10K-PPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62784f857be5e35d426ec41229ff239d40a0f082a529a6ecdc6e1d939a8f3ce0 +size 3156921088 diff --git a/Qwen3-4B-Base-DeepMath10K-PPO.Q5_K_S.gguf b/Qwen3-4B-Base-DeepMath10K-PPO.Q5_K_S.gguf new file mode 100644 index 0000000..a599b43 --- /dev/null +++ b/Qwen3-4B-Base-DeepMath10K-PPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:016ffa74e67da8e0cef153b783f8d998f0b0238c68b2ba3b6cf9d67e3d1b9890 +size 3091118848 diff --git a/Qwen3-4B-Base-DeepMath10K-PPO.Q6_K.gguf b/Qwen3-4B-Base-DeepMath10K-PPO.Q6_K.gguf new file mode 100644 index 0000000..cf0db8c --- /dev/null +++ b/Qwen3-4B-Base-DeepMath10K-PPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed1e06e16dc0a4dba33c944c1e208559281778fe234db1e012882e2afd7be655 +size 3625326848 diff --git a/Qwen3-4B-Base-DeepMath10K-PPO.Q8_0.gguf b/Qwen3-4B-Base-DeepMath10K-PPO.Q8_0.gguf new file mode 100644 index 0000000..7eb6309 --- /dev/null +++ b/Qwen3-4B-Base-DeepMath10K-PPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71c19212d346b80e53bf487f1faa649fedd9d51554c830c0a31e0b5ce36d0bc4 +size 4693671168 diff --git a/Qwen3-4B-Base-DeepMath10K-PPO.f16.gguf b/Qwen3-4B-Base-DeepMath10K-PPO.f16.gguf new file mode 100644 index 0000000..0408713 --- /dev/null +++ b/Qwen3-4B-Base-DeepMath10K-PPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7583013d74e664b0b709ccb89c7cb7d4c5aaee3ef003bcd3f70bb860fec8b795 +size 8829197568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5e18f54 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: xiaoyuanliu/Qwen3-4B-Base-DeepMath10K-PPO +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/xiaoyuanliu/Qwen3-4B-Base-DeepMath10K-PPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-Base-DeepMath10K-PPO-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-Base-DeepMath10K-PPO-GGUF/resolve/main/Qwen3-4B-Base-DeepMath10K-PPO.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-DeepMath10K-PPO-GGUF/resolve/main/Qwen3-4B-Base-DeepMath10K-PPO.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-DeepMath10K-PPO-GGUF/resolve/main/Qwen3-4B-Base-DeepMath10K-PPO.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-DeepMath10K-PPO-GGUF/resolve/main/Qwen3-4B-Base-DeepMath10K-PPO.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-DeepMath10K-PPO-GGUF/resolve/main/Qwen3-4B-Base-DeepMath10K-PPO.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-DeepMath10K-PPO-GGUF/resolve/main/Qwen3-4B-Base-DeepMath10K-PPO.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-DeepMath10K-PPO-GGUF/resolve/main/Qwen3-4B-Base-DeepMath10K-PPO.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-DeepMath10K-PPO-GGUF/resolve/main/Qwen3-4B-Base-DeepMath10K-PPO.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-DeepMath10K-PPO-GGUF/resolve/main/Qwen3-4B-Base-DeepMath10K-PPO.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-DeepMath10K-PPO-GGUF/resolve/main/Qwen3-4B-Base-DeepMath10K-PPO.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-DeepMath10K-PPO-GGUF/resolve/main/Qwen3-4B-Base-DeepMath10K-PPO.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-Base-DeepMath10K-PPO-GGUF/resolve/main/Qwen3-4B-Base-DeepMath10K-PPO.f16.gguf) | f16 | 8.9 | 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. + +