commit 0ce81f52f873c98e1352f34dfbf03748faf82308 Author: ModelHub XC Date: Wed Jul 22 13:02:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-3B-R1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..74ad1f1 --- /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 +Qwen2.5-3B-R1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-R1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-R1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-R1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-R1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-R1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-R1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-R1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-R1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-R1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-R1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-R1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-3B-R1.IQ4_XS.gguf b/Qwen2.5-3B-R1.IQ4_XS.gguf new file mode 100644 index 0000000..83ded94 --- /dev/null +++ b/Qwen2.5-3B-R1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2be4f6e4febc078dc9bca63b971884779669ed77a3b5a172afeacaa6f2445dab +size 1753185760 diff --git a/Qwen2.5-3B-R1.Q2_K.gguf b/Qwen2.5-3B-R1.Q2_K.gguf new file mode 100644 index 0000000..4a4b208 --- /dev/null +++ b/Qwen2.5-3B-R1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:703c5fab5017bb7fa630fd4249f186678d8d2858bc194d41257161217e6c96fd +size 1274756576 diff --git a/Qwen2.5-3B-R1.Q3_K_L.gguf b/Qwen2.5-3B-R1.Q3_K_L.gguf new file mode 100644 index 0000000..4e87091 --- /dev/null +++ b/Qwen2.5-3B-R1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:122ae7a37fe23ec55c448d471e174296be87ea28a08e9a9a1906be6278eb02a7 +size 1707392480 diff --git a/Qwen2.5-3B-R1.Q3_K_M.gguf b/Qwen2.5-3B-R1.Q3_K_M.gguf new file mode 100644 index 0000000..13b0b1f --- /dev/null +++ b/Qwen2.5-3B-R1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b1f24008a99df3322550db16423400ab9b23dd24ded9749e12e67df6ab0edb3 +size 1590476256 diff --git a/Qwen2.5-3B-R1.Q3_K_S.gguf b/Qwen2.5-3B-R1.Q3_K_S.gguf new file mode 100644 index 0000000..17a310f --- /dev/null +++ b/Qwen2.5-3B-R1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d366b888ba61469ce65059a5ef899dedb666c2959fa7c15f6377a7d7f2c4cf7 +size 1454357984 diff --git a/Qwen2.5-3B-R1.Q4_K_M.gguf b/Qwen2.5-3B-R1.Q4_K_M.gguf new file mode 100644 index 0000000..d61a774 --- /dev/null +++ b/Qwen2.5-3B-R1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df6c01e9d48baf1eb705d744d4034b26bf6a8142edc93621ffa7c4d05d807912 +size 1929903584 diff --git a/Qwen2.5-3B-R1.Q4_K_S.gguf b/Qwen2.5-3B-R1.Q4_K_S.gguf new file mode 100644 index 0000000..075c91f --- /dev/null +++ b/Qwen2.5-3B-R1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:704444b9b61d475bf3e269d2678e2f7e2b7c9d6c54545afd42d6e3db1a8ee1cb +size 1834384864 diff --git a/Qwen2.5-3B-R1.Q5_K_M.gguf b/Qwen2.5-3B-R1.Q5_K_M.gguf new file mode 100644 index 0000000..cbbc316 --- /dev/null +++ b/Qwen2.5-3B-R1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac6728284c4c64ad113a9713d48f201f471d8a1aba675fcc94d204dd0f56af9e +size 2224815584 diff --git a/Qwen2.5-3B-R1.Q5_K_S.gguf b/Qwen2.5-3B-R1.Q5_K_S.gguf new file mode 100644 index 0000000..34aaf3c --- /dev/null +++ b/Qwen2.5-3B-R1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bcc4e0385beabe73e1ef33b3ae49802b8163dccec189f170306a19eee13ec1e +size 2169667040 diff --git a/Qwen2.5-3B-R1.Q6_K.gguf b/Qwen2.5-3B-R1.Q6_K.gguf new file mode 100644 index 0000000..a799c4e --- /dev/null +++ b/Qwen2.5-3B-R1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2d51bc748950f368a59a3ef4fde808bf22ed5ff583a2fef7be84134c1428e74 +size 2538159584 diff --git a/Qwen2.5-3B-R1.Q8_0.gguf b/Qwen2.5-3B-R1.Q8_0.gguf new file mode 100644 index 0000000..6adc24e --- /dev/null +++ b/Qwen2.5-3B-R1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:260f05643fdca4b792c61ac0497ad74c02e299bbe73f2d1935303769981849c3 +size 3285476832 diff --git a/Qwen2.5-3B-R1.f16.gguf b/Qwen2.5-3B-R1.f16.gguf new file mode 100644 index 0000000..e2bc301 --- /dev/null +++ b/Qwen2.5-3B-R1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faa7a671b9bc03dc6aa304083962d5d37d02fd40eb30940051f0032e5065af28 +size 6178317792 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e686474 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: SunJack/Qwen2.5-3B-R1 +datasets: +- openai/gsm8k +language: +- en +- zh +library_name: transformers +license: mit +quantized_by: mradermacher +tags: +- unsloth +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/SunJack/Qwen2.5-3B-R1 + + +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/Qwen2.5-3B-R1-GGUF/resolve/main/Qwen2.5-3B-R1.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-R1-GGUF/resolve/main/Qwen2.5-3B-R1.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-R1-GGUF/resolve/main/Qwen2.5-3B-R1.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-R1-GGUF/resolve/main/Qwen2.5-3B-R1.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-R1-GGUF/resolve/main/Qwen2.5-3B-R1.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-R1-GGUF/resolve/main/Qwen2.5-3B-R1.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-R1-GGUF/resolve/main/Qwen2.5-3B-R1.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-R1-GGUF/resolve/main/Qwen2.5-3B-R1.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-R1-GGUF/resolve/main/Qwen2.5-3B-R1.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-R1-GGUF/resolve/main/Qwen2.5-3B-R1.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-R1-GGUF/resolve/main/Qwen2.5-3B-R1.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-R1-GGUF/resolve/main/Qwen2.5-3B-R1.f16.gguf) | f16 | 6.3 | 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. + +