commit b52c0c09d7ec914bb954f4e3ecaac9ee15172b13 Author: ModelHub XC Date: Fri Jul 3 00:44:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-3B-Instruct-reasoning-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..43d8ed4 --- /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-Instruct-reasoning.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-reasoning.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-reasoning.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-reasoning.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-reasoning.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-reasoning.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-reasoning.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-reasoning.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-reasoning.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-reasoning.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-reasoning.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-Instruct-reasoning.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-3B-Instruct-reasoning.IQ4_XS.gguf b/Qwen2.5-3B-Instruct-reasoning.IQ4_XS.gguf new file mode 100644 index 0000000..141ec79 --- /dev/null +++ b/Qwen2.5-3B-Instruct-reasoning.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb6f71340768591fd4012a377c2bb9d3fa438959ac805876e72088eb7398d4fe +size 1753185664 diff --git a/Qwen2.5-3B-Instruct-reasoning.Q2_K.gguf b/Qwen2.5-3B-Instruct-reasoning.Q2_K.gguf new file mode 100644 index 0000000..db88ba5 --- /dev/null +++ b/Qwen2.5-3B-Instruct-reasoning.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfd064498ac78647fd4fc915dd238acf28ab8826b98846c113b495e084420fe5 +size 1274756480 diff --git a/Qwen2.5-3B-Instruct-reasoning.Q3_K_L.gguf b/Qwen2.5-3B-Instruct-reasoning.Q3_K_L.gguf new file mode 100644 index 0000000..a9aae11 --- /dev/null +++ b/Qwen2.5-3B-Instruct-reasoning.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30f24610879ea0ee3fa28f08310336f0c6d49983a6488d8b869241443b85225b +size 1707392384 diff --git a/Qwen2.5-3B-Instruct-reasoning.Q3_K_M.gguf b/Qwen2.5-3B-Instruct-reasoning.Q3_K_M.gguf new file mode 100644 index 0000000..f113aca --- /dev/null +++ b/Qwen2.5-3B-Instruct-reasoning.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8532557765771673f4eb0d797313cf983f110dd3ac8a0fd8bdc148aeaac6accd +size 1590476160 diff --git a/Qwen2.5-3B-Instruct-reasoning.Q3_K_S.gguf b/Qwen2.5-3B-Instruct-reasoning.Q3_K_S.gguf new file mode 100644 index 0000000..e6b5d07 --- /dev/null +++ b/Qwen2.5-3B-Instruct-reasoning.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8085c37cf66a50c74ac559b32409ccc6fc1a156409caa522d34550c88aaf6444 +size 1454357888 diff --git a/Qwen2.5-3B-Instruct-reasoning.Q4_K_M.gguf b/Qwen2.5-3B-Instruct-reasoning.Q4_K_M.gguf new file mode 100644 index 0000000..c82ecbb --- /dev/null +++ b/Qwen2.5-3B-Instruct-reasoning.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:392a2921be61e702a6c1cd78efbc0957e4d2178b1001276e64aed4cae587dc6d +size 1929903488 diff --git a/Qwen2.5-3B-Instruct-reasoning.Q4_K_S.gguf b/Qwen2.5-3B-Instruct-reasoning.Q4_K_S.gguf new file mode 100644 index 0000000..f38f5ec --- /dev/null +++ b/Qwen2.5-3B-Instruct-reasoning.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8ceebe30c6cfd00d5fbde712dfbf74010613b9cd2bc9065beea8016746f2230 +size 1834384768 diff --git a/Qwen2.5-3B-Instruct-reasoning.Q5_K_M.gguf b/Qwen2.5-3B-Instruct-reasoning.Q5_K_M.gguf new file mode 100644 index 0000000..de361a2 --- /dev/null +++ b/Qwen2.5-3B-Instruct-reasoning.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:536cae3ba473baf7d5ff0d87eafdf4acec9d59909010828b551f2663e00d7890 +size 2224815488 diff --git a/Qwen2.5-3B-Instruct-reasoning.Q5_K_S.gguf b/Qwen2.5-3B-Instruct-reasoning.Q5_K_S.gguf new file mode 100644 index 0000000..8fefc4e --- /dev/null +++ b/Qwen2.5-3B-Instruct-reasoning.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa9e721f0d245a0d3e13310f67f5ec9e057eb5815cd9d3af11f1da6538d3d97e +size 2169666944 diff --git a/Qwen2.5-3B-Instruct-reasoning.Q6_K.gguf b/Qwen2.5-3B-Instruct-reasoning.Q6_K.gguf new file mode 100644 index 0000000..44bdc28 --- /dev/null +++ b/Qwen2.5-3B-Instruct-reasoning.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16a6b3f0f64a28edd31e139f197d52ccb2c170594834b7381ffbced42cde258f +size 2538159488 diff --git a/Qwen2.5-3B-Instruct-reasoning.Q8_0.gguf b/Qwen2.5-3B-Instruct-reasoning.Q8_0.gguf new file mode 100644 index 0000000..0fd95c4 --- /dev/null +++ b/Qwen2.5-3B-Instruct-reasoning.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afeb0452973f9b41d9d77c6632f2227409c255c67bf68091ee24cd13f8d9a328 +size 3285476736 diff --git a/Qwen2.5-3B-Instruct-reasoning.f16.gguf b/Qwen2.5-3B-Instruct-reasoning.f16.gguf new file mode 100644 index 0000000..3e5fe39 --- /dev/null +++ b/Qwen2.5-3B-Instruct-reasoning.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55589985f7d91287b308d0c2ba8ecfe0f1224c3124297fe0f094834f60a85125 +size 6178317696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f1b9449 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: shaktiman404/Qwen2.5-3B-Instruct-reasoning +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/shaktiman404/Qwen2.5-3B-Instruct-reasoning + + +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-Instruct-reasoning-GGUF/resolve/main/Qwen2.5-3B-Instruct-reasoning.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-reasoning-GGUF/resolve/main/Qwen2.5-3B-Instruct-reasoning.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-reasoning-GGUF/resolve/main/Qwen2.5-3B-Instruct-reasoning.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-reasoning-GGUF/resolve/main/Qwen2.5-3B-Instruct-reasoning.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-reasoning-GGUF/resolve/main/Qwen2.5-3B-Instruct-reasoning.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-reasoning-GGUF/resolve/main/Qwen2.5-3B-Instruct-reasoning.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-reasoning-GGUF/resolve/main/Qwen2.5-3B-Instruct-reasoning.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-reasoning-GGUF/resolve/main/Qwen2.5-3B-Instruct-reasoning.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-reasoning-GGUF/resolve/main/Qwen2.5-3B-Instruct-reasoning.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-reasoning-GGUF/resolve/main/Qwen2.5-3B-Instruct-reasoning.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-reasoning-GGUF/resolve/main/Qwen2.5-3B-Instruct-reasoning.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-Instruct-reasoning-GGUF/resolve/main/Qwen2.5-3B-Instruct-reasoning.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. + +