commit 92964c253db715ce3678f527f84c500490a996da Author: ModelHub XC Date: Tue Apr 21 18:48:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-1.5B-Thinking-v1.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bd16ed4 --- /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 +Qwen2.5-1.5B-Thinking-v1.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking-v1.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-1.5B-Thinking-v1.1.IQ4_XS.gguf b/Qwen2.5-1.5B-Thinking-v1.1.IQ4_XS.gguf new file mode 100644 index 0000000..4ed484f --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00b36e1a0f8b750820bafc0b50ae3c8ae7c850a97b98224f588f3a79d9f031ae +size 902183552 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.Q2_K.gguf b/Qwen2.5-1.5B-Thinking-v1.1.Q2_K.gguf new file mode 100644 index 0000000..e9de905 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20ea52661509f8bb2e1de127dda49fbc87c14b5d4fda700afeb5bab2d1f78a2f +size 676305536 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.Q3_K_L.gguf b/Qwen2.5-1.5B-Thinking-v1.1.Q3_K_L.gguf new file mode 100644 index 0000000..0c61c8d --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbf0e0fab7feffcc1844555d30686f9ac35f78928c6da133562bee7c45321039 +size 880163456 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.Q3_K_M.gguf b/Qwen2.5-1.5B-Thinking-v1.1.Q3_K_M.gguf new file mode 100644 index 0000000..a49c576 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21b7fd74e386027b8e0860b5d37a81ab5f0977b45364942add2ae6064a12dfc3 +size 824179328 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.Q3_K_S.gguf b/Qwen2.5-1.5B-Thinking-v1.1.Q3_K_S.gguf new file mode 100644 index 0000000..2587635 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a2ddad16ad0fc11e59fa4fbc7925a5c96dee9eed4affcf3161cedb608ca627d +size 760945280 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.Q4_K_M.gguf b/Qwen2.5-1.5B-Thinking-v1.1.Q4_K_M.gguf new file mode 100644 index 0000000..fb3644f --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68544e03632ec914d6dd7c1c52a4336824d901c16c3434ed37fbd21e8488256d +size 986049152 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.Q4_K_S.gguf b/Qwen2.5-1.5B-Thinking-v1.1.Q4_K_S.gguf new file mode 100644 index 0000000..b340ee7 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e711f59ebfc4504463137353756ab9b4f1572a9babb8672475a707caaad3e476 +size 940313216 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.Q5_K_M.gguf b/Qwen2.5-1.5B-Thinking-v1.1.Q5_K_M.gguf new file mode 100644 index 0000000..067c942 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4489350e4f5b97d597470067becab170055395addc2e2871a2ef04469c020f8 +size 1125051008 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.Q5_K_S.gguf b/Qwen2.5-1.5B-Thinking-v1.1.Q5_K_S.gguf new file mode 100644 index 0000000..e714e60 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb3eb6fe530e83824ac02e7da29448e591e4e240198bdd6970b73ab30df69d1c +size 1098730112 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.Q6_K.gguf b/Qwen2.5-1.5B-Thinking-v1.1.Q6_K.gguf new file mode 100644 index 0000000..417f5a3 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e5ce3e09e73867be8533e645feac4abe8d6e870e76263c53c135fd400581975 +size 1272740480 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.Q8_0.gguf b/Qwen2.5-1.5B-Thinking-v1.1.Q8_0.gguf new file mode 100644 index 0000000..47128ac --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:422a5f3d397cd468a1281a163a3bb2cb53e4fb0288c5ca71a8c213da7cda245e +size 1646573696 diff --git a/Qwen2.5-1.5B-Thinking-v1.1.f16.gguf b/Qwen2.5-1.5B-Thinking-v1.1.f16.gguf new file mode 100644 index 0000000..bfeb608 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking-v1.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58a85c97344df845f089cb2dfd210200dc616824a7f14bddc6cf63d3bb2c4472 +size 3093670016 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8d4ba07 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: justinj92/Qwen2.5-1.5B-Thinking-v1.1 +datasets: +- microsoft/orca-math-word-problems-200k +language: +- en +library_name: transformers +model_name: Qwen2.5-1.5B-Thinking-v1.1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/justinj92/Qwen2.5-1.5B-Thinking-v1.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-i1-GGUF +## 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/Qwen2.5-1.5B-Thinking-v1.1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-v1.1-GGUF/resolve/main/Qwen2.5-1.5B-Thinking-v1.1.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. + +