commit 42b3fc76d1f53ef9de223e96911d183de41ba1f0 Author: ModelHub XC Date: Thu Jul 16 18:24:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-1.5B-Thinking-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7ed17c5 --- /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.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-1.5B-Thinking.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-1.5B-Thinking.IQ4_XS.gguf b/Qwen2.5-1.5B-Thinking.IQ4_XS.gguf new file mode 100644 index 0000000..effd472 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86dcdc7520bd888b66b518d3ecce00895c412308cb70a968e6304e7c624e454e +size 902183520 diff --git a/Qwen2.5-1.5B-Thinking.Q2_K.gguf b/Qwen2.5-1.5B-Thinking.Q2_K.gguf new file mode 100644 index 0000000..3a09c85 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9da2089204d1c007f6b30e9ded9429ad8c30e3736feef75e531171824ea35e53 +size 676305504 diff --git a/Qwen2.5-1.5B-Thinking.Q3_K_L.gguf b/Qwen2.5-1.5B-Thinking.Q3_K_L.gguf new file mode 100644 index 0000000..c8f9f00 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c773125bfd2fcbf5bba1b565d2f933a91f69db66ecf37f9a7bce05cc265213a +size 880163424 diff --git a/Qwen2.5-1.5B-Thinking.Q3_K_M.gguf b/Qwen2.5-1.5B-Thinking.Q3_K_M.gguf new file mode 100644 index 0000000..651a316 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9a525d30705a19cc70e476d782e965eed5ad93091854105660c657b80a6565b +size 824179296 diff --git a/Qwen2.5-1.5B-Thinking.Q3_K_S.gguf b/Qwen2.5-1.5B-Thinking.Q3_K_S.gguf new file mode 100644 index 0000000..c2e656e --- /dev/null +++ b/Qwen2.5-1.5B-Thinking.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fe87ed0f68953b24049b320db62b538f409531e5bb68e8acdb44748750b0276 +size 760945248 diff --git a/Qwen2.5-1.5B-Thinking.Q4_K_M.gguf b/Qwen2.5-1.5B-Thinking.Q4_K_M.gguf new file mode 100644 index 0000000..779d4e7 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eebd74d1a2ba96a054b57a44b089b51c3de49efe4ab37f7702bbed5f518ff17 +size 986049120 diff --git a/Qwen2.5-1.5B-Thinking.Q4_K_S.gguf b/Qwen2.5-1.5B-Thinking.Q4_K_S.gguf new file mode 100644 index 0000000..fa6ebeb --- /dev/null +++ b/Qwen2.5-1.5B-Thinking.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:280faf45c9e62b5b071f33b7f4074f43fd88555db91e282d18fa0cb2c859d540 +size 940313184 diff --git a/Qwen2.5-1.5B-Thinking.Q5_K_M.gguf b/Qwen2.5-1.5B-Thinking.Q5_K_M.gguf new file mode 100644 index 0000000..4bf94a0 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f82c56239093c6e6af578e4d92d1e443b86cafb9da85b611c2596c3939f2770a +size 1125050976 diff --git a/Qwen2.5-1.5B-Thinking.Q5_K_S.gguf b/Qwen2.5-1.5B-Thinking.Q5_K_S.gguf new file mode 100644 index 0000000..9a46e46 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d7c9a3fe3a284e84ae1448b4ae76e3c32734ce96e739ea03f50f492327f461b +size 1098730080 diff --git a/Qwen2.5-1.5B-Thinking.Q6_K.gguf b/Qwen2.5-1.5B-Thinking.Q6_K.gguf new file mode 100644 index 0000000..33b59f0 --- /dev/null +++ b/Qwen2.5-1.5B-Thinking.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c76bc5712d2781feac3efecacbed9e863accda24949e250f31edae206d20c6b +size 1272740448 diff --git a/Qwen2.5-1.5B-Thinking.Q8_0.gguf b/Qwen2.5-1.5B-Thinking.Q8_0.gguf new file mode 100644 index 0000000..6c2264d --- /dev/null +++ b/Qwen2.5-1.5B-Thinking.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cbbb4c8d8a131bfe24dcd4600b0b8853646f7a3c9cf01ec08e5272f21f1da77 +size 1646573664 diff --git a/Qwen2.5-1.5B-Thinking.f16.gguf b/Qwen2.5-1.5B-Thinking.f16.gguf new file mode 100644 index 0000000..5b7d63e --- /dev/null +++ b/Qwen2.5-1.5B-Thinking.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4677fe92ee31a88920f935321508d221ab72223c47fc5bea651dbe4184eebfc4 +size 3093669984 diff --git a/README.md b/README.md new file mode 100644 index 0000000..04a160b --- /dev/null +++ b/README.md @@ -0,0 +1,87 @@ +--- +base_model: justinj92/Qwen2.5-1.5B-Thinking +datasets: +- microsoft/orca-math-word-problems-200k +language: +- zho +- eng +- fra +- spa +- por +- deu +- ita +- rus +- jpn +- kor +- vie +- tha +- ara +library_name: transformers +model_name: Qwen2.5-1.5B-Thinking +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- grpo +--- +## About + + + + + + +static quants of https://huggingface.co/justinj92/Qwen2.5-1.5B-Thinking + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-1.5B-Thinking-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/Qwen2.5-1.5B-Thinking-GGUF/resolve/main/Qwen2.5-1.5B-Thinking.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-GGUF/resolve/main/Qwen2.5-1.5B-Thinking.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-GGUF/resolve/main/Qwen2.5-1.5B-Thinking.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-GGUF/resolve/main/Qwen2.5-1.5B-Thinking.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-GGUF/resolve/main/Qwen2.5-1.5B-Thinking.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-GGUF/resolve/main/Qwen2.5-1.5B-Thinking.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-GGUF/resolve/main/Qwen2.5-1.5B-Thinking.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-GGUF/resolve/main/Qwen2.5-1.5B-Thinking.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-GGUF/resolve/main/Qwen2.5-1.5B-Thinking.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-GGUF/resolve/main/Qwen2.5-1.5B-Thinking.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-GGUF/resolve/main/Qwen2.5-1.5B-Thinking.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-1.5B-Thinking-GGUF/resolve/main/Qwen2.5-1.5B-Thinking.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. + +