commit 567ce9f74a39d952f989c7e1758392f76e29bd03 Author: ModelHub XC Date: Sat Jun 13 05:33:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/CogniTune-Qwen2.5-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8b98b06 --- /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 +CogniTune-Qwen2.5-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +CogniTune-Qwen2.5-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +CogniTune-Qwen2.5-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +CogniTune-Qwen2.5-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CogniTune-Qwen2.5-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CogniTune-Qwen2.5-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CogniTune-Qwen2.5-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CogniTune-Qwen2.5-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +CogniTune-Qwen2.5-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +CogniTune-Qwen2.5-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +CogniTune-Qwen2.5-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +CogniTune-Qwen2.5-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/CogniTune-Qwen2.5-3B.IQ4_XS.gguf b/CogniTune-Qwen2.5-3B.IQ4_XS.gguf new file mode 100644 index 0000000..9e38257 --- /dev/null +++ b/CogniTune-Qwen2.5-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2372ac522fa0cb5d3ec2843821743bc80e9555ef3e00363c57e001fbaff2b979 +size 1753185568 diff --git a/CogniTune-Qwen2.5-3B.Q2_K.gguf b/CogniTune-Qwen2.5-3B.Q2_K.gguf new file mode 100644 index 0000000..5ac51db --- /dev/null +++ b/CogniTune-Qwen2.5-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:384fa963b7b2badf99958be49a7bc26bdb3f1dc0ae787657dd428061d7a049de +size 1274756384 diff --git a/CogniTune-Qwen2.5-3B.Q3_K_L.gguf b/CogniTune-Qwen2.5-3B.Q3_K_L.gguf new file mode 100644 index 0000000..1c520b2 --- /dev/null +++ b/CogniTune-Qwen2.5-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66ea034856aae890dbc44ac4b91134166a5c67a303d177ad8640d1fdcf76f1f7 +size 1707392288 diff --git a/CogniTune-Qwen2.5-3B.Q3_K_M.gguf b/CogniTune-Qwen2.5-3B.Q3_K_M.gguf new file mode 100644 index 0000000..132865c --- /dev/null +++ b/CogniTune-Qwen2.5-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:815424ef56b580e23532888d2c30348bd5dd3dff695d5e4410ce233399e170f7 +size 1590476064 diff --git a/CogniTune-Qwen2.5-3B.Q3_K_S.gguf b/CogniTune-Qwen2.5-3B.Q3_K_S.gguf new file mode 100644 index 0000000..ffb11f2 --- /dev/null +++ b/CogniTune-Qwen2.5-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee8b10d226d629a758e10f0768c3c5520074097371bde507a02a686c6d6a9bcd +size 1454357792 diff --git a/CogniTune-Qwen2.5-3B.Q4_K_M.gguf b/CogniTune-Qwen2.5-3B.Q4_K_M.gguf new file mode 100644 index 0000000..38b5baa --- /dev/null +++ b/CogniTune-Qwen2.5-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93e5178839475398335fa1f3991466e1293d893b5a0331c255b1c389a038c7f4 +size 1929903392 diff --git a/CogniTune-Qwen2.5-3B.Q4_K_S.gguf b/CogniTune-Qwen2.5-3B.Q4_K_S.gguf new file mode 100644 index 0000000..9092d38 --- /dev/null +++ b/CogniTune-Qwen2.5-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:469c98ad461e6247c471632759fab4733050d9b4067af202a995a6558866a6f3 +size 1834384672 diff --git a/CogniTune-Qwen2.5-3B.Q5_K_M.gguf b/CogniTune-Qwen2.5-3B.Q5_K_M.gguf new file mode 100644 index 0000000..031e0e7 --- /dev/null +++ b/CogniTune-Qwen2.5-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b0f59833107bcf5fd2dfd1b66759f2f4bfa75637a588065301688bb2edc46c3 +size 2224815392 diff --git a/CogniTune-Qwen2.5-3B.Q5_K_S.gguf b/CogniTune-Qwen2.5-3B.Q5_K_S.gguf new file mode 100644 index 0000000..d543fa2 --- /dev/null +++ b/CogniTune-Qwen2.5-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ef915959fdc0bd04373d33df760e9241740a747744719e2ddcf07a734c7b1d1 +size 2169666848 diff --git a/CogniTune-Qwen2.5-3B.Q6_K.gguf b/CogniTune-Qwen2.5-3B.Q6_K.gguf new file mode 100644 index 0000000..9a4e32a --- /dev/null +++ b/CogniTune-Qwen2.5-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:237be9a20f0a4a5682b4faf458252489564edf26182c9f0f9a59aec2ac521c53 +size 2538159392 diff --git a/CogniTune-Qwen2.5-3B.Q8_0.gguf b/CogniTune-Qwen2.5-3B.Q8_0.gguf new file mode 100644 index 0000000..2db5f3a --- /dev/null +++ b/CogniTune-Qwen2.5-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e48dac2fd4ad5d5cc1fb0ade30fe71904adc99573d544db77a72c104e6e161e9 +size 3285476640 diff --git a/CogniTune-Qwen2.5-3B.f16.gguf b/CogniTune-Qwen2.5-3B.f16.gguf new file mode 100644 index 0000000..6020f84 --- /dev/null +++ b/CogniTune-Qwen2.5-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cba8556a0fedf4c4dae9405508257943fb42d6eb7664842df939544bbc8ec08 +size 6178317600 diff --git a/README.md b/README.md new file mode 100644 index 0000000..00654fe --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: Pickamon/CogniTune-Qwen2.5-3B +language: +- en +library_name: transformers +license: other +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- mlx +- lora +- fine-tuned +- education +- ai-tutor +- qwen2 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Pickamon/CogniTune-Qwen2.5-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#CogniTune-Qwen2.5-3B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/CogniTune-Qwen2.5-3B-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/CogniTune-Qwen2.5-3B-GGUF/resolve/main/CogniTune-Qwen2.5-3B.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/CogniTune-Qwen2.5-3B-GGUF/resolve/main/CogniTune-Qwen2.5-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/CogniTune-Qwen2.5-3B-GGUF/resolve/main/CogniTune-Qwen2.5-3B.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/CogniTune-Qwen2.5-3B-GGUF/resolve/main/CogniTune-Qwen2.5-3B.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/CogniTune-Qwen2.5-3B-GGUF/resolve/main/CogniTune-Qwen2.5-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/CogniTune-Qwen2.5-3B-GGUF/resolve/main/CogniTune-Qwen2.5-3B.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CogniTune-Qwen2.5-3B-GGUF/resolve/main/CogniTune-Qwen2.5-3B.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/CogniTune-Qwen2.5-3B-GGUF/resolve/main/CogniTune-Qwen2.5-3B.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/CogniTune-Qwen2.5-3B-GGUF/resolve/main/CogniTune-Qwen2.5-3B.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/CogniTune-Qwen2.5-3B-GGUF/resolve/main/CogniTune-Qwen2.5-3B.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/CogniTune-Qwen2.5-3B-GGUF/resolve/main/CogniTune-Qwen2.5-3B.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/CogniTune-Qwen2.5-3B-GGUF/resolve/main/CogniTune-Qwen2.5-3B.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. + +