commit 904ea51967baf29f808fe565311bbae95c10b1d2 Author: ModelHub XC Date: Sat May 9 23:51:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Nero-Qwen2.5-1.5B-Surgical-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c3c4a35 --- /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 +Nero-Qwen2.5-1.5B-Surgical.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Nero-Qwen2.5-1.5B-Surgical.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Nero-Qwen2.5-1.5B-Surgical.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Nero-Qwen2.5-1.5B-Surgical.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nero-Qwen2.5-1.5B-Surgical.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nero-Qwen2.5-1.5B-Surgical.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nero-Qwen2.5-1.5B-Surgical.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nero-Qwen2.5-1.5B-Surgical.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nero-Qwen2.5-1.5B-Surgical.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nero-Qwen2.5-1.5B-Surgical.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Nero-Qwen2.5-1.5B-Surgical.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Nero-Qwen2.5-1.5B-Surgical.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Nero-Qwen2.5-1.5B-Surgical.IQ4_XS.gguf b/Nero-Qwen2.5-1.5B-Surgical.IQ4_XS.gguf new file mode 100644 index 0000000..93b1129 --- /dev/null +++ b/Nero-Qwen2.5-1.5B-Surgical.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c512e1bbc30126a9862ae002d465802e0915e988ef61bdd742f1eb61c638835 +size 902183360 diff --git a/Nero-Qwen2.5-1.5B-Surgical.Q2_K.gguf b/Nero-Qwen2.5-1.5B-Surgical.Q2_K.gguf new file mode 100644 index 0000000..f97f331 --- /dev/null +++ b/Nero-Qwen2.5-1.5B-Surgical.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5947bd9f4c0fa615cca9e6c2d39735c2d99445e0f1afe2537240b7d7005e509 +size 676305344 diff --git a/Nero-Qwen2.5-1.5B-Surgical.Q3_K_L.gguf b/Nero-Qwen2.5-1.5B-Surgical.Q3_K_L.gguf new file mode 100644 index 0000000..8ca98fd --- /dev/null +++ b/Nero-Qwen2.5-1.5B-Surgical.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29f1fe11eea6d0e25cbf9975f651fa0af49ca00aa848203a7607cc5a0f971897 +size 880163264 diff --git a/Nero-Qwen2.5-1.5B-Surgical.Q3_K_M.gguf b/Nero-Qwen2.5-1.5B-Surgical.Q3_K_M.gguf new file mode 100644 index 0000000..5ac3c60 --- /dev/null +++ b/Nero-Qwen2.5-1.5B-Surgical.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23d1f00f04a42eeedba001f0099f8919516786ebe99c764259cb62aed4e34abe +size 824179136 diff --git a/Nero-Qwen2.5-1.5B-Surgical.Q3_K_S.gguf b/Nero-Qwen2.5-1.5B-Surgical.Q3_K_S.gguf new file mode 100644 index 0000000..cd1a317 --- /dev/null +++ b/Nero-Qwen2.5-1.5B-Surgical.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fed27676b7938ede2f5573295f0ee6bac00245854b8ce47ac11e644b0b410976 +size 760945088 diff --git a/Nero-Qwen2.5-1.5B-Surgical.Q4_K_M.gguf b/Nero-Qwen2.5-1.5B-Surgical.Q4_K_M.gguf new file mode 100644 index 0000000..e149259 --- /dev/null +++ b/Nero-Qwen2.5-1.5B-Surgical.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd9b37fd657b00044bd0123c5af09844a1d54551bd0922b026d226ee5ea6aa24 +size 986048960 diff --git a/Nero-Qwen2.5-1.5B-Surgical.Q4_K_S.gguf b/Nero-Qwen2.5-1.5B-Surgical.Q4_K_S.gguf new file mode 100644 index 0000000..4b7b674 --- /dev/null +++ b/Nero-Qwen2.5-1.5B-Surgical.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:397ef5e942f074667580ce9a12c2c8711836626f6e9b187a0aa3f8bafb360879 +size 940313024 diff --git a/Nero-Qwen2.5-1.5B-Surgical.Q5_K_M.gguf b/Nero-Qwen2.5-1.5B-Surgical.Q5_K_M.gguf new file mode 100644 index 0000000..46111e1 --- /dev/null +++ b/Nero-Qwen2.5-1.5B-Surgical.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5507dd809ab9b1b2c015549e75cd1db1d62e657c0df12a138ab1de9305b193eb +size 1125050816 diff --git a/Nero-Qwen2.5-1.5B-Surgical.Q5_K_S.gguf b/Nero-Qwen2.5-1.5B-Surgical.Q5_K_S.gguf new file mode 100644 index 0000000..f8f0528 --- /dev/null +++ b/Nero-Qwen2.5-1.5B-Surgical.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:449e38dcc6a0443e53279534eabb4c4fa4a7d8879feafad80c574500e69e02b5 +size 1098729920 diff --git a/Nero-Qwen2.5-1.5B-Surgical.Q6_K.gguf b/Nero-Qwen2.5-1.5B-Surgical.Q6_K.gguf new file mode 100644 index 0000000..d07d99f --- /dev/null +++ b/Nero-Qwen2.5-1.5B-Surgical.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ed0f0366a77b765fde82491dffe8b1d2effe15a54b4985366bd3270477beb2b +size 1272740288 diff --git a/Nero-Qwen2.5-1.5B-Surgical.Q8_0.gguf b/Nero-Qwen2.5-1.5B-Surgical.Q8_0.gguf new file mode 100644 index 0000000..4d77da3 --- /dev/null +++ b/Nero-Qwen2.5-1.5B-Surgical.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b313b904e6b6483641fce21071548382c06fb9e878991396f02c90e8fb98c96 +size 1646573504 diff --git a/Nero-Qwen2.5-1.5B-Surgical.f16.gguf b/Nero-Qwen2.5-1.5B-Surgical.f16.gguf new file mode 100644 index 0000000..5ed644d --- /dev/null +++ b/Nero-Qwen2.5-1.5B-Surgical.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e656f0701862bea118929a7f4afeddcff8c02ccfb345073cc86d459e52275578 +size 3093669824 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4b7a88e --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: neroai14/Nero-Qwen2.5-1.5B-Surgical +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- model-compression +- quantization +- svd +- nero-engine +- efficiency +--- +## About + + + + + + + + + +static quants of https://huggingface.co/neroai14/Nero-Qwen2.5-1.5B-Surgical + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Nero-Qwen2.5-1.5B-Surgical-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Nero-Qwen2.5-1.5B-Surgical-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/Nero-Qwen2.5-1.5B-Surgical-GGUF/resolve/main/Nero-Qwen2.5-1.5B-Surgical.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Nero-Qwen2.5-1.5B-Surgical-GGUF/resolve/main/Nero-Qwen2.5-1.5B-Surgical.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Nero-Qwen2.5-1.5B-Surgical-GGUF/resolve/main/Nero-Qwen2.5-1.5B-Surgical.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Nero-Qwen2.5-1.5B-Surgical-GGUF/resolve/main/Nero-Qwen2.5-1.5B-Surgical.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Nero-Qwen2.5-1.5B-Surgical-GGUF/resolve/main/Nero-Qwen2.5-1.5B-Surgical.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Nero-Qwen2.5-1.5B-Surgical-GGUF/resolve/main/Nero-Qwen2.5-1.5B-Surgical.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nero-Qwen2.5-1.5B-Surgical-GGUF/resolve/main/Nero-Qwen2.5-1.5B-Surgical.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nero-Qwen2.5-1.5B-Surgical-GGUF/resolve/main/Nero-Qwen2.5-1.5B-Surgical.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Nero-Qwen2.5-1.5B-Surgical-GGUF/resolve/main/Nero-Qwen2.5-1.5B-Surgical.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Nero-Qwen2.5-1.5B-Surgical-GGUF/resolve/main/Nero-Qwen2.5-1.5B-Surgical.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Nero-Qwen2.5-1.5B-Surgical-GGUF/resolve/main/Nero-Qwen2.5-1.5B-Surgical.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Nero-Qwen2.5-1.5B-Surgical-GGUF/resolve/main/Nero-Qwen2.5-1.5B-Surgical.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. + +