commit b840381783e5c3465c2dfd10a43fe47b995ab20a Author: ModelHub XC Date: Sat Jun 13 19:16:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Light-IF-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..77deb4e --- /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 +Light-IF-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Light-IF-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Light-IF-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Light-IF-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Light-IF-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Light-IF-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Light-IF-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Light-IF-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Light-IF-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Light-IF-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Light-IF-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Light-IF-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Light-IF-4B.IQ4_XS.gguf b/Light-IF-4B.IQ4_XS.gguf new file mode 100644 index 0000000..b1a7f5b --- /dev/null +++ b/Light-IF-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7cd9db54e52a6ba6d900abd26378f5e13f953c6e6bf6cc9fa1eb6b1c2175f1f +size 2492949472 diff --git a/Light-IF-4B.Q2_K.gguf b/Light-IF-4B.Q2_K.gguf new file mode 100644 index 0000000..a561f2d --- /dev/null +++ b/Light-IF-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff8dc1ff00fdc33232f755f3b2fab74ddd1032cc7322d942602890831081644e +size 1797126112 diff --git a/Light-IF-4B.Q3_K_L.gguf b/Light-IF-4B.Q3_K_L.gguf new file mode 100644 index 0000000..db78355 --- /dev/null +++ b/Light-IF-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfcf220aee90c2375bea080a0281d6463a994d110736cbd91943d088c651552b +size 2406915552 diff --git a/Light-IF-4B.Q3_K_M.gguf b/Light-IF-4B.Q3_K_M.gguf new file mode 100644 index 0000000..4d265ed --- /dev/null +++ b/Light-IF-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94784313735cc80d2fb9281a785380a3b5cae83cfa4c1cccf1092392fb1d5cc0 +size 2242747872 diff --git a/Light-IF-4B.Q3_K_S.gguf b/Light-IF-4B.Q3_K_S.gguf new file mode 100644 index 0000000..b0d4602 --- /dev/null +++ b/Light-IF-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c7909ed6bb51986fba8135587dca0b7b7b2a101265bc2fa1898d9b537057785 +size 2054127072 diff --git a/Light-IF-4B.Q4_K_M.gguf b/Light-IF-4B.Q4_K_M.gguf new file mode 100644 index 0000000..6f385ee --- /dev/null +++ b/Light-IF-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4b7b9af1848a5ea857b9dbadd48d2ae13b0cd8986914db8175c051e94df2a11 +size 2716068832 diff --git a/Light-IF-4B.Q4_K_S.gguf b/Light-IF-4B.Q4_K_S.gguf new file mode 100644 index 0000000..6b572ca --- /dev/null +++ b/Light-IF-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7a5995bb69de33feb44be4ccd73a117ba87b33dbb8198d6896b0f340892d9e4 +size 2602097632 diff --git a/Light-IF-4B.Q5_K_M.gguf b/Light-IF-4B.Q5_K_M.gguf new file mode 100644 index 0000000..609ab93 --- /dev/null +++ b/Light-IF-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae3a9ba2d65a8014f5127122b3eafe76de48d65644498a6f4ca21cdff75433d6 +size 3156921312 diff --git a/Light-IF-4B.Q5_K_S.gguf b/Light-IF-4B.Q5_K_S.gguf new file mode 100644 index 0000000..3f9aed2 --- /dev/null +++ b/Light-IF-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb9d54335e252864674c6c9c142274e5dae3fb752e612d796da264d0367c6252 +size 3091119072 diff --git a/Light-IF-4B.Q6_K.gguf b/Light-IF-4B.Q6_K.gguf new file mode 100644 index 0000000..07d624d --- /dev/null +++ b/Light-IF-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84adf801350e8553a76381e15c33f7571c2ce01dd804688f8ad18c6d4086328e +size 3625327072 diff --git a/Light-IF-4B.Q8_0.gguf b/Light-IF-4B.Q8_0.gguf new file mode 100644 index 0000000..f3ce9b1 --- /dev/null +++ b/Light-IF-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:036c2003f57693a27493f37b6511c4686a4605f312cc5453b9a9ba44a5dd59a2 +size 4693671392 diff --git a/Light-IF-4B.f16.gguf b/Light-IF-4B.f16.gguf new file mode 100644 index 0000000..0293f45 --- /dev/null +++ b/Light-IF-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e80bef7f3a28dd71ccacf5979bdf92bfb6ae5b45ba5292f97062146f0d7f218d +size 8829197792 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7d2081b --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: qihoo360/Light-IF-4B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/qihoo360/Light-IF-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Light-IF-4B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Light-IF-4B-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/Light-IF-4B-GGUF/resolve/main/Light-IF-4B.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Light-IF-4B-GGUF/resolve/main/Light-IF-4B.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Light-IF-4B-GGUF/resolve/main/Light-IF-4B.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Light-IF-4B-GGUF/resolve/main/Light-IF-4B.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Light-IF-4B-GGUF/resolve/main/Light-IF-4B.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Light-IF-4B-GGUF/resolve/main/Light-IF-4B.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Light-IF-4B-GGUF/resolve/main/Light-IF-4B.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Light-IF-4B-GGUF/resolve/main/Light-IF-4B.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/Light-IF-4B-GGUF/resolve/main/Light-IF-4B.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Light-IF-4B-GGUF/resolve/main/Light-IF-4B.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Light-IF-4B-GGUF/resolve/main/Light-IF-4B.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Light-IF-4B-GGUF/resolve/main/Light-IF-4B.f16.gguf) | f16 | 8.9 | 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. + +