commit 54851d87bac3a05cbdc9e3d6a84ae16f65103f8b Author: ModelHub XC Date: Fri May 15 00:52:46 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/light-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6dc35ae --- /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-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +light-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +light-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +light-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +light-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +light-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +light-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +light-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +light-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +light-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +light-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +light-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9c5e6e3 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: Sakalti/light-3B +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- qwen2 +- merge +- mergekit +--- +## About + + + + + + +static quants of https://huggingface.co/Sakalti/light-3B + + +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/light-3B-GGUF/resolve/main/light-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/light-3B-GGUF/resolve/main/light-3B.Q3_K_S.gguf) | Q3_K_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/light-3B-GGUF/resolve/main/light-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/light-3B-GGUF/resolve/main/light-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/light-3B-GGUF/resolve/main/light-3B.IQ4_XS.gguf) | IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/light-3B-GGUF/resolve/main/light-3B.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/light-3B-GGUF/resolve/main/light-3B.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/light-3B-GGUF/resolve/main/light-3B.Q5_K_S.gguf) | Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/light-3B-GGUF/resolve/main/light-3B.Q5_K_M.gguf) | Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/light-3B-GGUF/resolve/main/light-3B.Q6_K.gguf) | Q6_K | 2.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/light-3B-GGUF/resolve/main/light-3B.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/light-3B-GGUF/resolve/main/light-3B.f16.gguf) | f16 | 6.9 | 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. + + diff --git a/light-3B.IQ4_XS.gguf b/light-3B.IQ4_XS.gguf new file mode 100644 index 0000000..f04ad8a --- /dev/null +++ b/light-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b42b3cb8185cc48cb511e1b6de5d8c31a8bb3281174b54288127de8151950d4 +size 1918491616 diff --git a/light-3B.Q2_K.gguf b/light-3B.Q2_K.gguf new file mode 100644 index 0000000..46b0c1b --- /dev/null +++ b/light-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dad19571e36fe5263501759b463531abba496787026aa5a791168e380c38ec1 +size 1376857056 diff --git a/light-3B.Q3_K_L.gguf b/light-3B.Q3_K_L.gguf new file mode 100644 index 0000000..a0ffa4c --- /dev/null +++ b/light-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7677b8abbc6d446014c645c2b28abbe9ad82ddc2f3ce31f7e956690b9251afd9 +size 1841095648 diff --git a/light-3B.Q3_K_M.gguf b/light-3B.Q3_K_M.gguf new file mode 100644 index 0000000..43ba2da --- /dev/null +++ b/light-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af6b383198bfac82a8a8c068880d0838ce52346d44c769060e9a66713a5b0b17 +size 1724179424 diff --git a/light-3B.Q3_K_S.gguf b/light-3B.Q3_K_S.gguf new file mode 100644 index 0000000..4d53231 --- /dev/null +++ b/light-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ef14d744af11f084238fd4aec1b688150b811a21a3ce3e90f43e8a9d74b8c2b +size 1588061152 diff --git a/light-3B.Q4_K_M.gguf b/light-3B.Q4_K_M.gguf new file mode 100644 index 0000000..8ea770c --- /dev/null +++ b/light-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67168ee13145697a3ae84ebf413dbe9339244f413b4bcf9bb0233c480ba9e48f +size 2104933344 diff --git a/light-3B.Q4_K_S.gguf b/light-3B.Q4_K_S.gguf new file mode 100644 index 0000000..f54de32 --- /dev/null +++ b/light-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c238f3326d41646906d11ed04c0c8f515dd9e8047259de72ca91d941b034a9f7 +size 2009414624 diff --git a/light-3B.Q5_K_M.gguf b/light-3B.Q5_K_M.gguf new file mode 100644 index 0000000..77bf8b2 --- /dev/null +++ b/light-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef819d57f065010f030089812da78b5f09d06cfe6222ec6d518e00cace7dcfa8 +size 2438740960 diff --git a/light-3B.Q5_K_S.gguf b/light-3B.Q5_K_S.gguf new file mode 100644 index 0000000..8fbc56c --- /dev/null +++ b/light-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da9657ffa098a3246847819747fdf2d216f5e38073ca6f16633ffb3be5b67210 +size 2383592416 diff --git a/light-3B.Q6_K.gguf b/light-3B.Q6_K.gguf new file mode 100644 index 0000000..bfb9293 --- /dev/null +++ b/light-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e4ad9978fb979dfe9ac534cb98777f9fbb524a3db3378a47fb6ac98bcc7aaa7 +size 2793411552 diff --git a/light-3B.Q8_0.gguf b/light-3B.Q8_0.gguf new file mode 100644 index 0000000..3192990 --- /dev/null +++ b/light-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9015bae2c632731ca18e81cc209935948af18aeb021e322f1975f6056a56e13e +size 3616089056 diff --git a/light-3B.f16.gguf b/light-3B.f16.gguf new file mode 100644 index 0000000..cdbc28e --- /dev/null +++ b/light-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d985d375eafab8e489c12958e5645bfa1b7d248056fe2c625974d32a06d3f872 +size 6800647136