commit 4b1d8b8d1696d1a4ef443ed9a985e815a8e06a67 Author: ModelHub XC Date: Fri Jun 26 07:09:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Nemotron_W_4b_MagLight_0.1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ca1a522 --- /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 +Nemotron_W_4b_MagLight_0.1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron_W_4b_MagLight_0.1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron_W_4b_MagLight_0.1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron_W_4b_MagLight_0.1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron_W_4b_MagLight_0.1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron_W_4b_MagLight_0.1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron_W_4b_MagLight_0.1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron_W_4b_MagLight_0.1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron_W_4b_MagLight_0.1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron_W_4b_MagLight_0.1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron_W_4b_MagLight_0.1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Nemotron_W_4b_MagLight_0.1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Nemotron_W_4b_MagLight_0.1.IQ4_XS.gguf b/Nemotron_W_4b_MagLight_0.1.IQ4_XS.gguf new file mode 100644 index 0000000..dae758f --- /dev/null +++ b/Nemotron_W_4b_MagLight_0.1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86870e0cad65a852acb4e3854e4e3323e1fe5b7731f82431ddaadbf61be1660f +size 2553241568 diff --git a/Nemotron_W_4b_MagLight_0.1.Q2_K.gguf b/Nemotron_W_4b_MagLight_0.1.Q2_K.gguf new file mode 100644 index 0000000..d40c468 --- /dev/null +++ b/Nemotron_W_4b_MagLight_0.1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74250b5afa3a2873cb57ed4f998577282ec7e988a2c8d53f4091218be5395e7c +size 1839738848 diff --git a/Nemotron_W_4b_MagLight_0.1.Q3_K_L.gguf b/Nemotron_W_4b_MagLight_0.1.Q3_K_L.gguf new file mode 100644 index 0000000..3c1e6c1 --- /dev/null +++ b/Nemotron_W_4b_MagLight_0.1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ff44e4945de5573ae547c97cf28d20cf4ccc30d5c7c9f2070c06679b12551b8 +size 2464860128 diff --git a/Nemotron_W_4b_MagLight_0.1.Q3_K_M.gguf b/Nemotron_W_4b_MagLight_0.1.Q3_K_M.gguf new file mode 100644 index 0000000..13877da --- /dev/null +++ b/Nemotron_W_4b_MagLight_0.1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61212c0d4176b742eca5333217fd83d6d8ac991bb9c79b12470e0a87bf7ec2fc +size 2296563680 diff --git a/Nemotron_W_4b_MagLight_0.1.Q3_K_S.gguf b/Nemotron_W_4b_MagLight_0.1.Q3_K_S.gguf new file mode 100644 index 0000000..981e0fb --- /dev/null +++ b/Nemotron_W_4b_MagLight_0.1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63511ffbe37738676446662ef34ed0c94896fd2680b92014539a0d033b0e7b62 +size 2101528544 diff --git a/Nemotron_W_4b_MagLight_0.1.Q4_K_M.gguf b/Nemotron_W_4b_MagLight_0.1.Q4_K_M.gguf new file mode 100644 index 0000000..ba1a751 --- /dev/null +++ b/Nemotron_W_4b_MagLight_0.1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:069e34818ab7f9a1810c6d77a7aa57bb8256911b72a4af45921d9ed4b73a138d +size 2778284000 diff --git a/Nemotron_W_4b_MagLight_0.1.Q4_K_S.gguf b/Nemotron_W_4b_MagLight_0.1.Q4_K_S.gguf new file mode 100644 index 0000000..da1e90c --- /dev/null +++ b/Nemotron_W_4b_MagLight_0.1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d08e06914f9fde338a4f85208e3b03ee6d15a641ae64a9f4d75ea6e1c13281e3 +size 2664251360 diff --git a/Nemotron_W_4b_MagLight_0.1.Q5_K_M.gguf b/Nemotron_W_4b_MagLight_0.1.Q5_K_M.gguf new file mode 100644 index 0000000..8b366d7 --- /dev/null +++ b/Nemotron_W_4b_MagLight_0.1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b4998ad222be1680f1e005a1a3578a12da679daf7ea3a947279bdbc1caa550b +size 3230187488 diff --git a/Nemotron_W_4b_MagLight_0.1.Q5_K_S.gguf b/Nemotron_W_4b_MagLight_0.1.Q5_K_S.gguf new file mode 100644 index 0000000..457e6b9 --- /dev/null +++ b/Nemotron_W_4b_MagLight_0.1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc0f734f9eb5b00cdab77e2c605d1b38e450dec7fe657ddea226c62dfe189d41 +size 3163340768 diff --git a/Nemotron_W_4b_MagLight_0.1.Q6_K.gguf b/Nemotron_W_4b_MagLight_0.1.Q6_K.gguf new file mode 100644 index 0000000..5be7722 --- /dev/null +++ b/Nemotron_W_4b_MagLight_0.1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d098ad229bc8ae3e1ed152fb4d1c9a2f48d9419e52efd2a0dad8afd649e06aec +size 3710334944 diff --git a/Nemotron_W_4b_MagLight_0.1.Q8_0.gguf b/Nemotron_W_4b_MagLight_0.1.Q8_0.gguf new file mode 100644 index 0000000..8705cfa --- /dev/null +++ b/Nemotron_W_4b_MagLight_0.1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:171a19db46c68c20cdce3c8daabf11f009921bc9b37e23b554793875ff7cee93 +size 4803217376 diff --git a/Nemotron_W_4b_MagLight_0.1.f16.gguf b/Nemotron_W_4b_MagLight_0.1.f16.gguf new file mode 100644 index 0000000..27ca084 --- /dev/null +++ b/Nemotron_W_4b_MagLight_0.1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:359acdf4912d448624c13ed61f6f6b88e5b1fadb776c1f6b52503757792d131c +size 9033730016 diff --git a/README.md b/README.md new file mode 100644 index 0000000..79edb02 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: Nexesenex/Nemotron_W_4b_MagLight_0.1 +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/Nexesenex/Nemotron_W_4b_MagLight_0.1 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Nemotron_W_4b_MagLight_0.1-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/Nemotron_W_4b_MagLight_0.1-GGUF/resolve/main/Nemotron_W_4b_MagLight_0.1.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron_W_4b_MagLight_0.1-GGUF/resolve/main/Nemotron_W_4b_MagLight_0.1.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron_W_4b_MagLight_0.1-GGUF/resolve/main/Nemotron_W_4b_MagLight_0.1.Q3_K_M.gguf) | Q3_K_M | 2.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Nemotron_W_4b_MagLight_0.1-GGUF/resolve/main/Nemotron_W_4b_MagLight_0.1.Q3_K_L.gguf) | Q3_K_L | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron_W_4b_MagLight_0.1-GGUF/resolve/main/Nemotron_W_4b_MagLight_0.1.IQ4_XS.gguf) | IQ4_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron_W_4b_MagLight_0.1-GGUF/resolve/main/Nemotron_W_4b_MagLight_0.1.Q4_K_S.gguf) | Q4_K_S | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nemotron_W_4b_MagLight_0.1-GGUF/resolve/main/Nemotron_W_4b_MagLight_0.1.Q4_K_M.gguf) | Q4_K_M | 2.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Nemotron_W_4b_MagLight_0.1-GGUF/resolve/main/Nemotron_W_4b_MagLight_0.1.Q5_K_S.gguf) | Q5_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron_W_4b_MagLight_0.1-GGUF/resolve/main/Nemotron_W_4b_MagLight_0.1.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Nemotron_W_4b_MagLight_0.1-GGUF/resolve/main/Nemotron_W_4b_MagLight_0.1.Q6_K.gguf) | Q6_K | 3.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Nemotron_W_4b_MagLight_0.1-GGUF/resolve/main/Nemotron_W_4b_MagLight_0.1.Q8_0.gguf) | Q8_0 | 4.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Nemotron_W_4b_MagLight_0.1-GGUF/resolve/main/Nemotron_W_4b_MagLight_0.1.f16.gguf) | f16 | 9.1 | 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. + +