commit c0af54ec785b017251cf5a8b63e75afae97bcde2 Author: ModelHub XC Date: Tue Jul 21 23:18:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/NxMobileLM-1.5B-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4e444e7 --- /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 +NxMobileLM-1.5B-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +NxMobileLM-1.5B-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +NxMobileLM-1.5B-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +NxMobileLM-1.5B-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NxMobileLM-1.5B-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NxMobileLM-1.5B-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NxMobileLM-1.5B-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NxMobileLM-1.5B-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +NxMobileLM-1.5B-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +NxMobileLM-1.5B-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +NxMobileLM-1.5B-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +NxMobileLM-1.5B-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/NxMobileLM-1.5B-SFT.IQ4_XS.gguf b/NxMobileLM-1.5B-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..192f22f --- /dev/null +++ b/NxMobileLM-1.5B-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9161cca8fa99793365f6723ba031825be6583eae45bb458a23a9fe8c7f06f56e +size 902183232 diff --git a/NxMobileLM-1.5B-SFT.Q2_K.gguf b/NxMobileLM-1.5B-SFT.Q2_K.gguf new file mode 100644 index 0000000..b12deb6 --- /dev/null +++ b/NxMobileLM-1.5B-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:797574e4c8632e33c1aa76bf92481a68191ed7150d44f246a79c92bf12304d2f +size 676305216 diff --git a/NxMobileLM-1.5B-SFT.Q3_K_L.gguf b/NxMobileLM-1.5B-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..b984fa7 --- /dev/null +++ b/NxMobileLM-1.5B-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13d7c9ca2faa72edbb1cf33888b5859f519418c5bab386609ad335399fd73c23 +size 880163136 diff --git a/NxMobileLM-1.5B-SFT.Q3_K_M.gguf b/NxMobileLM-1.5B-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..8579cc6 --- /dev/null +++ b/NxMobileLM-1.5B-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e50beae26a4da3537f7df0e8425509bf4a93c05b79dcf17b6aa3a36c2875abf0 +size 824179008 diff --git a/NxMobileLM-1.5B-SFT.Q3_K_S.gguf b/NxMobileLM-1.5B-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..581fc25 --- /dev/null +++ b/NxMobileLM-1.5B-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3021d32b9d4ae0bb1d5be7a4e6c1b7a0f7d463d4463af994e264775b6bd687b +size 760944960 diff --git a/NxMobileLM-1.5B-SFT.Q4_K_M.gguf b/NxMobileLM-1.5B-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..6d1752e --- /dev/null +++ b/NxMobileLM-1.5B-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5ef57b3804db166f44b3d87855a79927d3cd88d124d22366b2aaa359ae85117 +size 986048832 diff --git a/NxMobileLM-1.5B-SFT.Q4_K_S.gguf b/NxMobileLM-1.5B-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..519188c --- /dev/null +++ b/NxMobileLM-1.5B-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5232e124f25fd2bf9044286f32e0e835a8d518e7793dd1c8bd6dc4a59c5515a6 +size 940312896 diff --git a/NxMobileLM-1.5B-SFT.Q5_K_M.gguf b/NxMobileLM-1.5B-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..c9429c7 --- /dev/null +++ b/NxMobileLM-1.5B-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f1fdc824c5d7beb02ca60bf54acb8d5940c600a862186e3664259de979fe734 +size 1125050688 diff --git a/NxMobileLM-1.5B-SFT.Q5_K_S.gguf b/NxMobileLM-1.5B-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..c0d20aa --- /dev/null +++ b/NxMobileLM-1.5B-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a13edb59ea51810bb32a4ce4c0c1fcd97e57895e84cacd8d229b61cf8a7a5d6 +size 1098729792 diff --git a/NxMobileLM-1.5B-SFT.Q6_K.gguf b/NxMobileLM-1.5B-SFT.Q6_K.gguf new file mode 100644 index 0000000..86026b1 --- /dev/null +++ b/NxMobileLM-1.5B-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e2c313e1fcb8f0e2c178ebfa1416a3b2c63b1d7a9e9599b653bd8b66d4e7a5b +size 1272740160 diff --git a/NxMobileLM-1.5B-SFT.Q8_0.gguf b/NxMobileLM-1.5B-SFT.Q8_0.gguf new file mode 100644 index 0000000..ee27359 --- /dev/null +++ b/NxMobileLM-1.5B-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aac234b9ff2f1875febfe2a07c0597d2b4a77c192c3bf21a7f89ffb43c27c46d +size 1646573376 diff --git a/NxMobileLM-1.5B-SFT.f16.gguf b/NxMobileLM-1.5B-SFT.f16.gguf new file mode 100644 index 0000000..a623723 --- /dev/null +++ b/NxMobileLM-1.5B-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0a8b3866f15228d1ed855e60c89a519db46a23eba1875c5075576b16da7fbab +size 3093669696 diff --git a/README.md b/README.md new file mode 100644 index 0000000..778a1da --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: NTQAI/NxMobileLM-1.5B-SFT +language: +- en +- ja +- ko +- vi +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/NTQAI/NxMobileLM-1.5B-SFT + + +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/NxMobileLM-1.5B-SFT-GGUF/resolve/main/NxMobileLM-1.5B-SFT.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/NxMobileLM-1.5B-SFT-GGUF/resolve/main/NxMobileLM-1.5B-SFT.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/NxMobileLM-1.5B-SFT-GGUF/resolve/main/NxMobileLM-1.5B-SFT.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/NxMobileLM-1.5B-SFT-GGUF/resolve/main/NxMobileLM-1.5B-SFT.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/NxMobileLM-1.5B-SFT-GGUF/resolve/main/NxMobileLM-1.5B-SFT.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/NxMobileLM-1.5B-SFT-GGUF/resolve/main/NxMobileLM-1.5B-SFT.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NxMobileLM-1.5B-SFT-GGUF/resolve/main/NxMobileLM-1.5B-SFT.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/NxMobileLM-1.5B-SFT-GGUF/resolve/main/NxMobileLM-1.5B-SFT.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/NxMobileLM-1.5B-SFT-GGUF/resolve/main/NxMobileLM-1.5B-SFT.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/NxMobileLM-1.5B-SFT-GGUF/resolve/main/NxMobileLM-1.5B-SFT.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/NxMobileLM-1.5B-SFT-GGUF/resolve/main/NxMobileLM-1.5B-SFT.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/NxMobileLM-1.5B-SFT-GGUF/resolve/main/NxMobileLM-1.5B-SFT.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. + +