commit efbec5935b2e7750f1418c7e3db6ae627a8572a8 Author: ModelHub XC Date: Tue Jun 16 22:44:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LFM2-350M-Pro-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53315bb --- /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 +LFM2-350M-Pro-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM2-350M-Pro-v2.IQ4_XS.gguf b/LFM2-350M-Pro-v2.IQ4_XS.gguf new file mode 100644 index 0000000..6da06aa --- /dev/null +++ b/LFM2-350M-Pro-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63f5b7854d33cceafb635ca06abd67f6007ca3a923094f40be110137a47d9713 +size 210827744 diff --git a/LFM2-350M-Pro-v2.Q2_K.gguf b/LFM2-350M-Pro-v2.Q2_K.gguf new file mode 100644 index 0000000..fed1a5f --- /dev/null +++ b/LFM2-350M-Pro-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ada414a55c442074df0578839108ec1c1b3d73e862ec0b23ac2008cc6175f7d +size 159619552 diff --git a/LFM2-350M-Pro-v2.Q3_K_L.gguf b/LFM2-350M-Pro-v2.Q3_K_L.gguf new file mode 100644 index 0000000..3385d98 --- /dev/null +++ b/LFM2-350M-Pro-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e82a972c4876c070be4256cc450df0e1713f81c687199311c8bdd674c85c052 +size 202070496 diff --git a/LFM2-350M-Pro-v2.Q3_K_M.gguf b/LFM2-350M-Pro-v2.Q3_K_M.gguf new file mode 100644 index 0000000..0e80090 --- /dev/null +++ b/LFM2-350M-Pro-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28203ccec0f4116a1964ffc10e3baab1a4fdf3a0cd468e7f8d4697464c26e3b1 +size 192174560 diff --git a/LFM2-350M-Pro-v2.Q3_K_S.gguf b/LFM2-350M-Pro-v2.Q3_K_S.gguf new file mode 100644 index 0000000..323a1db --- /dev/null +++ b/LFM2-350M-Pro-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a12cd43ea6bccafb22cabf019cbe42b53a305b4fe702a00e3675256b22d3d41f +size 180173280 diff --git a/LFM2-350M-Pro-v2.Q4_K_M.gguf b/LFM2-350M-Pro-v2.Q4_K_M.gguf new file mode 100644 index 0000000..7d1b6ee --- /dev/null +++ b/LFM2-350M-Pro-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4beea703158402827612b93703c15c2b8d16f5af27af0b3c3c61cbc346adaac8 +size 228334048 diff --git a/LFM2-350M-Pro-v2.Q4_K_S.gguf b/LFM2-350M-Pro-v2.Q4_K_S.gguf new file mode 100644 index 0000000..5cf8885 --- /dev/null +++ b/LFM2-350M-Pro-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbbe15e2df3ae77a9db5e07be0dea1c50b6e41c6c994911fe49451b7d3609c2b +size 219773408 diff --git a/LFM2-350M-Pro-v2.Q5_K_M.gguf b/LFM2-350M-Pro-v2.Q5_K_M.gguf new file mode 100644 index 0000000..eae1024 --- /dev/null +++ b/LFM2-350M-Pro-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f92aad92b3cf241d07a6a9b648b8370a1320d7a297f3902ee449cd454ce9ba18 +size 259398112 diff --git a/LFM2-350M-Pro-v2.Q5_K_S.gguf b/LFM2-350M-Pro-v2.Q5_K_S.gguf new file mode 100644 index 0000000..1746cb1 --- /dev/null +++ b/LFM2-350M-Pro-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:232fa79239ed585dcebcc6202a1a8c3b45f2eff2e71ad3d58767da4ea5cae9c2 +size 254245344 diff --git a/LFM2-350M-Pro-v2.Q6_K.gguf b/LFM2-350M-Pro-v2.Q6_K.gguf new file mode 100644 index 0000000..9bbafd3 --- /dev/null +++ b/LFM2-350M-Pro-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7604ef86bf064896072409e941b7cfd18310899719bc5ab6f9563fedb265653b +size 292403680 diff --git a/LFM2-350M-Pro-v2.Q8_0.gguf b/LFM2-350M-Pro-v2.Q8_0.gguf new file mode 100644 index 0000000..802bbd4 --- /dev/null +++ b/LFM2-350M-Pro-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a5256a79cbf3e660418bb8d621280997404cfc3c7e4c0095629e8c1694cd0da +size 377958208 diff --git a/LFM2-350M-Pro-v2.f16.gguf b/LFM2-350M-Pro-v2.f16.gguf new file mode 100644 index 0000000..1542729 --- /dev/null +++ b/LFM2-350M-Pro-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbc9dca0d936599115d1667312e5a76b758385bca0cf10431735a5d9e369b56a +size 709137088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..909fb59 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: FlameF0X/LFM2-350M-Pro-v2 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/FlameF0X/LFM2-350M-Pro-v2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LFM2-350M-Pro-v2-GGUF).*** + +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/LFM2-350M-Pro-v2-GGUF/resolve/main/LFM2-350M-Pro-v2.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-v2-GGUF/resolve/main/LFM2-350M-Pro-v2.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-v2-GGUF/resolve/main/LFM2-350M-Pro-v2.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-v2-GGUF/resolve/main/LFM2-350M-Pro-v2.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-v2-GGUF/resolve/main/LFM2-350M-Pro-v2.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-v2-GGUF/resolve/main/LFM2-350M-Pro-v2.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-v2-GGUF/resolve/main/LFM2-350M-Pro-v2.Q4_K_M.gguf) | Q4_K_M | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-v2-GGUF/resolve/main/LFM2-350M-Pro-v2.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-v2-GGUF/resolve/main/LFM2-350M-Pro-v2.Q5_K_M.gguf) | Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-v2-GGUF/resolve/main/LFM2-350M-Pro-v2.Q6_K.gguf) | Q6_K | 0.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-v2-GGUF/resolve/main/LFM2-350M-Pro-v2.Q8_0.gguf) | Q8_0 | 0.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-v2-GGUF/resolve/main/LFM2-350M-Pro-v2.f16.gguf) | f16 | 0.8 | 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. + +