commit ce37ee4cfcffc62d6bda7c2a005d23a693b43d63 Author: ModelHub XC Date: Sat Jun 13 22:12:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LFM2-350M-Pro-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c12b232 --- /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.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LFM2-350M-Pro.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LFM2-350M-Pro.IQ4_XS.gguf b/LFM2-350M-Pro.IQ4_XS.gguf new file mode 100644 index 0000000..fdd070a --- /dev/null +++ b/LFM2-350M-Pro.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ae324dce355cf8e83d59116ddc07b4e097412da39f0019d7cc760a7297d60fb +size 211805216 diff --git a/LFM2-350M-Pro.Q2_K.gguf b/LFM2-350M-Pro.Q2_K.gguf new file mode 100644 index 0000000..14a0528 --- /dev/null +++ b/LFM2-350M-Pro.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bd5ddc4f479a3d34994e84634fadc09e0b85439004f5283d330b5327a434995 +size 160597024 diff --git a/LFM2-350M-Pro.Q3_K_L.gguf b/LFM2-350M-Pro.Q3_K_L.gguf new file mode 100644 index 0000000..ab4d667 --- /dev/null +++ b/LFM2-350M-Pro.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d429a70b8342b25bf8073ff6b076fb5eb06cc77e0905ec435eb4626573a3e6a +size 203047968 diff --git a/LFM2-350M-Pro.Q3_K_M.gguf b/LFM2-350M-Pro.Q3_K_M.gguf new file mode 100644 index 0000000..d7aad54 --- /dev/null +++ b/LFM2-350M-Pro.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a06bf2957482dcea969acbf5543cc192ab5fd681d4b9e00bc8d8409c14a1cab +size 193152032 diff --git a/LFM2-350M-Pro.Q3_K_S.gguf b/LFM2-350M-Pro.Q3_K_S.gguf new file mode 100644 index 0000000..8d606da --- /dev/null +++ b/LFM2-350M-Pro.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cae8614085a0e6327d67d669f23e8c5682f96fa625bc47bbb9f62facfcff70c9 +size 181150752 diff --git a/LFM2-350M-Pro.Q4_K_M.gguf b/LFM2-350M-Pro.Q4_K_M.gguf new file mode 100644 index 0000000..8d2e3e3 --- /dev/null +++ b/LFM2-350M-Pro.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d06902c491416405b79ae5f3539f54f3dc912e1b65419293c8eebbb3d709169 +size 229311520 diff --git a/LFM2-350M-Pro.Q4_K_S.gguf b/LFM2-350M-Pro.Q4_K_S.gguf new file mode 100644 index 0000000..04907df --- /dev/null +++ b/LFM2-350M-Pro.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:806537ff6e04c6c9c73a8d6f4d6f03583eafa22715a4d3a015fba282c906f96a +size 220750880 diff --git a/LFM2-350M-Pro.Q5_K_M.gguf b/LFM2-350M-Pro.Q5_K_M.gguf new file mode 100644 index 0000000..75eaadc --- /dev/null +++ b/LFM2-350M-Pro.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d426650f9ffccd7ac2ff9c3cb5927042774c4ee2b0b4d43e034d4b6826f0da69 +size 260375584 diff --git a/LFM2-350M-Pro.Q5_K_S.gguf b/LFM2-350M-Pro.Q5_K_S.gguf new file mode 100644 index 0000000..51b52df --- /dev/null +++ b/LFM2-350M-Pro.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd334947c2d726f2cfa3f384b73dbf82585afd9446402c2a72f8b68ce2ce2982 +size 255222816 diff --git a/LFM2-350M-Pro.Q6_K.gguf b/LFM2-350M-Pro.Q6_K.gguf new file mode 100644 index 0000000..86c3307 --- /dev/null +++ b/LFM2-350M-Pro.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7753c26985c7bbefe6926d442a033903f6ea66925c3690444b49edf275d4107b +size 293381152 diff --git a/LFM2-350M-Pro.Q8_0.gguf b/LFM2-350M-Pro.Q8_0.gguf new file mode 100644 index 0000000..5d75a88 --- /dev/null +++ b/LFM2-350M-Pro.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5073d1b9048c195c57a5540b1fba7a5e0ab36337b4ba57f2604c8e95d193b106 +size 379216928 diff --git a/LFM2-350M-Pro.f16.gguf b/LFM2-350M-Pro.f16.gguf new file mode 100644 index 0000000..54cd18a --- /dev/null +++ b/LFM2-350M-Pro.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa7411be47b0041ae340e9d195c74180904f2d57890cb90c2a1936422411c156 +size 711484448 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cbc3870 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: FlameF0X/LFM2-350M-Pro +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/FlameF0X/LFM2-350M-Pro + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LFM2-350M-Pro-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-GGUF/resolve/main/LFM2-350M-Pro.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-GGUF/resolve/main/LFM2-350M-Pro.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-GGUF/resolve/main/LFM2-350M-Pro.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-GGUF/resolve/main/LFM2-350M-Pro.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-GGUF/resolve/main/LFM2-350M-Pro.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-GGUF/resolve/main/LFM2-350M-Pro.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-GGUF/resolve/main/LFM2-350M-Pro.Q4_K_M.gguf) | Q4_K_M | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-GGUF/resolve/main/LFM2-350M-Pro.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-GGUF/resolve/main/LFM2-350M-Pro.Q5_K_M.gguf) | Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-GGUF/resolve/main/LFM2-350M-Pro.Q6_K.gguf) | Q6_K | 0.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-GGUF/resolve/main/LFM2-350M-Pro.Q8_0.gguf) | Q8_0 | 0.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LFM2-350M-Pro-GGUF/resolve/main/LFM2-350M-Pro.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. + +