commit 84be64b909c5585bdde9fd37dcedadf5611e472d Author: ModelHub XC Date: Mon Aug 24 21:39:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/lfm25-350m-struct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..98ff44f --- /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 +lfm25-350m-struct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +lfm25-350m-struct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +lfm25-350m-struct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +lfm25-350m-struct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +lfm25-350m-struct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +lfm25-350m-struct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +lfm25-350m-struct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +lfm25-350m-struct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +lfm25-350m-struct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +lfm25-350m-struct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +lfm25-350m-struct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +lfm25-350m-struct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..dc00675 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: mlabonne/lfm25-350m-struct +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- trl +- grpo +--- +## About + + + + + + + + + +static quants of https://huggingface.co/mlabonne/lfm25-350m-struct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#lfm25-350m-struct-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/lfm25-350m-struct-GGUF/resolve/main/lfm25-350m-struct.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/lfm25-350m-struct-GGUF/resolve/main/lfm25-350m-struct.Q3_K_S.gguf) | Q3_K_S | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/lfm25-350m-struct-GGUF/resolve/main/lfm25-350m-struct.Q3_K_M.gguf) | Q3_K_M | 0.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/lfm25-350m-struct-GGUF/resolve/main/lfm25-350m-struct.Q3_K_L.gguf) | Q3_K_L | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/lfm25-350m-struct-GGUF/resolve/main/lfm25-350m-struct.IQ4_XS.gguf) | IQ4_XS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/lfm25-350m-struct-GGUF/resolve/main/lfm25-350m-struct.Q4_K_S.gguf) | Q4_K_S | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/lfm25-350m-struct-GGUF/resolve/main/lfm25-350m-struct.Q4_K_M.gguf) | Q4_K_M | 0.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/lfm25-350m-struct-GGUF/resolve/main/lfm25-350m-struct.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/lfm25-350m-struct-GGUF/resolve/main/lfm25-350m-struct.Q5_K_M.gguf) | Q5_K_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/lfm25-350m-struct-GGUF/resolve/main/lfm25-350m-struct.Q6_K.gguf) | Q6_K | 0.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/lfm25-350m-struct-GGUF/resolve/main/lfm25-350m-struct.Q8_0.gguf) | Q8_0 | 0.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/lfm25-350m-struct-GGUF/resolve/main/lfm25-350m-struct.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. + + diff --git a/lfm25-350m-struct.IQ4_XS.gguf b/lfm25-350m-struct.IQ4_XS.gguf new file mode 100644 index 0000000..ff5a598 --- /dev/null +++ b/lfm25-350m-struct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10b78e7ee11b40992007c1221c732f638064297409f0bc8b8090565c972667df +size 211805856 diff --git a/lfm25-350m-struct.Q2_K.gguf b/lfm25-350m-struct.Q2_K.gguf new file mode 100644 index 0000000..5cd8391 --- /dev/null +++ b/lfm25-350m-struct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e5182ddb83571d756a4bbff4a2bab873cec1e4fef15c348d8abd7bdb7570e01 +size 160597664 diff --git a/lfm25-350m-struct.Q3_K_L.gguf b/lfm25-350m-struct.Q3_K_L.gguf new file mode 100644 index 0000000..4d71e85 --- /dev/null +++ b/lfm25-350m-struct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c706559553cfe83e6a3402891c6a46700e53e6eac7b3e73562066de29de22253 +size 203048608 diff --git a/lfm25-350m-struct.Q3_K_M.gguf b/lfm25-350m-struct.Q3_K_M.gguf new file mode 100644 index 0000000..544eaf1 --- /dev/null +++ b/lfm25-350m-struct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:918b601a31b17c8a50894f98753989e695ad559cd16483be5e5e3db57e5fa582 +size 193152672 diff --git a/lfm25-350m-struct.Q3_K_S.gguf b/lfm25-350m-struct.Q3_K_S.gguf new file mode 100644 index 0000000..e87f2f4 --- /dev/null +++ b/lfm25-350m-struct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f623b2c5d8c88feee3114ea6260e5169ac44fa3568ef9306ce18f21d3e8cd6e +size 181151392 diff --git a/lfm25-350m-struct.Q4_K_M.gguf b/lfm25-350m-struct.Q4_K_M.gguf new file mode 100644 index 0000000..1a799ef --- /dev/null +++ b/lfm25-350m-struct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99d1f717ecda55cf38c3f35ffa528dd790e25cf4616a15fa1fdc61c499f0c310 +size 229312160 diff --git a/lfm25-350m-struct.Q4_K_S.gguf b/lfm25-350m-struct.Q4_K_S.gguf new file mode 100644 index 0000000..e5ee7dd --- /dev/null +++ b/lfm25-350m-struct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5529763220e2b86af61c527e6e1747cea8f7ddaf44fdd4d9b891d4de2c09a20 +size 220751520 diff --git a/lfm25-350m-struct.Q5_K_M.gguf b/lfm25-350m-struct.Q5_K_M.gguf new file mode 100644 index 0000000..a019e11 --- /dev/null +++ b/lfm25-350m-struct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f356c83b27d2e0a0627e33611a452435dc2984a47f0871504c005e0285c1faae +size 260376224 diff --git a/lfm25-350m-struct.Q5_K_S.gguf b/lfm25-350m-struct.Q5_K_S.gguf new file mode 100644 index 0000000..6d5ed62 --- /dev/null +++ b/lfm25-350m-struct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a91a8e731986175673310157e8226127c4e4b63a6171f60be3bb90ceed01e1d6 +size 255223456 diff --git a/lfm25-350m-struct.Q6_K.gguf b/lfm25-350m-struct.Q6_K.gguf new file mode 100644 index 0000000..e48bdb4 --- /dev/null +++ b/lfm25-350m-struct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c38caf3a9b1b5804549dc96734d7e6e4fb542f1ae0a655bcfae193e70bd0cfae +size 293381792 diff --git a/lfm25-350m-struct.Q8_0.gguf b/lfm25-350m-struct.Q8_0.gguf new file mode 100644 index 0000000..ce801ac --- /dev/null +++ b/lfm25-350m-struct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1ef625d29ace5c89abb367177ac29d019a20b6744f6a3592b7e9f0060ba43b9 +size 379217568 diff --git a/lfm25-350m-struct.f16.gguf b/lfm25-350m-struct.f16.gguf new file mode 100644 index 0000000..0798a0b --- /dev/null +++ b/lfm25-350m-struct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a711be2469fb46381c7495f36c0d056f6586f88f97a3930a17601de4ae0c05c +size 711485088