commit e1162e29f200b48220eb85451cf7e9ce82987196 Author: ModelHub XC Date: Tue Oct 20 11:54:24 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MiLMMT-46-4B-v1.0-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..de54a7a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +MiLMMT-46-4B-v1.0.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MiLMMT-46-4B-v1.0.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +MiLMMT-46-4B-v1.0.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MiLMMT-46-4B-v1.0.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MiLMMT-46-4B-v1.0.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MiLMMT-46-4B-v1.0.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiLMMT-46-4B-v1.0.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiLMMT-46-4B-v1.0.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiLMMT-46-4B-v1.0.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiLMMT-46-4B-v1.0.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiLMMT-46-4B-v1.0.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiLMMT-46-4B-v1.0.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MiLMMT-46-4B-v1.0.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MiLMMT-46-4B-v1.0.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MiLMMT-46-4B-v1.0.IQ4_XS.gguf b/MiLMMT-46-4B-v1.0.IQ4_XS.gguf new file mode 100644 index 0000000..9736c4e --- /dev/null +++ b/MiLMMT-46-4B-v1.0.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66a1cef8260ab1dd6d8bd8554e6dc19c97a9bae72617e78c28fa796c981a9981 +size 2279624992 diff --git a/MiLMMT-46-4B-v1.0.Q2_K.gguf b/MiLMMT-46-4B-v1.0.Q2_K.gguf new file mode 100644 index 0000000..e7591c6 --- /dev/null +++ b/MiLMMT-46-4B-v1.0.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3452bb3bb63a07b92b140aa8bb62befacb1959dc7e9c23b684845f21a96a99c +size 1729163552 diff --git a/MiLMMT-46-4B-v1.0.Q3_K_L.gguf b/MiLMMT-46-4B-v1.0.Q3_K_L.gguf new file mode 100644 index 0000000..78ac591 --- /dev/null +++ b/MiLMMT-46-4B-v1.0.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6db08e3cf5f4a756120e01239c54ad1a8edc496fd5d3e0853fa9a46147d63d9 +size 2236084512 diff --git a/MiLMMT-46-4B-v1.0.Q3_K_M.gguf b/MiLMMT-46-4B-v1.0.Q3_K_M.gguf new file mode 100644 index 0000000..982ddb4 --- /dev/null +++ b/MiLMMT-46-4B-v1.0.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df0774cbdfc9be0650b675194d36b2543d48296da8348db2895003592a20ef2d +size 2098458912 diff --git a/MiLMMT-46-4B-v1.0.Q3_K_S.gguf b/MiLMMT-46-4B-v1.0.Q3_K_S.gguf new file mode 100644 index 0000000..15aa47f --- /dev/null +++ b/MiLMMT-46-4B-v1.0.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f22251c4abd9b19ce22155f688751be303397c2dbd1a93a8561665a5c4e06ba7 +size 1937363232 diff --git a/MiLMMT-46-4B-v1.0.Q4_K_M.gguf b/MiLMMT-46-4B-v1.0.Q4_K_M.gguf new file mode 100644 index 0000000..2b44c28 --- /dev/null +++ b/MiLMMT-46-4B-v1.0.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25424cbb5423afaa22b1b53bfb3d8aa116cfd84b5f8dcfa82363bfb3c4221ddf +size 2489893152 diff --git a/MiLMMT-46-4B-v1.0.Q4_K_S.gguf b/MiLMMT-46-4B-v1.0.Q4_K_S.gguf new file mode 100644 index 0000000..08142a5 --- /dev/null +++ b/MiLMMT-46-4B-v1.0.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2740cba76c863b6fa258fb0e5722c676e0d49443b56a617e66a7856559702ece +size 2377928992 diff --git a/MiLMMT-46-4B-v1.0.Q5_K_M.gguf b/MiLMMT-46-4B-v1.0.Q5_K_M.gguf new file mode 100644 index 0000000..f50f46e --- /dev/null +++ b/MiLMMT-46-4B-v1.0.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ff57e6723b0a551446732cbbe40cdc210d19813de4e5e51476bc1ae365bce78 +size 2829697312 diff --git a/MiLMMT-46-4B-v1.0.Q5_K_S.gguf b/MiLMMT-46-4B-v1.0.Q5_K_S.gguf new file mode 100644 index 0000000..ecc2892 --- /dev/null +++ b/MiLMMT-46-4B-v1.0.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0fdff8b3ee7873756435faa9207e5c8c0fc3887f3eeecedd65ac253285334a4 +size 2764591392 diff --git a/MiLMMT-46-4B-v1.0.Q6_K.gguf b/MiLMMT-46-4B-v1.0.Q6_K.gguf new file mode 100644 index 0000000..5038c38 --- /dev/null +++ b/MiLMMT-46-4B-v1.0.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:056d0c29d132a8f77a791720e8032b252c1d4af3c5696a132aaf85416c4fc00b +size 3190739232 diff --git a/MiLMMT-46-4B-v1.0.Q8_0.gguf b/MiLMMT-46-4B-v1.0.Q8_0.gguf new file mode 100644 index 0000000..d48fe63 --- /dev/null +++ b/MiLMMT-46-4B-v1.0.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92796e263e22461c273c9f964ba4c1454d8dc764a482af60bc1ad9c269d9e7d0 +size 4130401312 diff --git a/MiLMMT-46-4B-v1.0.f16.gguf b/MiLMMT-46-4B-v1.0.f16.gguf new file mode 100644 index 0000000..081a7a1 --- /dev/null +++ b/MiLMMT-46-4B-v1.0.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad0b6df7f0449958184830f496994298ebd9effa915b97811d6e653fed19d059 +size 7767802912 diff --git a/MiLMMT-46-4B-v1.0.mmproj-Q8_0.gguf b/MiLMMT-46-4B-v1.0.mmproj-Q8_0.gguf new file mode 100644 index 0000000..d1a50ef --- /dev/null +++ b/MiLMMT-46-4B-v1.0.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b2d2a9c92a67e825e678d888951198d05f867b1b24d3d62009616dd330b1f7 +size 591377952 diff --git a/MiLMMT-46-4B-v1.0.mmproj-f16.gguf b/MiLMMT-46-4B-v1.0.mmproj-f16.gguf new file mode 100644 index 0000000..393ad9a --- /dev/null +++ b/MiLMMT-46-4B-v1.0.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8e919bd78ce9af53c1233bfd95aed6d8608494ed7fa2fbbbdf5220b2a58815b +size 851251872 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f919913 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: xiaomi-research/MiLMMT-46-4B-v1.0 +language: +- en +library_name: transformers +license: gemma +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/xiaomi-research/MiLMMT-46-4B-v1.0 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MiLMMT-46-4B-v1.0-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/MiLMMT-46-4B-v1.0-GGUF/resolve/main/MiLMMT-46-4B-v1.0.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/MiLMMT-46-4B-v1.0-GGUF/resolve/main/MiLMMT-46-4B-v1.0.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/MiLMMT-46-4B-v1.0-GGUF/resolve/main/MiLMMT-46-4B-v1.0.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/MiLMMT-46-4B-v1.0-GGUF/resolve/main/MiLMMT-46-4B-v1.0.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/MiLMMT-46-4B-v1.0-GGUF/resolve/main/MiLMMT-46-4B-v1.0.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MiLMMT-46-4B-v1.0-GGUF/resolve/main/MiLMMT-46-4B-v1.0.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MiLMMT-46-4B-v1.0-GGUF/resolve/main/MiLMMT-46-4B-v1.0.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/MiLMMT-46-4B-v1.0-GGUF/resolve/main/MiLMMT-46-4B-v1.0.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MiLMMT-46-4B-v1.0-GGUF/resolve/main/MiLMMT-46-4B-v1.0.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MiLMMT-46-4B-v1.0-GGUF/resolve/main/MiLMMT-46-4B-v1.0.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/MiLMMT-46-4B-v1.0-GGUF/resolve/main/MiLMMT-46-4B-v1.0.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/MiLMMT-46-4B-v1.0-GGUF/resolve/main/MiLMMT-46-4B-v1.0.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MiLMMT-46-4B-v1.0-GGUF/resolve/main/MiLMMT-46-4B-v1.0.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MiLMMT-46-4B-v1.0-GGUF/resolve/main/MiLMMT-46-4B-v1.0.f16.gguf) | f16 | 7.9 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +