commit f9a51d569503422ccc48ea571577789ea27b7686 Author: ModelHub XC Date: Sun Jun 14 03:34:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MMR1-3B-RL-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..eaabcb6 --- /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 +MMR1-3B-RL.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MMR1-3B-RL.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +MMR1-3B-RL.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MMR1-3B-RL.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MMR1-3B-RL.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MMR1-3B-RL.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MMR1-3B-RL.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MMR1-3B-RL.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MMR1-3B-RL.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MMR1-3B-RL.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MMR1-3B-RL.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MMR1-3B-RL.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MMR1-3B-RL.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MMR1-3B-RL.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MMR1-3B-RL.IQ4_XS.gguf b/MMR1-3B-RL.IQ4_XS.gguf new file mode 100644 index 0000000..25def99 --- /dev/null +++ b/MMR1-3B-RL.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:327439f36cf0fd31951fdcbfea028614b9d7576582470961152d5f8bdda12348 +size 1918490048 diff --git a/MMR1-3B-RL.Q2_K.gguf b/MMR1-3B-RL.Q2_K.gguf new file mode 100644 index 0000000..1b63932 --- /dev/null +++ b/MMR1-3B-RL.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5a1f5d340d923f506fc962b604471a85dbc6d700b5f4390aa51e41944b92064 +size 1376855488 diff --git a/MMR1-3B-RL.Q3_K_L.gguf b/MMR1-3B-RL.Q3_K_L.gguf new file mode 100644 index 0000000..8311edc --- /dev/null +++ b/MMR1-3B-RL.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:466dad22b994b5fc1ad46904bcae7c59add3cf9d8431bb01246ea2d1bc8d1905 +size 1841094080 diff --git a/MMR1-3B-RL.Q3_K_M.gguf b/MMR1-3B-RL.Q3_K_M.gguf new file mode 100644 index 0000000..a6f0cb4 --- /dev/null +++ b/MMR1-3B-RL.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54f375f912b470e8a3269bb8b6d978a56fc474fb70d5ebd9afb9c553b2759dd4 +size 1724177856 diff --git a/MMR1-3B-RL.Q3_K_S.gguf b/MMR1-3B-RL.Q3_K_S.gguf new file mode 100644 index 0000000..260c5ed --- /dev/null +++ b/MMR1-3B-RL.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef55c97d9edba2b3dbc8e4e33da3a63afdafde757f77a556c02b612da1d0e29a +size 1588059584 diff --git a/MMR1-3B-RL.Q4_K_M.gguf b/MMR1-3B-RL.Q4_K_M.gguf new file mode 100644 index 0000000..5568eed --- /dev/null +++ b/MMR1-3B-RL.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6a79d3a5876a5bcfebe63e2e0f110dc4c99bf4594258bd0e954ef19aee9f4e8 +size 2104931776 diff --git a/MMR1-3B-RL.Q4_K_S.gguf b/MMR1-3B-RL.Q4_K_S.gguf new file mode 100644 index 0000000..5e927ce --- /dev/null +++ b/MMR1-3B-RL.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c2f669e1c62a9e7386d6482982a3796283f52bb3db8cad3d4729eb8255c50d6 +size 2009413056 diff --git a/MMR1-3B-RL.Q5_K_M.gguf b/MMR1-3B-RL.Q5_K_M.gguf new file mode 100644 index 0000000..b938a10 --- /dev/null +++ b/MMR1-3B-RL.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:150760b5c1b36ba41dd07abdc2ffe31766499b881742b0a18db2df6d355b298a +size 2438739392 diff --git a/MMR1-3B-RL.Q5_K_S.gguf b/MMR1-3B-RL.Q5_K_S.gguf new file mode 100644 index 0000000..a63502b --- /dev/null +++ b/MMR1-3B-RL.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a49ba1e5de1bc3bd2eca8646b51fd9524534573c16cae182ad8a0c58e57b5cf +size 2383590848 diff --git a/MMR1-3B-RL.Q6_K.gguf b/MMR1-3B-RL.Q6_K.gguf new file mode 100644 index 0000000..49db2ee --- /dev/null +++ b/MMR1-3B-RL.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34b74062f9784dda447ba7eab2c3b7fc431fee6917e342cd9aad8e83a75ffc94 +size 2793409984 diff --git a/MMR1-3B-RL.Q8_0.gguf b/MMR1-3B-RL.Q8_0.gguf new file mode 100644 index 0000000..2192146 --- /dev/null +++ b/MMR1-3B-RL.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:045b317285d513e6ed5b4d49e432a43364c21b79acc29ddc8a8a3b0553c7e7f2 +size 3616087488 diff --git a/MMR1-3B-RL.f16.gguf b/MMR1-3B-RL.f16.gguf new file mode 100644 index 0000000..976eb8e --- /dev/null +++ b/MMR1-3B-RL.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb1477c08ac03c660bb9e29afcf637048844285f3f8c6c6ec43ff489f67b8daa +size 6800645568 diff --git a/MMR1-3B-RL.mmproj-Q8_0.gguf b/MMR1-3B-RL.mmproj-Q8_0.gguf new file mode 100644 index 0000000..65e323c --- /dev/null +++ b/MMR1-3B-RL.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f542b78f9ddefce27cb686296e8ce6742e94e49589b2ba31123890c544820fd +size 847768256 diff --git a/MMR1-3B-RL.mmproj-f16.gguf b/MMR1-3B-RL.mmproj-f16.gguf new file mode 100644 index 0000000..447d003 --- /dev/null +++ b/MMR1-3B-RL.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e0e3ee973d30edad6fe4f27c1fe25b7ae8b8e75b3aa275396674783c2236f6e +size 1338428096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5b49aea --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: MMR1/MMR1-3B-RL +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- multimodal-llm +- qwen +- reasoning +- llm +--- +## About + + + + + + + + + +static quants of https://huggingface.co/MMR1/MMR1-3B-RL + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MMR1-3B-RL-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/MMR1-3B-RL-GGUF/resolve/main/MMR1-3B-RL.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/MMR1-3B-RL-GGUF/resolve/main/MMR1-3B-RL.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/MMR1-3B-RL-GGUF/resolve/main/MMR1-3B-RL.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/MMR1-3B-RL-GGUF/resolve/main/MMR1-3B-RL.Q3_K_S.gguf) | Q3_K_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/MMR1-3B-RL-GGUF/resolve/main/MMR1-3B-RL.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MMR1-3B-RL-GGUF/resolve/main/MMR1-3B-RL.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/MMR1-3B-RL-GGUF/resolve/main/MMR1-3B-RL.IQ4_XS.gguf) | IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/MMR1-3B-RL-GGUF/resolve/main/MMR1-3B-RL.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MMR1-3B-RL-GGUF/resolve/main/MMR1-3B-RL.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MMR1-3B-RL-GGUF/resolve/main/MMR1-3B-RL.Q5_K_S.gguf) | Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/MMR1-3B-RL-GGUF/resolve/main/MMR1-3B-RL.Q5_K_M.gguf) | Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/MMR1-3B-RL-GGUF/resolve/main/MMR1-3B-RL.Q6_K.gguf) | Q6_K | 2.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MMR1-3B-RL-GGUF/resolve/main/MMR1-3B-RL.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MMR1-3B-RL-GGUF/resolve/main/MMR1-3B-RL.f16.gguf) | f16 | 6.9 | 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. + +