commit d691d4b9ccc0bcecdae0080bedda171c37e971a4 Author: ModelHub XC Date: Thu Apr 30 12:13:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MiniMA-2-3B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..717223c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,57 @@ +*.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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +MiniMA-2-3B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MiniMA-2-3B.i1-IQ1_M.gguf b/MiniMA-2-3B.i1-IQ1_M.gguf new file mode 100644 index 0000000..9496737 --- /dev/null +++ b/MiniMA-2-3B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ceafc4bae8a28cc345c1ffe83ca7111c940378da8cebf4c0c68f15866fbc45c +size 791683744 diff --git a/MiniMA-2-3B.i1-IQ1_S.gguf b/MiniMA-2-3B.i1-IQ1_S.gguf new file mode 100644 index 0000000..1d181d7 --- /dev/null +++ b/MiniMA-2-3B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:853ab01e7e0a297cd5098fff1fca8799853c76537d7eaa28268510a9c1c11149 +size 740369056 diff --git a/MiniMA-2-3B.i1-IQ2_M.gguf b/MiniMA-2-3B.i1-IQ2_M.gguf new file mode 100644 index 0000000..0d8bf38 --- /dev/null +++ b/MiniMA-2-3B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e0991636f31f88b8000b8a417ca48935578fac94459721d8261b99589274690 +size 1099002016 diff --git a/MiniMA-2-3B.i1-IQ2_S.gguf b/MiniMA-2-3B.i1-IQ2_S.gguf new file mode 100644 index 0000000..c457972 --- /dev/null +++ b/MiniMA-2-3B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aca1ebf3625b1742a66f37c37bc1a061c3d13d6de062fa9f7cfdec975effb5fc +size 1030582432 diff --git a/MiniMA-2-3B.i1-IQ2_XS.gguf b/MiniMA-2-3B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..11f99bb --- /dev/null +++ b/MiniMA-2-3B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97cc733e8ea00ea1f902e200112560dae7f8648b9414c629401540c4997b918e +size 952705696 diff --git a/MiniMA-2-3B.i1-IQ2_XXS.gguf b/MiniMA-2-3B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..de25cb0 --- /dev/null +++ b/MiniMA-2-3B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:285ff049a09f442550aae77ce2c5dd8e98057cd66c89e5834e9256bfdae2c9ba +size 877208224 diff --git a/MiniMA-2-3B.i1-IQ3_M.gguf b/MiniMA-2-3B.i1-IQ3_M.gguf new file mode 100644 index 0000000..21d95f3 --- /dev/null +++ b/MiniMA-2-3B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b423404cb029116d704e54bb6f833170b5585768f8b6880e7507ae8719dde8a7 +size 1428739744 diff --git a/MiniMA-2-3B.i1-IQ3_S.gguf b/MiniMA-2-3B.i1-IQ3_S.gguf new file mode 100644 index 0000000..4fe4084 --- /dev/null +++ b/MiniMA-2-3B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcf7d277764a1e11d183367fe24c12b321c84fffb810eb1a1f751b3608d5c82b +size 1358550688 diff --git a/MiniMA-2-3B.i1-IQ3_XS.gguf b/MiniMA-2-3B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..50d0f8b --- /dev/null +++ b/MiniMA-2-3B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00fc8e36d058265c346480c4c37a8eaaa37aab34a588e75be8f58df487c05389 +size 1294849696 diff --git a/MiniMA-2-3B.i1-IQ3_XXS.gguf b/MiniMA-2-3B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..4ee75db --- /dev/null +++ b/MiniMA-2-3B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb6765a8179907cecbf2033dbfaea10490065759f5b8113998258fd4c6617c98 +size 1193373856 diff --git a/MiniMA-2-3B.i1-IQ4_XS.gguf b/MiniMA-2-3B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..d6bb44a --- /dev/null +++ b/MiniMA-2-3B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:562755bd4a4ffe9adaff127c583f0f0a180c251ec301dfe05a70797b9d432521 +size 1649943712 diff --git a/MiniMA-2-3B.i1-Q2_K.gguf b/MiniMA-2-3B.i1-Q2_K.gguf new file mode 100644 index 0000000..dcd02fd --- /dev/null +++ b/MiniMA-2-3B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75ef5c8713081e69fed90ae084b41dbeed29811525261ffa1cd3200155b70d36 +size 1174505632 diff --git a/MiniMA-2-3B.i1-Q3_K_L.gguf b/MiniMA-2-3B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..14f0851 --- /dev/null +++ b/MiniMA-2-3B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62b774826b691ce2d9fdb007f98b01f2791be75c38144292f652dfaf9db65b03 +size 1631049376 diff --git a/MiniMA-2-3B.i1-Q3_K_M.gguf b/MiniMA-2-3B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..14e911a --- /dev/null +++ b/MiniMA-2-3B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cff6f92d51cba0e85c4b3affd39257c764293cc3f210b2761aa9055880bdec7c +size 1504433824 diff --git a/MiniMA-2-3B.i1-Q3_K_S.gguf b/MiniMA-2-3B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..d87ea9a --- /dev/null +++ b/MiniMA-2-3B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15e3e34067b8a8f2faa311474f5ff83e02240b6a584218af60c2cb666b7b1566 +size 1358550688 diff --git a/MiniMA-2-3B.i1-Q4_0.gguf b/MiniMA-2-3B.i1-Q4_0.gguf new file mode 100644 index 0000000..461a62b --- /dev/null +++ b/MiniMA-2-3B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f041e51683a212382599e1fe6065045ed2a5d3e760c130c090aa353dd5476db6 +size 1744321696 diff --git a/MiniMA-2-3B.i1-Q4_K_M.gguf b/MiniMA-2-3B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..fbe4380 --- /dev/null +++ b/MiniMA-2-3B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b2533f1f6ebb94fce839320e45a2f5f9e2d987e2440c9a283e4e8c6a3414b82 +size 1846656160 diff --git a/MiniMA-2-3B.i1-Q4_K_S.gguf b/MiniMA-2-3B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..8af095a --- /dev/null +++ b/MiniMA-2-3B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:259d67a0cfa156d0edcb58704a331253537854b0c021843aea28a57eb8080300 +size 1753758880 diff --git a/MiniMA-2-3B.i1-Q5_K_M.gguf b/MiniMA-2-3B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..e39821d --- /dev/null +++ b/MiniMA-2-3B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59c7e7fd39a2bb089d0925d1335b6611742bf366e9d4ea171fe27e0cba2e5430 +size 2153389216 diff --git a/MiniMA-2-3B.i1-Q5_K_S.gguf b/MiniMA-2-3B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..fbf62ee --- /dev/null +++ b/MiniMA-2-3B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09d1b77c14591043bdd4bf031c56bf4d44b1867007335c557386b6abf496fd07 +size 2098240672 diff --git a/MiniMA-2-3B.i1-Q6_K.gguf b/MiniMA-2-3B.i1-Q6_K.gguf new file mode 100644 index 0000000..0bd1e4c --- /dev/null +++ b/MiniMA-2-3B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dd1bb06ec6824481191e295bfa0067ad94424718094b57a33c0c9ed386aa7e5 +size 2479293088 diff --git a/README.md b/README.md new file mode 100644 index 0000000..80b3f71 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: GeneZC/MiniMA-2-3B +datasets: +- EleutherAI/pile +- togethercomputer/RedPajama-Data-1T +- p208p2002/wudao +language: +- en +- zh +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/GeneZC/MiniMA-2-3B + + +static quants are available at https://huggingface.co/mradermacher/MiniMA-2-3B-GGUF +## 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/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.8 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-IQ2_S.gguf) | i1-IQ2_S | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-IQ2_M.gguf) | i1-IQ2_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-Q2_K.gguf) | i1-Q2_K | 1.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-IQ3_S.gguf) | i1-IQ3_S | 1.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-IQ3_M.gguf) | i1-IQ3_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 1.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 1.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-Q4_0.gguf) | i1-Q4_0 | 1.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 1.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MiniMA-2-3B-i1-GGUF/resolve/main/MiniMA-2-3B.i1-Q6_K.gguf) | i1-Q6_K | 2.6 | practically like static Q6_K | + +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. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..4fcf216 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0bb7141ef472d63d72486fc3a83ef5c5a49d57116accdde1d64a27936654c09 +size 2561461