commit a200f1e59f8d807709a17b98ac98781db5d16472 Author: ModelHub XC Date: Fri Jun 12 19:04:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/bella-2-8b-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..70ee096 --- /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 +bella-2-8b.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +bella-2-8b.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e80d296 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: CognitivessAI/bella-2-8b +language: +- en +- ro +library_name: transformers +license: apache-2.0 +license_link: https://cognitivess.com/terms +license_name: cognitivess +quantized_by: mradermacher +tags: +- text-generation-inference +- text-generation +- Sentiment Analysis +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/CognitivessAI/bella-2-8b + + +static quants are available at https://huggingface.co/mradermacher/bella-2-8b-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/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/bella-2-8b-i1-GGUF/resolve/main/bella-2-8b.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | 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/bella-2-8b.i1-IQ1_M.gguf b/bella-2-8b.i1-IQ1_M.gguf new file mode 100644 index 0000000..cb6082a --- /dev/null +++ b/bella-2-8b.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe1ebe53e2c6da1c684748fbc814be004dc605c3f082c0ebf7f1c6014cee994a +size 2161972320 diff --git a/bella-2-8b.i1-IQ1_S.gguf b/bella-2-8b.i1-IQ1_S.gguf new file mode 100644 index 0000000..bd5f482 --- /dev/null +++ b/bella-2-8b.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e02f45654ab3e4f40d1b868949453baa706d82e985c206f126660cdaf8a0cebe +size 2019628128 diff --git a/bella-2-8b.i1-IQ2_M.gguf b/bella-2-8b.i1-IQ2_M.gguf new file mode 100644 index 0000000..e06221d --- /dev/null +++ b/bella-2-8b.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3eba91857eed236e275b0f10793c9f8969beeb93c4c23ef61fbd92972ccfc1cf +size 2948281440 diff --git a/bella-2-8b.i1-IQ2_S.gguf b/bella-2-8b.i1-IQ2_S.gguf new file mode 100644 index 0000000..27e698d --- /dev/null +++ b/bella-2-8b.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d8a3dbccc21939cb5e2cc2f26a270a70bcbf35ecc5dbc0ad39812bb549e1820 +size 2758489184 diff --git a/bella-2-8b.i1-IQ2_XS.gguf b/bella-2-8b.i1-IQ2_XS.gguf new file mode 100644 index 0000000..8fc75c9 --- /dev/null +++ b/bella-2-8b.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50f1a26fe690acdf892db71ee54e5ccdbedcffa91d1fa696ebc1de77319c0a63 +size 2605782112 diff --git a/bella-2-8b.i1-IQ2_XXS.gguf b/bella-2-8b.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..a2d8653 --- /dev/null +++ b/bella-2-8b.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba601e983cd4c96c93be5dcb7ec1e8889969f0f83bbdbd98360df367b0692467 +size 2399212640 diff --git a/bella-2-8b.i1-IQ3_M.gguf b/bella-2-8b.i1-IQ3_M.gguf new file mode 100644 index 0000000..69af9f4 --- /dev/null +++ b/bella-2-8b.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3491b6729bb243d6b9cb430c5562a5c671860c55a230f7f5c73c44387a48984 +size 3784823904 diff --git a/bella-2-8b.i1-IQ3_S.gguf b/bella-2-8b.i1-IQ3_S.gguf new file mode 100644 index 0000000..96e03fa --- /dev/null +++ b/bella-2-8b.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8e119f262e3e43c2a0f51be166b6d5d2ac80b724e604c6d35775c8b1677dd07 +size 3682325600 diff --git a/bella-2-8b.i1-IQ3_XS.gguf b/bella-2-8b.i1-IQ3_XS.gguf new file mode 100644 index 0000000..e6a88ed --- /dev/null +++ b/bella-2-8b.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6442efbac7bb1564d0e6b7063c0a73fb38ee9e7a862ee5b9d0bb56fd374c222d +size 3518747744 diff --git a/bella-2-8b.i1-IQ3_XXS.gguf b/bella-2-8b.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..9c6abe8 --- /dev/null +++ b/bella-2-8b.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae88f1fff5745a18e900d0f98c9d0b3a4d14b86a05d580f68ad86ec66c359bb5 +size 3274912864 diff --git a/bella-2-8b.i1-IQ4_XS.gguf b/bella-2-8b.i1-IQ4_XS.gguf new file mode 100644 index 0000000..eac7928 --- /dev/null +++ b/bella-2-8b.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abb15906f3fe23702d157ccd70db7876c2d042f4e5cca6b7c2b90eda0beeba35 +size 4447663200 diff --git a/bella-2-8b.i1-Q2_K.gguf b/bella-2-8b.i1-Q2_K.gguf new file mode 100644 index 0000000..f09d372 --- /dev/null +++ b/bella-2-8b.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07bcada91d39ca6e718bd23629f72821b16abb0a5509e8d56d10a8d3814ca466 +size 3179132000 diff --git a/bella-2-8b.i1-Q3_K_L.gguf b/bella-2-8b.i1-Q3_K_L.gguf new file mode 100644 index 0000000..7f33f6f --- /dev/null +++ b/bella-2-8b.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06da5092fb2f7906a44e54d73d904ae1ec6ae7096660a81261e5ad61360c748 +size 4321956960 diff --git a/bella-2-8b.i1-Q3_K_M.gguf b/bella-2-8b.i1-Q3_K_M.gguf new file mode 100644 index 0000000..812f4bd --- /dev/null +++ b/bella-2-8b.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e7b9d806b64addce84a7b755f816c741875f0366a4e2ca05e301343c5b0b311 +size 4018918496 diff --git a/bella-2-8b.i1-Q3_K_S.gguf b/bella-2-8b.i1-Q3_K_S.gguf new file mode 100644 index 0000000..9f79d35 --- /dev/null +++ b/bella-2-8b.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5fe661cd5d37922aee51b9b7686e8c1feac8493185e7b3b26f373751a7e23ec +size 3664499808 diff --git a/bella-2-8b.i1-Q4_0.gguf b/bella-2-8b.i1-Q4_0.gguf new file mode 100644 index 0000000..b683b5c --- /dev/null +++ b/bella-2-8b.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ab097be0139cbe7ea60db393f95ce4d0a92d9eeeac510f1dd357763c3c209fb +size 4675892320 diff --git a/bella-2-8b.i1-Q4_K_M.gguf b/bella-2-8b.i1-Q4_K_M.gguf new file mode 100644 index 0000000..bfabbef --- /dev/null +++ b/bella-2-8b.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e9274c246056490d29bc68141b91a6541336973fe9a943f212337b552ed82fd +size 4920734816 diff --git a/bella-2-8b.i1-Q4_K_S.gguf b/bella-2-8b.i1-Q4_K_S.gguf new file mode 100644 index 0000000..4884020 --- /dev/null +++ b/bella-2-8b.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f67a40baf073f3eba58fe1008c7b785b9a98bddf3c5485ffb18561d2c456a33 +size 4692669536 diff --git a/bella-2-8b.i1-Q5_K_M.gguf b/bella-2-8b.i1-Q5_K_M.gguf new file mode 100644 index 0000000..8c8a3b8 --- /dev/null +++ b/bella-2-8b.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4444b8737e1ff23996130972edd673ce40e614b1d9a00821d85bc760fc85199 +size 5732988000 diff --git a/bella-2-8b.i1-Q5_K_S.gguf b/bella-2-8b.i1-Q5_K_S.gguf new file mode 100644 index 0000000..5b123cc --- /dev/null +++ b/bella-2-8b.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d41340e4d63a20e8556aa293b7babbf314c9048320c5124f405de924a290a038 +size 5599294560 diff --git a/bella-2-8b.i1-Q6_K.gguf b/bella-2-8b.i1-Q6_K.gguf new file mode 100644 index 0000000..b2f2588 --- /dev/null +++ b/bella-2-8b.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d03ae2d033b66fbeb1d378102c3a046138e6256b505a9bf100551a9fd26e457 +size 6596007008 diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..9f57f51 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3160a8d47581e6cd1f82b73116bddd7030eab248d0cf3ff473ebabc497760cda +size 4988161