commit cc4ac8007614d03e93f2534b4e96c8c2dfcda6b3 Author: ModelHub XC Date: Mon Apr 27 14:15:21 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/cerbero-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d412e48 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +cerbero-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cerbero-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +cerbero-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cerbero-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cerbero-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +cerbero-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +cerbero-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +cerbero-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cerbero-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +cerbero-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cerbero-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cerbero-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +cerbero-7b.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..08a5e38 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: galatolo/cerbero-7b +datasets: +- andreabac3/Quora-Italian-Fauno-Baize +- andreabac3/StackOverflow-Italian-Fauno-Baize +- andreabac3/MedQuaAD-Italian-Fauno-Baize +language: +- it +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/galatolo/cerbero-7b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/cerbero-7b-i1-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/cerbero-7b-GGUF/resolve/main/cerbero-7b.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/cerbero-7b-GGUF/resolve/main/cerbero-7b.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/cerbero-7b-GGUF/resolve/main/cerbero-7b.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/cerbero-7b-GGUF/resolve/main/cerbero-7b.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/cerbero-7b-GGUF/resolve/main/cerbero-7b.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/cerbero-7b-GGUF/resolve/main/cerbero-7b.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/cerbero-7b-GGUF/resolve/main/cerbero-7b.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/cerbero-7b-GGUF/resolve/main/cerbero-7b.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/cerbero-7b-GGUF/resolve/main/cerbero-7b.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/cerbero-7b-GGUF/resolve/main/cerbero-7b.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/cerbero-7b-GGUF/resolve/main/cerbero-7b.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/cerbero-7b-GGUF/resolve/main/cerbero-7b.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/cerbero-7b-GGUF/resolve/main/cerbero-7b.f16.gguf) | f16 | 14.6 | 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/cerbero-7b.IQ4_XS.gguf b/cerbero-7b.IQ4_XS.gguf new file mode 100644 index 0000000..db44e05 --- /dev/null +++ b/cerbero-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b54f2f152c7045b80255dfcdd96f66523987f9e3b3cdb2eef9bd1833e929d56 +size 3944390368 diff --git a/cerbero-7b.Q2_K.gguf b/cerbero-7b.Q2_K.gguf new file mode 100644 index 0000000..5239507 --- /dev/null +++ b/cerbero-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c382c864bd8c0ea8d27e14c0e7e4e8baa03bcbde910971a35fb41062ece7ac04 +size 2719244000 diff --git a/cerbero-7b.Q3_K_L.gguf b/cerbero-7b.Q3_K_L.gguf new file mode 100644 index 0000000..df1f1c5 --- /dev/null +++ b/cerbero-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de10ca743d0d527f46a87735c27faef4c5e3c87ea51f1f746e28a1a096d13ba5 +size 3822026464 diff --git a/cerbero-7b.Q3_K_M.gguf b/cerbero-7b.Q3_K_M.gguf new file mode 100644 index 0000000..89489db --- /dev/null +++ b/cerbero-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf747530fcef9c57394070a7016e4c40a0bf9ed2b44d0f8ff1469349411b1c55 +size 3518988000 diff --git a/cerbero-7b.Q3_K_S.gguf b/cerbero-7b.Q3_K_S.gguf new file mode 100644 index 0000000..10af91e --- /dev/null +++ b/cerbero-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69b09b64a6b8747d88183e698bad0bec11a4b39cda4c7ad9f3b4ee7d301c7ae4 +size 3164569312 diff --git a/cerbero-7b.Q4_0_4_4.gguf b/cerbero-7b.Q4_0_4_4.gguf new file mode 100644 index 0000000..f511744 --- /dev/null +++ b/cerbero-7b.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b04a4a8cebcfc14a852b14798b035812059c8514904bb1d15c839d206ed1bba7 +size 4108918496 diff --git a/cerbero-7b.Q4_K_M.gguf b/cerbero-7b.Q4_K_M.gguf new file mode 100644 index 0000000..c8b82d5 --- /dev/null +++ b/cerbero-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba58393b79dab8c2eae7ca85ddd75ec456f970defad41a7e344f95da3ea538ac +size 4368441056 diff --git a/cerbero-7b.Q4_K_S.gguf b/cerbero-7b.Q4_K_S.gguf new file mode 100644 index 0000000..a86114d --- /dev/null +++ b/cerbero-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:799accaaf0f6180a4b3ae1c8a035e46a5043ec7e8dbf772eb07e76d0a08be279 +size 4140375776 diff --git a/cerbero-7b.Q5_K_M.gguf b/cerbero-7b.Q5_K_M.gguf new file mode 100644 index 0000000..a21be18 --- /dev/null +++ b/cerbero-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bff4eff93d2c88984d097c57a8fdedbc2fbc29a6fc451ab436f4c8f851bce160 +size 5131411168 diff --git a/cerbero-7b.Q5_K_S.gguf b/cerbero-7b.Q5_K_S.gguf new file mode 100644 index 0000000..5d80d93 --- /dev/null +++ b/cerbero-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0236534d96d4123a599efb93088afd6624b8b18dc175bd40b060fb6be2298540 +size 4997717728 diff --git a/cerbero-7b.Q6_K.gguf b/cerbero-7b.Q6_K.gguf new file mode 100644 index 0000000..e795bf2 --- /dev/null +++ b/cerbero-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d1b838ae549a2e028e814adc045a44fb343fc901fc66f3f2c614e618448fb4c +size 5942066912 diff --git a/cerbero-7b.Q8_0.gguf b/cerbero-7b.Q8_0.gguf new file mode 100644 index 0000000..a3168d5 --- /dev/null +++ b/cerbero-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:537bfb76a32a5f1613c6349ef485f435a84dc5439c9e8a36851f0861bb326421 +size 7695859424 diff --git a/cerbero-7b.f16.gguf b/cerbero-7b.f16.gguf new file mode 100644 index 0000000..6b05afc --- /dev/null +++ b/cerbero-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f154479e5358364bc8ba5baa76d6c03cb9f13137b71637f84a5d6dd5afe75c88 +size 14484733664