commit 91a23487896f1eaf7347ff2f832c3e5dac71ccd7 Author: ModelHub XC Date: Sat Oct 24 21:16:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/cuscuz-7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f63c35b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +cuscuz-7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +cuscuz-7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cuscuz-7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cuscuz-7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cuscuz-7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +cuscuz-7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +cuscuz-7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +cuscuz-7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cuscuz-7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +cuscuz-7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +cuscuz-7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +cuscuz-7b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..5f3eed3 --- /dev/null +++ b/README.md @@ -0,0 +1,70 @@ +--- +base_model: rhaymison/cuscuz-7b +datasets: +- rhaymison/questions_answers_geo_nord +language: +- pt +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- portuguese +- version:0.1 +--- +## About + + + + + + +static quants of https://huggingface.co/rhaymison/cuscuz-7b + + +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/cuscuz-7b-GGUF/resolve/main/cuscuz-7b.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/cuscuz-7b-GGUF/resolve/main/cuscuz-7b.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/cuscuz-7b-GGUF/resolve/main/cuscuz-7b.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/cuscuz-7b-GGUF/resolve/main/cuscuz-7b.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/cuscuz-7b-GGUF/resolve/main/cuscuz-7b.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/cuscuz-7b-GGUF/resolve/main/cuscuz-7b.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/cuscuz-7b-GGUF/resolve/main/cuscuz-7b.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/cuscuz-7b-GGUF/resolve/main/cuscuz-7b.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/cuscuz-7b-GGUF/resolve/main/cuscuz-7b.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/cuscuz-7b-GGUF/resolve/main/cuscuz-7b.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/cuscuz-7b-GGUF/resolve/main/cuscuz-7b.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/cuscuz-7b-GGUF/resolve/main/cuscuz-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. 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/cuscuz-7b.IQ4_XS.gguf b/cuscuz-7b.IQ4_XS.gguf new file mode 100644 index 0000000..faa1344 --- /dev/null +++ b/cuscuz-7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:741a3d45fd8058db8ec4dc92506464d60d20e8f4750b29675d15ac6072b02fd9 +size 3944390368 diff --git a/cuscuz-7b.Q2_K.gguf b/cuscuz-7b.Q2_K.gguf new file mode 100644 index 0000000..406caf2 --- /dev/null +++ b/cuscuz-7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52ca02fd194336f5c6937bd3eaf8c6c0cc050a4ee739fc809af7772bc8dec275 +size 2719244000 diff --git a/cuscuz-7b.Q3_K_L.gguf b/cuscuz-7b.Q3_K_L.gguf new file mode 100644 index 0000000..8e7277e --- /dev/null +++ b/cuscuz-7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eee669946fc3d9c8200164f6b0de5e3a5c88763459c1a30cbc6795e82b365a85 +size 3822026464 diff --git a/cuscuz-7b.Q3_K_M.gguf b/cuscuz-7b.Q3_K_M.gguf new file mode 100644 index 0000000..53f9e4b --- /dev/null +++ b/cuscuz-7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93f3f43b568c8bf57aa49adae83480ac8d53195f4ed0aea9f0229560f93fae54 +size 3518988000 diff --git a/cuscuz-7b.Q3_K_S.gguf b/cuscuz-7b.Q3_K_S.gguf new file mode 100644 index 0000000..7078695 --- /dev/null +++ b/cuscuz-7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6a05a2e102e26220fc779d39ea8243e55e50de573374f8077159fd984f7bed1 +size 3164569312 diff --git a/cuscuz-7b.Q4_K_M.gguf b/cuscuz-7b.Q4_K_M.gguf new file mode 100644 index 0000000..fa0abb7 --- /dev/null +++ b/cuscuz-7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11d225276aa006b594ec6d1f05eef1dbc7539b976563d906ea25ad3705abbecd +size 4368441056 diff --git a/cuscuz-7b.Q4_K_S.gguf b/cuscuz-7b.Q4_K_S.gguf new file mode 100644 index 0000000..0af963a --- /dev/null +++ b/cuscuz-7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a66d20fdf2431bdf15a26d5e8e378b2c25553d58fb6aa27f1ba662063ae45c51 +size 4140375776 diff --git a/cuscuz-7b.Q5_K_M.gguf b/cuscuz-7b.Q5_K_M.gguf new file mode 100644 index 0000000..1fb3dac --- /dev/null +++ b/cuscuz-7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cbda656c8661990e85394d48af47fc1bc4e61090d035d75ffa903d22e802b65 +size 5131411168 diff --git a/cuscuz-7b.Q5_K_S.gguf b/cuscuz-7b.Q5_K_S.gguf new file mode 100644 index 0000000..156d22a --- /dev/null +++ b/cuscuz-7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b72e395d2e49d7d78afbf39a64b812ea6b6cf1f1e5fdd262a531fa78b9f89abf +size 4997717728 diff --git a/cuscuz-7b.Q6_K.gguf b/cuscuz-7b.Q6_K.gguf new file mode 100644 index 0000000..1055ba7 --- /dev/null +++ b/cuscuz-7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7656a9f8175b2a9ea54801887c1491f913510fc38938b3dec92e4002198dcdb +size 5942066912 diff --git a/cuscuz-7b.Q8_0.gguf b/cuscuz-7b.Q8_0.gguf new file mode 100644 index 0000000..bbdd2df --- /dev/null +++ b/cuscuz-7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fb718ac391e627e1b90a8051808d29b6483399d94a33918f72e63f383984a19 +size 7695859424 diff --git a/cuscuz-7b.f16.gguf b/cuscuz-7b.f16.gguf new file mode 100644 index 0000000..0dc6c22 --- /dev/null +++ b/cuscuz-7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b85bd18e892d5b76118ae288229e81991ec0301aa1c91d70862d3b266f599555 +size 14484733664