commit a694f49864ab3d40f37a55ef9bb78d0ef10d0645 Author: ModelHub XC Date: Thu May 7 15:57:29 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Quokka_2.7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..61fdcbb --- /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 +Quokka_2.7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_2.7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_2.7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_2.7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_2.7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_2.7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_2.7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_2.7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_2.7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_2.7b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_2.7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_2.7b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Quokka_2.7b.IQ4_XS.gguf b/Quokka_2.7b.IQ4_XS.gguf new file mode 100644 index 0000000..c8f5dc3 --- /dev/null +++ b/Quokka_2.7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbbd24136faa33006c768379733c5d20b7c4541df17533cbe4a78fa8173097ce +size 1485905888 diff --git a/Quokka_2.7b.Q2_K.gguf b/Quokka_2.7b.Q2_K.gguf new file mode 100644 index 0000000..dbdcea8 --- /dev/null +++ b/Quokka_2.7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e0e193c7def6393b4bba1d6c19426fcd4986cdd77b369eb004662613dcd636e +size 1064837088 diff --git a/Quokka_2.7b.Q3_K_L.gguf b/Quokka_2.7b.Q3_K_L.gguf new file mode 100644 index 0000000..5206ec4 --- /dev/null +++ b/Quokka_2.7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1be6c1cbb77d4dba177b227de84b876cb6e2c20ce2a5c2fd89cf791673ab6c10 +size 1567825888 diff --git a/Quokka_2.7b.Q3_K_M.gguf b/Quokka_2.7b.Q3_K_M.gguf new file mode 100644 index 0000000..6ba6b81 --- /dev/null +++ b/Quokka_2.7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b327eb87b2ba73b8befd97f2b76e32ca3e493ce88ecddad4c92bd457aa55e948 +size 1443307488 diff --git a/Quokka_2.7b.Q3_K_S.gguf b/Quokka_2.7b.Q3_K_S.gguf new file mode 100644 index 0000000..5ca06c6 --- /dev/null +++ b/Quokka_2.7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89571cb50b2f2d251a995c928ba229d19da1c0ad5ba93f17467db1fb639d6083 +size 1213931488 diff --git a/Quokka_2.7b.Q4_K_M.gguf b/Quokka_2.7b.Q4_K_M.gguf new file mode 100644 index 0000000..6bf971d --- /dev/null +++ b/Quokka_2.7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf8dadbc14a7264e6189f62dc60aef041b361de99f6c93162eba66a87fbb38da +size 1734942688 diff --git a/Quokka_2.7b.Q4_K_S.gguf b/Quokka_2.7b.Q4_K_S.gguf new file mode 100644 index 0000000..f2b9a9e --- /dev/null +++ b/Quokka_2.7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6c486e9e470693b2d56e445a49e3cc7d264911f20591388ab1e4418ab363471 +size 1561272288 diff --git a/Quokka_2.7b.Q5_K_M.gguf b/Quokka_2.7b.Q5_K_M.gguf new file mode 100644 index 0000000..4f05420 --- /dev/null +++ b/Quokka_2.7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8763dc5b58d940cd04de8e2100d6e96ffeab073b41ced6e0cafaefb814efc033 +size 2002001888 diff --git a/Quokka_2.7b.Q5_K_S.gguf b/Quokka_2.7b.Q5_K_S.gguf new file mode 100644 index 0000000..6140483 --- /dev/null +++ b/Quokka_2.7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef89e0a0625819e6070c3c8b51ae64524891d3b3008668600d2b95cf64ba6111 +size 1862737888 diff --git a/Quokka_2.7b.Q6_K.gguf b/Quokka_2.7b.Q6_K.gguf new file mode 100644 index 0000000..4581987 --- /dev/null +++ b/Quokka_2.7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37fcb79e5ca1072f988a7e3082ce0859b2dabc72bd1f8e9c9e479bccc035deab +size 2196971488 diff --git a/Quokka_2.7b.Q8_0.gguf b/Quokka_2.7b.Q8_0.gguf new file mode 100644 index 0000000..05de052 --- /dev/null +++ b/Quokka_2.7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5611443d41dc72736273ef1d5152f1377ca2e99190ee668229c834c78e45c64d +size 2837617472 diff --git a/Quokka_2.7b.f16.gguf b/Quokka_2.7b.f16.gguf new file mode 100644 index 0000000..d8c18b5 --- /dev/null +++ b/Quokka_2.7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d48722560de9ffd7216efba04314ce12be73420846975a8b0cfbf5dae9387b8b +size 5317537472 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4f6b8a2 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Corianas/Quokka_2.7b +datasets: +- the_pile +- guanaco/guanaco +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Corianas/Quokka_2.7b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Quokka_2.7b-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/Quokka_2.7b-GGUF/resolve/main/Quokka_2.7b.Q2_K.gguf) | Q2_K | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Quokka_2.7b-GGUF/resolve/main/Quokka_2.7b.Q3_K_S.gguf) | Q3_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Quokka_2.7b-GGUF/resolve/main/Quokka_2.7b.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Quokka_2.7b-GGUF/resolve/main/Quokka_2.7b.IQ4_XS.gguf) | IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Quokka_2.7b-GGUF/resolve/main/Quokka_2.7b.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Quokka_2.7b-GGUF/resolve/main/Quokka_2.7b.Q3_K_L.gguf) | Q3_K_L | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Quokka_2.7b-GGUF/resolve/main/Quokka_2.7b.Q4_K_M.gguf) | Q4_K_M | 1.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Quokka_2.7b-GGUF/resolve/main/Quokka_2.7b.Q5_K_S.gguf) | Q5_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Quokka_2.7b-GGUF/resolve/main/Quokka_2.7b.Q5_K_M.gguf) | Q5_K_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Quokka_2.7b-GGUF/resolve/main/Quokka_2.7b.Q6_K.gguf) | Q6_K | 2.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Quokka_2.7b-GGUF/resolve/main/Quokka_2.7b.Q8_0.gguf) | Q8_0 | 2.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Quokka_2.7b-GGUF/resolve/main/Quokka_2.7b.f16.gguf) | f16 | 5.4 | 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. + +