commit f6beeb79ffb69af7d024accd6bdc46cb0777b8d5 Author: ModelHub XC Date: Sat May 9 14:54:39 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Quokka_1.3b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..465bf1d --- /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_1.3b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_1.3b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_1.3b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_1.3b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_1.3b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_1.3b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_1.3b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_1.3b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_1.3b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_1.3b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_1.3b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Quokka_1.3b.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Quokka_1.3b.IQ4_XS.gguf b/Quokka_1.3b.IQ4_XS.gguf new file mode 100644 index 0000000..3af25c3 --- /dev/null +++ b/Quokka_1.3b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc38a3e49e6245d26bcabbd22d7c21a88f7ab3989bca4b7b75345838ce7bfcc1 +size 755163392 diff --git a/Quokka_1.3b.Q2_K.gguf b/Quokka_1.3b.Q2_K.gguf new file mode 100644 index 0000000..d6f0c73 --- /dev/null +++ b/Quokka_1.3b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3cfa9f1de8649881e7c7a574dbfca6481cbf4be8ccd73725cd47ba6189ae1e6 +size 553050368 diff --git a/Quokka_1.3b.Q3_K_L.gguf b/Quokka_1.3b.Q3_K_L.gguf new file mode 100644 index 0000000..99139db --- /dev/null +++ b/Quokka_1.3b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3c1a3993af930823d5b44ff2f1d9cf11ce1eec5140445eedafc170ae86fdf51 +size 794484992 diff --git a/Quokka_1.3b.Q3_K_M.gguf b/Quokka_1.3b.Q3_K_M.gguf new file mode 100644 index 0000000..aaff3a5 --- /dev/null +++ b/Quokka_1.3b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d40ecb878dcb3cdbe74365e7f0f589bd2d82b8489693e9f98727d32ee5fa50f +size 733667584 diff --git a/Quokka_1.3b.Q3_K_S.gguf b/Quokka_1.3b.Q3_K_S.gguf new file mode 100644 index 0000000..bf5f48b --- /dev/null +++ b/Quokka_1.3b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b03265e74b6a7733b5611f258434bb07fa2975a54768e0b94e339b23161ffed4 +size 624615680 diff --git a/Quokka_1.3b.Q4_K_M.gguf b/Quokka_1.3b.Q4_K_M.gguf new file mode 100644 index 0000000..e85d290 --- /dev/null +++ b/Quokka_1.3b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eab2649d0a47f1a6ff7665b01f15a0f74a6788f717918fa051a0f93befa4fb46 +size 874701056 diff --git a/Quokka_1.3b.Q4_K_S.gguf b/Quokka_1.3b.Q4_K_S.gguf new file mode 100644 index 0000000..2b688ff --- /dev/null +++ b/Quokka_1.3b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3b3c2ef6ef1fee6ce6c819b28c2321d4fdd5beb80106133e1b80b438dc6d629 +size 791339264 diff --git a/Quokka_1.3b.Q5_K_M.gguf b/Quokka_1.3b.Q5_K_M.gguf new file mode 100644 index 0000000..0f458a5 --- /dev/null +++ b/Quokka_1.3b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51af834bda57b255646c547b6c8fc7fa7f94363b8653d36226c464489f424b98 +size 1002889472 diff --git a/Quokka_1.3b.Q5_K_S.gguf b/Quokka_1.3b.Q5_K_S.gguf new file mode 100644 index 0000000..010691f --- /dev/null +++ b/Quokka_1.3b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:189114be3bceae81f7d62e7a1260e90068821efe4afd2c5af6c3a5b7937647ef +size 936042752 diff --git a/Quokka_1.3b.Q6_K.gguf b/Quokka_1.3b.Q6_K.gguf new file mode 100644 index 0000000..b301f8d --- /dev/null +++ b/Quokka_1.3b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b19f68ddf239313e609159a0e95c9c54bc1e9cd04c474b2b8164a564523518ba +size 1096474880 diff --git a/Quokka_1.3b.Q8_0.gguf b/Quokka_1.3b.Q8_0.gguf new file mode 100644 index 0000000..7a203bc --- /dev/null +++ b/Quokka_1.3b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92a92a0bee29a3f9aee2fe464337b4f540999fb52d358e4c49a47c36e4e47cfa +size 1413956544 diff --git a/Quokka_1.3b.f16.gguf b/Quokka_1.3b.f16.gguf new file mode 100644 index 0000000..777392f --- /dev/null +++ b/Quokka_1.3b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0375dbe57015f5ac8494aaa7f0958c0cdd96421468a48eb1c13e2d5a36fb1da2 +size 2642917824 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a8b2d7d --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: Corianas/Quokka_1.3b +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_1.3b + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Quokka_1.3b-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_1.3b-GGUF/resolve/main/Quokka_1.3b.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Quokka_1.3b-GGUF/resolve/main/Quokka_1.3b.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Quokka_1.3b-GGUF/resolve/main/Quokka_1.3b.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Quokka_1.3b-GGUF/resolve/main/Quokka_1.3b.IQ4_XS.gguf) | IQ4_XS | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Quokka_1.3b-GGUF/resolve/main/Quokka_1.3b.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Quokka_1.3b-GGUF/resolve/main/Quokka_1.3b.Q3_K_L.gguf) | Q3_K_L | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Quokka_1.3b-GGUF/resolve/main/Quokka_1.3b.Q4_K_M.gguf) | Q4_K_M | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Quokka_1.3b-GGUF/resolve/main/Quokka_1.3b.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Quokka_1.3b-GGUF/resolve/main/Quokka_1.3b.Q5_K_M.gguf) | Q5_K_M | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/Quokka_1.3b-GGUF/resolve/main/Quokka_1.3b.Q6_K.gguf) | Q6_K | 1.2 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Quokka_1.3b-GGUF/resolve/main/Quokka_1.3b.Q8_0.gguf) | Q8_0 | 1.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Quokka_1.3b-GGUF/resolve/main/Quokka_1.3b.f16.gguf) | f16 | 2.7 | 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. + +