commit f880ffeed1bb3d62594ed20880f61fe8403e25a6 Author: ModelHub XC Date: Fri Jun 12 01:16:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Zyte-1B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7c78bf2 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +Zyte-1B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Zyte-1B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a59036c --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +base_model: venkycs/Zyte-1B +datasets: +- HuggingFaceH4/ultrachat_200k +- HuggingFaceH4/ultrafeedback_binarized +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- slm +- llama +- tiny +- tinyllama +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/venkycs/Zyte-1B + + +static quants are available at https://huggingface.co/mradermacher/Zyte-1B-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/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-IQ1_S.gguf) | i1-IQ1_S | 0.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-IQ1_M.gguf) | i1-IQ1_M | 0.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-IQ2_S.gguf) | i1-IQ2_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-IQ2_M.gguf) | i1-IQ2_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-Q2_K.gguf) | i1-Q2_K | 0.5 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-IQ3_S.gguf) | i1-IQ3_S | 0.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-IQ3_M.gguf) | i1-IQ3_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.7 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-Q4_0.gguf) | i1-Q4_0 | 0.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-Q4_1.gguf) | i1-Q4_1 | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Zyte-1B-i1-GGUF/resolve/main/Zyte-1B.i1-Q6_K.gguf) | i1-Q6_K | 1.0 | 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/Zyte-1B.i1-IQ1_M.gguf b/Zyte-1B.i1-IQ1_M.gguf new file mode 100644 index 0000000..ddaf250 --- /dev/null +++ b/Zyte-1B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e657c5a9f780bd8bc697aafdf10eb8f7d115252faeb1d6dca4245dc17551338b +size 289702464 diff --git a/Zyte-1B.i1-IQ1_S.gguf b/Zyte-1B.i1-IQ1_S.gguf new file mode 100644 index 0000000..b10532f --- /dev/null +++ b/Zyte-1B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04bb61b3d18dae5f0beb0658bf8fe5c7e8fb5c9a31e6e956bf2ac70d0f913b44 +size 269967936 diff --git a/Zyte-1B.i1-IQ2_M.gguf b/Zyte-1B.i1-IQ2_M.gguf new file mode 100644 index 0000000..b0c4524 --- /dev/null +++ b/Zyte-1B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e2985b12705ae9b4e325296d010214e900d8d65b477f4d21eba6f7389f6eb2e +size 400077376 diff --git a/Zyte-1B.i1-IQ2_S.gguf b/Zyte-1B.i1-IQ2_S.gguf new file mode 100644 index 0000000..ab82f22 --- /dev/null +++ b/Zyte-1B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2adcb567d6b0380ec1137c45a8c95309dcd9aaa37b96689e1f94af9e5fc1c20a +size 373764672 diff --git a/Zyte-1B.i1-IQ2_XS.gguf b/Zyte-1B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..5232c93 --- /dev/null +++ b/Zyte-1B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da324e45fa36adf4b49a37761d19170480914608ca8f8ee9f1700383740974e1 +size 351789632 diff --git a/Zyte-1B.i1-IQ2_XXS.gguf b/Zyte-1B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..fbca088 --- /dev/null +++ b/Zyte-1B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c57d0ab6463ec2ef3c41792ea389908acd6a2a27fa974f4345852d7560961fd4 +size 322593344 diff --git a/Zyte-1B.i1-IQ3_M.gguf b/Zyte-1B.i1-IQ3_M.gguf new file mode 100644 index 0000000..ca01153 --- /dev/null +++ b/Zyte-1B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cec7bb654aa7592c4a26a3ebf288a52ffe2fdcdb2e59dfa225d751e09612c62c +size 516194880 diff --git a/Zyte-1B.i1-IQ3_S.gguf b/Zyte-1B.i1-IQ3_S.gguf new file mode 100644 index 0000000..047779c --- /dev/null +++ b/Zyte-1B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efad6623c56d934e47a0a35a9b9d3b1f61086c4af7c71f6f950b61b74a59811d +size 500875840 diff --git a/Zyte-1B.i1-IQ3_XS.gguf b/Zyte-1B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..4246714 --- /dev/null +++ b/Zyte-1B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5c4522c9d1c4836344adaf50a2e5d445ad9213331d3c509c94df47889d0f103 +size 477626944 diff --git a/Zyte-1B.i1-IQ3_XXS.gguf b/Zyte-1B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..441eb13 --- /dev/null +++ b/Zyte-1B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c116c94cc5efdad77393f296e4664b6c0be3d6fec7c5588bf4b3d1c364728ead +size 445133376 diff --git a/Zyte-1B.i1-IQ4_NL.gguf b/Zyte-1B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..aebb705 --- /dev/null +++ b/Zyte-1B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5124c2329722390e29e5a9b2f1c1f1c314e13c90ee4d8387d4bdd1d9b7f3fee +size 638169664 diff --git a/Zyte-1B.i1-IQ4_XS.gguf b/Zyte-1B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..f1b9413 --- /dev/null +++ b/Zyte-1B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57c8f5a1912209cc0ea8912afe8a0738ce8ec8c21b70bcea754773aacad0bef2 +size 606204480 diff --git a/Zyte-1B.i1-Q2_K.gguf b/Zyte-1B.i1-Q2_K.gguf new file mode 100644 index 0000000..35b30cf --- /dev/null +++ b/Zyte-1B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4404ef5a6e96958a83a88837fa246d9f27b49f86dd1e8e2f7e0d0c437fbfbc99 +size 432132672 diff --git a/Zyte-1B.i1-Q2_K_S.gguf b/Zyte-1B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..421b68c --- /dev/null +++ b/Zyte-1B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:012a65d792680c579d644c9df4773f0040326a1fc550ed492aa7485254ec0a49 +size 402395712 diff --git a/Zyte-1B.i1-Q3_K_L.gguf b/Zyte-1B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..610c18b --- /dev/null +++ b/Zyte-1B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99195811e8a880733b4351a107d6fae679ce1ea03f32d76808e0fdc51426667a +size 591528512 diff --git a/Zyte-1B.i1-Q3_K_M.gguf b/Zyte-1B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..47b1f89 --- /dev/null +++ b/Zyte-1B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc4db3508c8deca0671254a22bd01e772c933ed088816dbe96fd4a2febdd499c +size 548405824 diff --git a/Zyte-1B.i1-Q3_K_S.gguf b/Zyte-1B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..7b03773 --- /dev/null +++ b/Zyte-1B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:580e5928be1339b57139fae7c29732e6c6a7241920ddfdf30adf54279755d5d7 +size 499343936 diff --git a/Zyte-1B.i1-Q4_0.gguf b/Zyte-1B.i1-Q4_0.gguf new file mode 100644 index 0000000..ff7fc71 --- /dev/null +++ b/Zyte-1B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4583960cfbb27ff2b8acc79ef081495584e7722c4af84ecc016b247e3050cc0 +size 638169664 diff --git a/Zyte-1B.i1-Q4_1.gguf b/Zyte-1B.i1-Q4_1.gguf new file mode 100644 index 0000000..efa7306 --- /dev/null +++ b/Zyte-1B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71ebf8413a10b0cfc2349068ec97b4e328cd87709f2eba6e7b344332bd5dbe5c +size 701379136 diff --git a/Zyte-1B.i1-Q4_K_M.gguf b/Zyte-1B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..a52055a --- /dev/null +++ b/Zyte-1B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96b11e93ec52d7f373c943202f2982ae5a33fbb7e6b844d7d24ddfa8199c926b +size 667816512 diff --git a/Zyte-1B.i1-Q4_K_S.gguf b/Zyte-1B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..9bcb5b4 --- /dev/null +++ b/Zyte-1B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:888fa90562ebfd7cbf74d764efb702664aa69208a843de2d04d387795908a7a2 +size 639873600 diff --git a/Zyte-1B.i1-Q5_K_M.gguf b/Zyte-1B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..d0fef0d --- /dev/null +++ b/Zyte-1B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:344c5edfbf3404a978bead999b554957013780f9cbbf1e5cddb523a67aa30d94 +size 782045760 diff --git a/Zyte-1B.i1-Q5_K_S.gguf b/Zyte-1B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..6be1ee6 --- /dev/null +++ b/Zyte-1B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f61ca33829d5e39f89348c1b0b2e2cb6066d070ef06083b6f7eabe547c409459 +size 766030400 diff --git a/Zyte-1B.i1-Q6_K.gguf b/Zyte-1B.i1-Q6_K.gguf new file mode 100644 index 0000000..23221d8 --- /dev/null +++ b/Zyte-1B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e8a1088a5fc09f259cbe4c86c10f99906ef3011d84e751b22fc69d42ceae0d0 +size 903414336