commit 1d2614971c3d688f71b7b5a5fe2fd3b4666cc366 Author: ModelHub XC Date: Tue Jun 16 09:02:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/kona2-12B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a81118b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.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 +kona2-12B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +kona2-12B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..9080af0 --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +--- +base_model: tbilisi-ai-lab/kona2-12B +datasets: +- tbilisi-ai-lab/kona-dpo-mix-387k +language: +- ka +- en +- multilingual +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llm +- georgian +- dpo +- rlhf +- aligned +- chat +- conversational +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/tbilisi-ai-lab/kona2-12B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#kona2-12B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/kona2-12B-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/kona2-12B-i1-GGUF/resolve/main/kona2-12B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-IQ1_S.gguf) | i1-IQ1_S | 3.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-IQ1_M.gguf) | i1-IQ1_M | 3.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.1 | | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-IQ2_S.gguf) | i1-IQ2_S | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-IQ2_M.gguf) | i1-IQ2_M | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.7 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-Q2_K.gguf) | i1-Q2_K | 5.0 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-IQ3_S.gguf) | i1-IQ3_S | 5.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-IQ3_M.gguf) | i1-IQ3_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.3 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.8 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-Q4_0.gguf) | i1-Q4_0 | 7.3 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.3 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.4 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-Q4_1.gguf) | i1-Q4_1 | 8.0 | | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 9.0 | | +| [GGUF](https://huggingface.co/mradermacher/kona2-12B-i1-GGUF/resolve/main/kona2-12B.i1-Q6_K.gguf) | i1-Q6_K | 10.3 | 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/kona2-12B.i1-IQ1_M.gguf b/kona2-12B.i1-IQ1_M.gguf new file mode 100644 index 0000000..dc66f3c --- /dev/null +++ b/kona2-12B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d71ca85976e4122f0a4906f9d1ca3c23732d8aee477413a6925504466c0acbcb +size 3326293856 diff --git a/kona2-12B.i1-IQ1_S.gguf b/kona2-12B.i1-IQ1_S.gguf new file mode 100644 index 0000000..a13c308 --- /dev/null +++ b/kona2-12B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ba6eaa881e7483664426fc1cbde94d64571fd2310a2b0005f3613f8b1be97db +size 3103881056 diff --git a/kona2-12B.i1-IQ2_M.gguf b/kona2-12B.i1-IQ2_M.gguf new file mode 100644 index 0000000..e37b366 --- /dev/null +++ b/kona2-12B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0635ba634897952213a9b543fe82dd0a2179b10e8a1aee3060390ac2e7317967 +size 4550097568 diff --git a/kona2-12B.i1-IQ2_S.gguf b/kona2-12B.i1-IQ2_S.gguf new file mode 100644 index 0000000..2dfd86e --- /dev/null +++ b/kona2-12B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef25bbd46e00b995bc2e977535d6a02efe5fc2d492d2c36f107bd13228c8e76c +size 4253547168 diff --git a/kona2-12B.i1-IQ2_XS.gguf b/kona2-12B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..fe9eae5 --- /dev/null +++ b/kona2-12B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18466e205e398c6edd42aa1d25e612408335f06603fa1f137027a2b28d853c6b +size 4019746656 diff --git a/kona2-12B.i1-IQ2_XXS.gguf b/kona2-12B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..639ce3e --- /dev/null +++ b/kona2-12B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4869eb1819d4480bfb71daa63856abd944fa614e6ce909c6a91b8232ae356bb7 +size 3696981856 diff --git a/kona2-12B.i1-IQ3_M.gguf b/kona2-12B.i1-IQ3_M.gguf new file mode 100644 index 0000000..1bccf80 --- /dev/null +++ b/kona2-12B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21143758d261363d1622963454b251feb6b27a9d9e0d59965d11687fda295be1 +size 5850912672 diff --git a/kona2-12B.i1-IQ3_S.gguf b/kona2-12B.i1-IQ3_S.gguf new file mode 100644 index 0000000..1eade46 --- /dev/null +++ b/kona2-12B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b50a2344ed71f744428678732f8c8e1d9810fddf2ac9b68303150c8d56bb5269 +size 5690759072 diff --git a/kona2-12B.i1-IQ3_XS.gguf b/kona2-12B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..4eb1a5c --- /dev/null +++ b/kona2-12B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69d2cf207883346fb19f83a71cfb0037a6abae3a95c1d8ac013a4332fb038933 +size 5435168672 diff --git a/kona2-12B.i1-IQ3_XXS.gguf b/kona2-12B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..5205aa5 --- /dev/null +++ b/kona2-12B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19dff5638cda313e052b695c4fe1096ee2d9b7b4a6e07d2a523565aed6d4a496 +size 5060459168 diff --git a/kona2-12B.i1-IQ4_NL.gguf b/kona2-12B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..bdcf214 --- /dev/null +++ b/kona2-12B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81cb0e44f637e4adb44ab25cc845c6e1091799bfb2843b6f46be6476fc2d5c6c +size 7240201344 diff --git a/kona2-12B.i1-IQ4_XS.gguf b/kona2-12B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..e4e244b --- /dev/null +++ b/kona2-12B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1ad95275e40cd3f5d393975fe4e5ca8eca4fcd3107225365859edc5dedd5923 +size 6881794784 diff --git a/kona2-12B.i1-Q2_K.gguf b/kona2-12B.i1-Q2_K.gguf new file mode 100644 index 0000000..5db6df1 --- /dev/null +++ b/kona2-12B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa73ad1e99b55a902a838daabacdc7d008f3ce272fe0828b0059e33c98eb745d +size 4909323360 diff --git a/kona2-12B.i1-Q2_K_S.gguf b/kona2-12B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..745914e --- /dev/null +++ b/kona2-12B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17614e73d75d59f9a5766859958604589336dabd4b2e25da5ee771f146e95d89 +size 4611953760 diff --git a/kona2-12B.i1-Q3_K_L.gguf b/kona2-12B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..cc7bab2 --- /dev/null +++ b/kona2-12B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0a8f8ad17d53e9bd5f7f0098e72b78c379c524d3c74a4d8a240bfda80356916 +size 6690183072 diff --git a/kona2-12B.i1-Q3_K_M.gguf b/kona2-12B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..99c0eb1 --- /dev/null +++ b/kona2-12B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57591475d780addc0c10a25c52baeb117d22e293f404923d0552fd1da6cba8ed +size 6211770272 diff --git a/kona2-12B.i1-Q3_K_S.gguf b/kona2-12B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..8da28de --- /dev/null +++ b/kona2-12B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb2014ff65c1a0e97697e236d8e11f2f792788ecc58d23d70d0826c3fea16681 +size 5662906272 diff --git a/kona2-12B.i1-Q4_0.gguf b/kona2-12B.i1-Q4_0.gguf new file mode 100644 index 0000000..f6336ea --- /dev/null +++ b/kona2-12B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1763ae9300a95673c47ab82ad6e917ecd666047809915c95e4b8118f939630a1 +size 7236924544 diff --git a/kona2-12B.i1-Q4_1.gguf b/kona2-12B.i1-Q4_1.gguf new file mode 100644 index 0000000..fb9cfbf --- /dev/null +++ b/kona2-12B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a81c6ce86215aa267b26df487f057eb45e9df8e3ac979d99617511fdc3919df +size 7943907264 diff --git a/kona2-12B.i1-Q4_K_M.gguf b/kona2-12B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..3b364ab --- /dev/null +++ b/kona2-12B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d74cd77f4445572b9029f38f70ce9819b33342a2d5e18bf5de8bc4caf14b4fc5 +size 7619490944 diff --git a/kona2-12B.i1-Q4_K_S.gguf b/kona2-12B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..0c07590 --- /dev/null +++ b/kona2-12B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:644d2589dcd60921dda91fbd335342c37341f2ea8a20088a5c629b157787752c +size 7262483584 diff --git a/kona2-12B.i1-Q5_K_M.gguf b/kona2-12B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..aa41f05 --- /dev/null +++ b/kona2-12B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a748c87299dec12e5c20f07d108ad7c86bb2286fd0613345750d508c3eb0f273 +size 8882723584 diff --git a/kona2-12B.i1-Q5_K_S.gguf b/kona2-12B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..a2e3211 --- /dev/null +++ b/kona2-12B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:845f2f68763b558ef9a2a11390596af7ac8c6a1564e26fb84dd05cde888510b7 +size 8673827584 diff --git a/kona2-12B.i1-Q6_K.gguf b/kona2-12B.i1-Q6_K.gguf new file mode 100644 index 0000000..f319b31 --- /dev/null +++ b/kona2-12B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b8a21ea6c63f520d04b43b35dbcbb8542a809d295d11082620dc1dc17695dae +size 10224908288 diff --git a/kona2-12B.imatrix.gguf b/kona2-12B.imatrix.gguf new file mode 100644 index 0000000..2f2684b --- /dev/null +++ b/kona2-12B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb3918c0f670f46e0bde8a8d09ee7229f836f034f35baf85ca3a9b130dfc28b0 +size 7088192