commit b32514fbb9c434aca791846b669a3395d0f4e190 Author: ModelHub XC Date: Thu Apr 30 12:13:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/sirona-14b-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..48d926d --- /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 +imatrix.dat filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +sirona-14b.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..3b62ec4 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: vapa/sirona-14b +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- sft +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/vapa/sirona-14b + + +static quants are available at https://huggingface.co/mradermacher/sirona-14b-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/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 5.5 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-IQ4_NL.gguf) | i1-IQ4_NL | 8.6 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-Q4_1.gguf) | i1-Q4_1 | 9.5 | | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | | +| [GGUF](https://huggingface.co/mradermacher/sirona-14b-i1-GGUF/resolve/main/sirona-14b.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | 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/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..ad5ab56 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93ea122bca84414c1add02f915d7b2f7eb6fefe43d68ea02106e5331c6f0e625 +size 8563597 diff --git a/sirona-14b.i1-IQ1_M.gguf b/sirona-14b.i1-IQ1_M.gguf new file mode 100644 index 0000000..5d7fcdf --- /dev/null +++ b/sirona-14b.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34308c8ab563103003486c122ad4cd289ab0da4aecc0fe91215d716d2dabdbd1 +size 3872309792 diff --git a/sirona-14b.i1-IQ1_S.gguf b/sirona-14b.i1-IQ1_S.gguf new file mode 100644 index 0000000..86fa30c --- /dev/null +++ b/sirona-14b.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a386a50b8f657a4a42a513e9051005342ca18b6072c2b16ab3ad40cd66a17761 +size 3607994912 diff --git a/sirona-14b.i1-IQ2_M.gguf b/sirona-14b.i1-IQ2_M.gguf new file mode 100644 index 0000000..99892d2 --- /dev/null +++ b/sirona-14b.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cde0273cf91a77fcc9c28763e7ab9975905f0ac750fdbcc4338f9b8bfda8dfe +size 5356147232 diff --git a/sirona-14b.i1-IQ2_S.gguf b/sirona-14b.i1-IQ2_S.gguf new file mode 100644 index 0000000..8a6b548 --- /dev/null +++ b/sirona-14b.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5261b2b66f3826c8e4dddbe2c1a049b8542496721b33f35c05bc0a2d961069e +size 5003727392 diff --git a/sirona-14b.i1-IQ2_XS.gguf b/sirona-14b.i1-IQ2_XS.gguf new file mode 100644 index 0000000..4bb9743 --- /dev/null +++ b/sirona-14b.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07fd8d45d485114a3dada71f4188812e52d5cb1057e4474c503463b681c31f3e +size 4704576032 diff --git a/sirona-14b.i1-IQ2_XXS.gguf b/sirona-14b.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..1844c66 --- /dev/null +++ b/sirona-14b.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8920f48fc2a476c1536d20f991d883488eac094f15fc3b368e50657b6ef42c46 +size 4312834592 diff --git a/sirona-14b.i1-IQ3_M.gguf b/sirona-14b.i1-IQ3_M.gguf new file mode 100644 index 0000000..2ffae86 --- /dev/null +++ b/sirona-14b.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e741872343714b78a446c38a932f582ab6a337d790de149616fa38a5a8ced47 +size 6916538912 diff --git a/sirona-14b.i1-IQ3_S.gguf b/sirona-14b.i1-IQ3_S.gguf new file mode 100644 index 0000000..d4de7e5 --- /dev/null +++ b/sirona-14b.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa90b96cb7c703ccd8541a1161cdf94fa93237807a9fc157b9c061c5ca1e645a +size 6693020192 diff --git a/sirona-14b.i1-IQ3_XS.gguf b/sirona-14b.i1-IQ3_XS.gguf new file mode 100644 index 0000000..50e0396 --- /dev/null +++ b/sirona-14b.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65f65e59ed359dbc78a438cd8effd7b2d6886f75b52058c4c60bef81db1b62c5 +size 6383362592 diff --git a/sirona-14b.i1-IQ3_XXS.gguf b/sirona-14b.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..0e379ed --- /dev/null +++ b/sirona-14b.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1956e57a44ef3be2743c2921bf7542365b72be844c20a836beeba40b1b8fbfe6 +size 5946708512 diff --git a/sirona-14b.i1-IQ4_NL.gguf b/sirona-14b.i1-IQ4_NL.gguf new file mode 100644 index 0000000..536b370 --- /dev/null +++ b/sirona-14b.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11ce60a36de7ed3c75fada38324d223b25fd6d3882af69f21ac0746094d849eb +size 8549184032 diff --git a/sirona-14b.i1-IQ4_XS.gguf b/sirona-14b.i1-IQ4_XS.gguf new file mode 100644 index 0000000..b35a53a --- /dev/null +++ b/sirona-14b.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d305b9ccdfc91e32e4a98c2daa12ba5c89dd581975cf68d6d0225951a21ec2f8 +size 8119841312 diff --git a/sirona-14b.i1-Q2_K.gguf b/sirona-14b.i1-Q2_K.gguf new file mode 100644 index 0000000..b2c4a5d --- /dev/null +++ b/sirona-14b.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c8bfb443cf094252b1549a4e5a9249aa42048ce20caf728d1f2c7712d6c0fd7 +size 5770498592 diff --git a/sirona-14b.i1-Q2_K_S.gguf b/sirona-14b.i1-Q2_K_S.gguf new file mode 100644 index 0000000..3ffe23c --- /dev/null +++ b/sirona-14b.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c59f91fce0c805f5685ac07f503800d5cd109a9cb53ee3abd65cf0ad2bd1be68 +size 5397189152 diff --git a/sirona-14b.i1-Q3_K_L.gguf b/sirona-14b.i1-Q3_K_L.gguf new file mode 100644 index 0000000..d12435e --- /dev/null +++ b/sirona-14b.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1a60c0837ef6bd8c288365e47c92c632f180b04ce68d84dd47370f427a5760d +size 7924769312 diff --git a/sirona-14b.i1-Q3_K_M.gguf b/sirona-14b.i1-Q3_K_M.gguf new file mode 100644 index 0000000..1b23d81 --- /dev/null +++ b/sirona-14b.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32b727765a5eabf5b5405a44fc0f76801f7fc50fb27db4ab13123b55386aebbb +size 7339205152 diff --git a/sirona-14b.i1-Q3_K_S.gguf b/sirona-14b.i1-Q3_K_S.gguf new file mode 100644 index 0000000..7264e84 --- /dev/null +++ b/sirona-14b.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f62ce84e238d00d2c298459c5cca4bc6a56f1632e2429f65e19895601958ede +size 6659596832 diff --git a/sirona-14b.i1-Q4_0.gguf b/sirona-14b.i1-Q4_0.gguf new file mode 100644 index 0000000..a916943 --- /dev/null +++ b/sirona-14b.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2df65de83b6945404028d891715ae86415f49bd087b0b8f859242a9e4e99b0f +size 8544268832 diff --git a/sirona-14b.i1-Q4_1.gguf b/sirona-14b.i1-Q4_1.gguf new file mode 100644 index 0000000..903ad23 --- /dev/null +++ b/sirona-14b.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4eb7a8d7f9e9cd76288bde0f183cfff153f369dc62eb333a6f3062e6d531376 +size 9392140832 diff --git a/sirona-14b.i1-Q4_K_M.gguf b/sirona-14b.i1-Q4_K_M.gguf new file mode 100644 index 0000000..35e6ae1 --- /dev/null +++ b/sirona-14b.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5299dcedd6e003c26618cf68223a6864c4ed605f838694babf0d50542b0905b0 +size 8988111392 diff --git a/sirona-14b.i1-Q4_K_S.gguf b/sirona-14b.i1-Q4_K_S.gguf new file mode 100644 index 0000000..aa27bf0 --- /dev/null +++ b/sirona-14b.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:427034c8eed475e3d0adc3c2050beda8f5596fffabc521f57cb4b81605f5592b +size 8573432352 diff --git a/sirona-14b.i1-Q5_K_M.gguf b/sirona-14b.i1-Q5_K_M.gguf new file mode 100644 index 0000000..0a2a467 --- /dev/null +++ b/sirona-14b.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d36c0b28d01755615bdb0e60eca8b97f15efbafe1755157e5dfc202eae2f53ed +size 10508874272 diff --git a/sirona-14b.i1-Q5_K_S.gguf b/sirona-14b.i1-Q5_K_S.gguf new file mode 100644 index 0000000..03e92b9 --- /dev/null +++ b/sirona-14b.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0324623f766609123a46964bc2a22c0f076690c487331065c62d43958d45287b +size 10266554912 diff --git a/sirona-14b.i1-Q6_K.gguf b/sirona-14b.i1-Q6_K.gguf new file mode 100644 index 0000000..296c119 --- /dev/null +++ b/sirona-14b.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02bf4d1fef115e2a13038308465a65d68ba03ab2b5ec830cdab3e68442bec02a +size 12124684832