commit f1e3f265ee763517794f8fc898ce84d4ed037318 Author: ModelHub XC Date: Mon Apr 13 21:29:52 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Quyen-SE-v0.1-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e14187b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,56 @@ +*.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 +Quyen-SE-v0.1.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Quyen-SE-v0.1.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Quyen-SE-v0.1.i1-IQ1_M.gguf b/Quyen-SE-v0.1.i1-IQ1_M.gguf new file mode 100644 index 0000000..b152ab9 --- /dev/null +++ b/Quyen-SE-v0.1.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae929a6055b23f07be2715b14be577e77a08b0510ffc7ece2fdf976b741879f3 +size 236573696 diff --git a/Quyen-SE-v0.1.i1-IQ1_S.gguf b/Quyen-SE-v0.1.i1-IQ1_S.gguf new file mode 100644 index 0000000..551fc12 --- /dev/null +++ b/Quyen-SE-v0.1.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:219635afb0420de23cec027864937936a0186f8868c005cb574a1b3c53bcf02a +size 230730752 diff --git a/Quyen-SE-v0.1.i1-IQ2_M.gguf b/Quyen-SE-v0.1.i1-IQ2_M.gguf new file mode 100644 index 0000000..91545ac --- /dev/null +++ b/Quyen-SE-v0.1.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfc2d043e3ec5e2fbe87cd4b9392399f5929376597ad0514c5e20d0f1ef76842 +size 285454336 diff --git a/Quyen-SE-v0.1.i1-IQ2_S.gguf b/Quyen-SE-v0.1.i1-IQ2_S.gguf new file mode 100644 index 0000000..eecc286 --- /dev/null +++ b/Quyen-SE-v0.1.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26e5040be6872dc10ec9aae23e69a83d7e5eb942fbbe127d5071a0f9808f3e98 +size 277663744 diff --git a/Quyen-SE-v0.1.i1-IQ2_XS.gguf b/Quyen-SE-v0.1.i1-IQ2_XS.gguf new file mode 100644 index 0000000..eee9f03 --- /dev/null +++ b/Quyen-SE-v0.1.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0d3a8fbc5b66bbf074124d4b50ab33b9610f938025456fda7e97b9387742ce4 +size 254888960 diff --git a/Quyen-SE-v0.1.i1-IQ2_XXS.gguf b/Quyen-SE-v0.1.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..392cb5a --- /dev/null +++ b/Quyen-SE-v0.1.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27ff3927710e8d104e6a5322346f0d1838a474eef7e0e6f6f7dd67db9442aef8 +size 246311936 diff --git a/Quyen-SE-v0.1.i1-IQ3_M.gguf b/Quyen-SE-v0.1.i1-IQ3_M.gguf new file mode 100644 index 0000000..51bce4d --- /dev/null +++ b/Quyen-SE-v0.1.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:322510e4bd5b83c248da3a80a46bb9fcdfcce17038aabf7a702e6655de64168a +size 341218304 diff --git a/Quyen-SE-v0.1.i1-IQ3_S.gguf b/Quyen-SE-v0.1.i1-IQ3_S.gguf new file mode 100644 index 0000000..2874eee --- /dev/null +++ b/Quyen-SE-v0.1.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf36f049ed81bced266e65c779a549775e8830f42f80be4246022cebda953ce9 +size 333384704 diff --git a/Quyen-SE-v0.1.i1-IQ3_XS.gguf b/Quyen-SE-v0.1.i1-IQ3_XS.gguf new file mode 100644 index 0000000..92f93f9 --- /dev/null +++ b/Quyen-SE-v0.1.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:556e5208ecb861e9358f0a382bc097921a359ecba94460a04fc5eb3bf18ee2ef +size 326159360 diff --git a/Quyen-SE-v0.1.i1-IQ3_XXS.gguf b/Quyen-SE-v0.1.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..6b4f89d --- /dev/null +++ b/Quyen-SE-v0.1.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a134bf9d012b6c19bf063f3d23df18243bbf144443817afb8c1eef06436b1748 +size 296304640 diff --git a/Quyen-SE-v0.1.i1-IQ4_XS.gguf b/Quyen-SE-v0.1.i1-IQ4_XS.gguf new file mode 100644 index 0000000..57c3c97 --- /dev/null +++ b/Quyen-SE-v0.1.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed6396f4809a771c8cc37aebe3384c06698ba33c88ba8ef61384fa8e61164fd8 +size 380495872 diff --git a/Quyen-SE-v0.1.i1-Q2_K.gguf b/Quyen-SE-v0.1.i1-Q2_K.gguf new file mode 100644 index 0000000..93b4135 --- /dev/null +++ b/Quyen-SE-v0.1.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb40df2a42aa4685265a1e4d192cfca384c6da5f27a8f9150b2c4f4c7798731e +size 298414080 diff --git a/Quyen-SE-v0.1.i1-Q3_K_L.gguf b/Quyen-SE-v0.1.i1-Q3_K_L.gguf new file mode 100644 index 0000000..bc7b352 --- /dev/null +++ b/Quyen-SE-v0.1.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8ff2c5f5f6ee0327d2e90bc0f9c6eb6a869f4b30e86e4dc9cd889d98b1361de +size 364203008 diff --git a/Quyen-SE-v0.1.i1-Q3_K_M.gguf b/Quyen-SE-v0.1.i1-Q3_K_M.gguf new file mode 100644 index 0000000..0fc9713 --- /dev/null +++ b/Quyen-SE-v0.1.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8f06c2090e9d2baccfe34fa7f99334fe78f585a970d11815f573cfb334a16c4 +size 349883392 diff --git a/Quyen-SE-v0.1.i1-Q3_K_S.gguf b/Quyen-SE-v0.1.i1-Q3_K_S.gguf new file mode 100644 index 0000000..ec88495 --- /dev/null +++ b/Quyen-SE-v0.1.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e10bab98cb74b0bb4e84f3f0c6d908e2dcb9498633849a62f21a2249621417d +size 333384704 diff --git a/Quyen-SE-v0.1.i1-Q4_0.gguf b/Quyen-SE-v0.1.i1-Q4_0.gguf new file mode 100644 index 0000000..544640d --- /dev/null +++ b/Quyen-SE-v0.1.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e80b1e5b1f53833fa113d0f920cb9fb1f4992bc7a25be8ebef0b145f29cbee24 +size 395532288 diff --git a/Quyen-SE-v0.1.i1-Q4_K_M.gguf b/Quyen-SE-v0.1.i1-Q4_K_M.gguf new file mode 100644 index 0000000..ac6ac3f --- /dev/null +++ b/Quyen-SE-v0.1.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e396238a2051faadd0bddcdb97d16d5b14cff75a91a14f5b43f3b2635c20e5d +size 407156736 diff --git a/Quyen-SE-v0.1.i1-Q4_K_S.gguf b/Quyen-SE-v0.1.i1-Q4_K_S.gguf new file mode 100644 index 0000000..086d4bd --- /dev/null +++ b/Quyen-SE-v0.1.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbc94c957ea7c616f660660782ee421f58407f8d6c09849ddd54add7299362a8 +size 396597248 diff --git a/Quyen-SE-v0.1.i1-Q5_K_M.gguf b/Quyen-SE-v0.1.i1-Q5_K_M.gguf new file mode 100644 index 0000000..d456daf --- /dev/null +++ b/Quyen-SE-v0.1.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bb447710aaca22840d58cb483f6793efb7eb7346384b1051c165f820c119b11 +size 459241472 diff --git a/Quyen-SE-v0.1.i1-Q5_K_S.gguf b/Quyen-SE-v0.1.i1-Q5_K_S.gguf new file mode 100644 index 0000000..af6582a --- /dev/null +++ b/Quyen-SE-v0.1.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b90765b607b775620ff45f60b8f91f6e2e7be85a1d0700add4b899846909ac61 +size 452974592 diff --git a/Quyen-SE-v0.1.i1-Q6_K.gguf b/Quyen-SE-v0.1.i1-Q6_K.gguf new file mode 100644 index 0000000..d2bad0d --- /dev/null +++ b/Quyen-SE-v0.1.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45459228804f288ee163fc7da2181ab2d0eb4c6f7ccf249b03a0c8437398804e +size 514581504 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e59d927 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: vilm/Quyen-SE-v0.1 +datasets: +- teknium/OpenHermes-2.5 +- LDJnr/Capybara +- Intel/orca_dpo_pairs +- argilla/distilabel-capybara-dpo-7k-binarized +language: +- en +library_name: transformers +license: other +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/vilm/Quyen-SE-v0.1 + + +static quants are available at https://huggingface.co/mradermacher/Quyen-SE-v0.1-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/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-IQ1_S.gguf) | i1-IQ1_S | 0.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-IQ1_M.gguf) | i1-IQ1_M | 0.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-IQ2_S.gguf) | i1-IQ2_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-IQ2_M.gguf) | i1-IQ2_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-Q2_K.gguf) | i1-Q2_K | 0.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-IQ3_S.gguf) | i1-IQ3_S | 0.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-IQ3_M.gguf) | i1-IQ3_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.4 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-Q4_0.gguf) | i1-Q4_0 | 0.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Quyen-SE-v0.1-i1-GGUF/resolve/main/Quyen-SE-v0.1.i1-Q6_K.gguf) | i1-Q6_K | 0.6 | 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..266cc46 Binary files /dev/null and b/imatrix.dat differ