commit 51f4904fb1c059622d8cc082b0528d2c64a1802d Author: ModelHub XC Date: Fri Oct 9 04:17:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AutoTriton-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..75b2363 --- /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 +AutoTriton.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +AutoTriton.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AutoTriton.i1-IQ1_M.gguf b/AutoTriton.i1-IQ1_M.gguf new file mode 100644 index 0000000..4a44961 --- /dev/null +++ b/AutoTriton.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50cc1b8292264a49be3749c914f87bdc676214fd8d59153dc5ed9266f00aacbd +size 2272220832 diff --git a/AutoTriton.i1-IQ1_S.gguf b/AutoTriton.i1-IQ1_S.gguf new file mode 100644 index 0000000..2b6c585 --- /dev/null +++ b/AutoTriton.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa7d9f0d3957cd1b83296fb317239da91f9f99141658dfb6a69f810d8eecf577 +size 2129876640 diff --git a/AutoTriton.i1-IQ2_M.gguf b/AutoTriton.i1-IQ2_M.gguf new file mode 100644 index 0000000..38ecc1a --- /dev/null +++ b/AutoTriton.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9848551617f75af38f696da2ca71f19e9ef0b8f213896647aba095ed0a70328b +size 3069712032 diff --git a/AutoTriton.i1-IQ2_S.gguf b/AutoTriton.i1-IQ2_S.gguf new file mode 100644 index 0000000..5422564 --- /dev/null +++ b/AutoTriton.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf467191597c48ba24b4668556cdddb968eaaab42948d9fdc8a8518b1723b6ca +size 2879919776 diff --git a/AutoTriton.i1-IQ2_XS.gguf b/AutoTriton.i1-IQ2_XS.gguf new file mode 100644 index 0000000..d88d128 --- /dev/null +++ b/AutoTriton.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53ec30e183bff60e4a95c3fc49797ab3af549902a351ce1874b61968bc0d544c +size 2716030624 diff --git a/AutoTriton.i1-IQ2_XXS.gguf b/AutoTriton.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..63788e8 --- /dev/null +++ b/AutoTriton.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acf58ed649927e2905e700f3ef889b8ded07ec3ce34bd6c1d779cfff1ac67607 +size 2509461152 diff --git a/AutoTriton.i1-IQ3_M.gguf b/AutoTriton.i1-IQ3_M.gguf new file mode 100644 index 0000000..32ff098 --- /dev/null +++ b/AutoTriton.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40a70ddf4f81c16907c35dc7f65f55b2a10c732050dffeaf3fe18ac1483d3562 +size 3920877216 diff --git a/AutoTriton.i1-IQ3_S.gguf b/AutoTriton.i1-IQ3_S.gguf new file mode 100644 index 0000000..9044ba3 --- /dev/null +++ b/AutoTriton.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50464600b09a1d0418dff62bd04cc9772e64f4f32d0c2339ee377f5842841dbf +size 3818378912 diff --git a/AutoTriton.i1-IQ3_XS.gguf b/AutoTriton.i1-IQ3_XS.gguf new file mode 100644 index 0000000..d3789db --- /dev/null +++ b/AutoTriton.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e3a7d0e37c6ef3eb0da75de785607f0daa7e9fe4dd1bf8f5049caadc721f5c9 +size 3654801056 diff --git a/AutoTriton.i1-IQ3_XXS.gguf b/AutoTriton.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..27d1839 --- /dev/null +++ b/AutoTriton.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1fe8779b4cf04365b3f047561623f31682ea3698479aabad6e0fcf89bd2ce13 +size 3396343456 diff --git a/AutoTriton.i1-IQ4_NL.gguf b/AutoTriton.i1-IQ4_NL.gguf new file mode 100644 index 0000000..9199d37 --- /dev/null +++ b/AutoTriton.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26e5d65c31e2e1ecaae60868cbc03c369798230e1df4e4cfce3914379d322fe6 +size 4828665504 diff --git a/AutoTriton.i1-IQ4_XS.gguf b/AutoTriton.i1-IQ4_XS.gguf new file mode 100644 index 0000000..370c554 --- /dev/null +++ b/AutoTriton.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a03b48ff4c14ce80d37b33a500b0d1c7082185af5156dd62d1c72642d03d8557 +size 4594898592 diff --git a/AutoTriton.i1-Q2_K.gguf b/AutoTriton.i1-Q2_K.gguf new file mode 100644 index 0000000..910151f --- /dev/null +++ b/AutoTriton.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b4b840c1c18b37445755b68d9289d7f94cfadcbe34ca6da1c54d2f93b722fd1 +size 3304003232 diff --git a/AutoTriton.i1-Q2_K_S.gguf b/AutoTriton.i1-Q2_K_S.gguf new file mode 100644 index 0000000..964e82e --- /dev/null +++ b/AutoTriton.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1253085220af0c2c53bf84dd84da533471a9e834684bfcad5095508d5cdf821a +size 3113686688 diff --git a/AutoTriton.i1-Q3_K_L.gguf b/AutoTriton.i1-Q3_K_L.gguf new file mode 100644 index 0000000..f468693 --- /dev/null +++ b/AutoTriton.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:367244d7ef559610c62bc9b648232d18aaec00d183b6132824403c52dec5f701 +size 4458010272 diff --git a/AutoTriton.i1-Q3_K_M.gguf b/AutoTriton.i1-Q3_K_M.gguf new file mode 100644 index 0000000..c1e17eb --- /dev/null +++ b/AutoTriton.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:239c4c092fb1e7ab0df36c684d6e2937815db0a5c12d35f3ab4409b17702610e +size 4154971808 diff --git a/AutoTriton.i1-Q3_K_S.gguf b/AutoTriton.i1-Q3_K_S.gguf new file mode 100644 index 0000000..ee89514 --- /dev/null +++ b/AutoTriton.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b7a32592dc1c3c0801fdf680f190fec09583a8366964391b7b32a4d6783917b +size 3800553120 diff --git a/AutoTriton.i1-Q4_0.gguf b/AutoTriton.i1-Q4_0.gguf new file mode 100644 index 0000000..6eec6d5 --- /dev/null +++ b/AutoTriton.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:551f5641af7ec578e2baa08f1b2a985e3ce791fa6e5ea5af5fc401c3d6e6fff8 +size 4826568352 diff --git a/AutoTriton.i1-Q4_1.gguf b/AutoTriton.i1-Q4_1.gguf new file mode 100644 index 0000000..f6c961b --- /dev/null +++ b/AutoTriton.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:587bb85c2155b04591cb9cff6c172126a63b83d4ba31a5187a66fc49c267cdaf +size 5287810720 diff --git a/AutoTriton.i1-Q4_K_M.gguf b/AutoTriton.i1-Q4_K_M.gguf new file mode 100644 index 0000000..621ed64 --- /dev/null +++ b/AutoTriton.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94f50825764374de3dd1e73db84a90c25f1853ce4e234d0107c49e6113c9078f +size 5071410848 diff --git a/AutoTriton.i1-Q4_K_S.gguf b/AutoTriton.i1-Q4_K_S.gguf new file mode 100644 index 0000000..75e74cb --- /dev/null +++ b/AutoTriton.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83c165c7bd0151d49141184d8c469f0123f21bb37ccc4e95831c7a7aa7804e5b +size 4843345568 diff --git a/AutoTriton.i1-Q5_K_M.gguf b/AutoTriton.i1-Q5_K_M.gguf new file mode 100644 index 0000000..0250c57 --- /dev/null +++ b/AutoTriton.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cc143f7cbf9d96544e4db6e009a82f69ec3a1c1a6baee1f6037057e6b563902 +size 5897426592 diff --git a/AutoTriton.i1-Q5_K_S.gguf b/AutoTriton.i1-Q5_K_S.gguf new file mode 100644 index 0000000..c8a29ca --- /dev/null +++ b/AutoTriton.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39c8b4a401f477787fcc52c05e7beedf4f9af9adcf23a98ba39ff997bd3c7ccb +size 5763733152 diff --git a/AutoTriton.i1-Q6_K.gguf b/AutoTriton.i1-Q6_K.gguf new file mode 100644 index 0000000..da5ce44 --- /dev/null +++ b/AutoTriton.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a32d7494ee6456a101691f9aedbf568c2e4b86a21bfbc6995253bc8d9aa59dc +size 6775068320 diff --git a/AutoTriton.imatrix.gguf b/AutoTriton.imatrix.gguf new file mode 100644 index 0000000..fed3c6d --- /dev/null +++ b/AutoTriton.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18f152ae60f89973a05d145e9b5a90eb56953022eb27d63fcf33c9642392f0bd +size 5015200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4ae517b --- /dev/null +++ b/README.md @@ -0,0 +1,90 @@ +--- +base_model: ai9stars/AutoTriton +datasets: +- ScalingIntelligence/KernelBench +- LiShangZ/TritonBench +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- code-generation +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/ai9stars/AutoTriton + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#AutoTriton-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/AutoTriton-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/AutoTriton-i1-GGUF/resolve/main/AutoTriton.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-IQ1_S.gguf) | i1-IQ1_S | 2.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-IQ1_M.gguf) | i1-IQ1_M | 2.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-IQ2_S.gguf) | i1-IQ2_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-Q2_K.gguf) | i1-Q2_K | 3.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-IQ3_S.gguf) | i1-IQ3_S | 3.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-IQ3_M.gguf) | i1-IQ3_M | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.3 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.6 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-Q4_0.gguf) | i1-Q4_0 | 4.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-Q4_1.gguf) | i1-Q4_1 | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.9 | | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/AutoTriton-i1-GGUF/resolve/main/AutoTriton.i1-Q6_K.gguf) | i1-Q6_K | 6.9 | 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. + +