commit 3d8832ea00d3e6d4b613c47231c958f7187ae489 Author: ModelHub XC Date: Sun May 10 01:09:01 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/GEITje-7B-ultra-sft-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ffdbc4b --- /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 +GEITje-7B-ultra-sft.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +GEITje-7B-ultra-sft.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GEITje-7B-ultra-sft.i1-IQ1_M.gguf b/GEITje-7B-ultra-sft.i1-IQ1_M.gguf new file mode 100644 index 0000000..2846417 --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2fb1a1f4784d35bf2717f49169df90b0f2920437e8204a9d54fd535f6d1ea22 +size 1754448640 diff --git a/GEITje-7B-ultra-sft.i1-IQ1_S.gguf b/GEITje-7B-ultra-sft.i1-IQ1_S.gguf new file mode 100644 index 0000000..a5ff305 --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ebca2b17656e6042a410559546d502c1d5971fd2261f05fead23faf1e651b25 +size 1612104448 diff --git a/GEITje-7B-ultra-sft.i1-IQ2_M.gguf b/GEITje-7B-ultra-sft.i1-IQ2_M.gguf new file mode 100644 index 0000000..36e2647 --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8df08b0857d5054aa5b9e65dfc49c0a07e035836f80f0cef4715ecdf22d36e2 +size 2500715264 diff --git a/GEITje-7B-ultra-sft.i1-IQ2_S.gguf b/GEITje-7B-ultra-sft.i1-IQ2_S.gguf new file mode 100644 index 0000000..dbea29c --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c2db91b64b1c22a58b66199924036645ac914454b90c2f7904a6891fe9e178b +size 2310923008 diff --git a/GEITje-7B-ultra-sft.i1-IQ2_XS.gguf b/GEITje-7B-ultra-sft.i1-IQ2_XS.gguf new file mode 100644 index 0000000..6fe173f --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d42302e630a6003d9b490ec3f30ac15adb81dc9bf325475372f98d10e37bd17 +size 2198258432 diff --git a/GEITje-7B-ultra-sft.i1-IQ2_XXS.gguf b/GEITje-7B-ultra-sft.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..ac36460 --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:914a7027c91243b296b0b98d282e9cdfda0ca9a600f560a1c02bfad92858e290 +size 1991688960 diff --git a/GEITje-7B-ultra-sft.i1-IQ3_M.gguf b/GEITje-7B-ultra-sft.i1-IQ3_M.gguf new file mode 100644 index 0000000..f8d479a --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f396297909e2a7409615bce1d6fc490e4dceb8a80e5dd65b76ee194605eebc73 +size 3284894464 diff --git a/GEITje-7B-ultra-sft.i1-IQ3_S.gguf b/GEITje-7B-ultra-sft.i1-IQ3_S.gguf new file mode 100644 index 0000000..a641aef --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:678382362afada7ccf1dcd24411346fd0fae9e5273fc2b3b01f6db3edb722131 +size 3182396160 diff --git a/GEITje-7B-ultra-sft.i1-IQ3_XS.gguf b/GEITje-7B-ultra-sft.i1-IQ3_XS.gguf new file mode 100644 index 0000000..6cc6519 --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d02b49e8027affdc31c076c7a6ec0a131fea36860c394d5b6bcb154d2a182dcf +size 3018818304 diff --git a/GEITje-7B-ultra-sft.i1-IQ3_XXS.gguf b/GEITje-7B-ultra-sft.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..ecf757b --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ef1d43fa7b48fd42ec360f35c39f92563277d490ba703f7532e8d4243769c65 +size 2827346688 diff --git a/GEITje-7B-ultra-sft.i1-IQ4_NL.gguf b/GEITje-7B-ultra-sft.i1-IQ4_NL.gguf new file mode 100644 index 0000000..52065b4 --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5e11ade540132384bcc89325f2ec8f3225a7c06bbb2624e0718fc94218eb102 +size 4125696768 diff --git a/GEITje-7B-ultra-sft.i1-IQ4_XS.gguf b/GEITje-7B-ultra-sft.i1-IQ4_XS.gguf new file mode 100644 index 0000000..14453ec --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c139343259be6162b612abd435765bbbf956a5dade3702313a51aff1dcfd5d03 +size 3907691264 diff --git a/GEITje-7B-ultra-sft.i1-Q2_K.gguf b/GEITje-7B-ultra-sft.i1-Q2_K.gguf new file mode 100644 index 0000000..913b2c1 --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97ee61dbba21d06dc03de44d1c7610378577ef3c7c80f9d5862e1c40c41c84b0 +size 2719245056 diff --git a/GEITje-7B-ultra-sft.i1-Q2_K_S.gguf b/GEITje-7B-ultra-sft.i1-Q2_K_S.gguf new file mode 100644 index 0000000..3de6095 --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdb404866e203f76994c0f575fc614c26cc7860e5930f13afa1751cd79b42518 +size 2528928512 diff --git a/GEITje-7B-ultra-sft.i1-Q3_K_L.gguf b/GEITje-7B-ultra-sft.i1-Q3_K_L.gguf new file mode 100644 index 0000000..16a13f4 --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:376445a4d4f7c5a4c550fc33cbfbd604958bee6552cb71fa60c9a0af429e6f77 +size 3822027520 diff --git a/GEITje-7B-ultra-sft.i1-Q3_K_M.gguf b/GEITje-7B-ultra-sft.i1-Q3_K_M.gguf new file mode 100644 index 0000000..d5b204b --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0ac427810580bdbc8a9af27fa988d08823455e2c26b864699d30683bc6d5663 +size 3518989056 diff --git a/GEITje-7B-ultra-sft.i1-Q3_K_S.gguf b/GEITje-7B-ultra-sft.i1-Q3_K_S.gguf new file mode 100644 index 0000000..1c29ea8 --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ee1d574af4cdd4228dd9f68b3632a9c40709807139edaced15fc68864253f11 +size 3164570368 diff --git a/GEITje-7B-ultra-sft.i1-Q4_0.gguf b/GEITje-7B-ultra-sft.i1-Q4_0.gguf new file mode 100644 index 0000000..8962914 --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9d18b92df480ae30a8d0a8ae36be971718a99975918e02ffd6d779e7d41aacb +size 4123599616 diff --git a/GEITje-7B-ultra-sft.i1-Q4_1.gguf b/GEITje-7B-ultra-sft.i1-Q4_1.gguf new file mode 100644 index 0000000..a01d229 --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b74cafb7d4b999cf341310f2563549e3a0d4dbb720ead4c9c5c8cf99d3bb9cd +size 4553319168 diff --git a/GEITje-7B-ultra-sft.i1-Q4_K_M.gguf b/GEITje-7B-ultra-sft.i1-Q4_K_M.gguf new file mode 100644 index 0000000..619d5fc --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c0135d06e8094b31eb3297ad5a7427e0eb0eaa171c96a42d254ffd6e41492dc +size 4368442112 diff --git a/GEITje-7B-ultra-sft.i1-Q4_K_S.gguf b/GEITje-7B-ultra-sft.i1-Q4_K_S.gguf new file mode 100644 index 0000000..aa74558 --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92736bdc58921292d51ddae95188720999c0b63b150075fe64fb5928b15030f1 +size 4140376832 diff --git a/GEITje-7B-ultra-sft.i1-Q5_K_M.gguf b/GEITje-7B-ultra-sft.i1-Q5_K_M.gguf new file mode 100644 index 0000000..f9d8da6 --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c766d0e0e4598bc2a6f08f213f60fe4d3802fcaff4119115913bac9d0e8f296e +size 5131412224 diff --git a/GEITje-7B-ultra-sft.i1-Q5_K_S.gguf b/GEITje-7B-ultra-sft.i1-Q5_K_S.gguf new file mode 100644 index 0000000..5e43987 --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:189fff80f334a6310ad1558c572cbbdc2210de19cab8b726df553c33dc9270e4 +size 4997718784 diff --git a/GEITje-7B-ultra-sft.i1-Q6_K.gguf b/GEITje-7B-ultra-sft.i1-Q6_K.gguf new file mode 100644 index 0000000..e414828 --- /dev/null +++ b/GEITje-7B-ultra-sft.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db9ca050e6a5ff77835a77bc6863c4dc7b8548895ecba0fb00531bf2068d50f7 +size 5942067968 diff --git a/README.md b/README.md new file mode 100644 index 0000000..cdf9661 --- /dev/null +++ b/README.md @@ -0,0 +1,88 @@ +--- +base_model: BramVanroy/GEITje-7B-ultra-sft +datasets: +- BramVanroy/ultrachat_200k_dutch +- BramVanroy/stackoverflow-chat-dutch +- BramVanroy/alpaca-cleaned-dutch +- BramVanroy/dolly-15k-dutch +- BramVanroy/no_robots_dutch +language: +- nl +library_name: transformers +license: cc-by-nc-4.0 +quantized_by: mradermacher +tags: +- alignment-handbook +- trl +- sft +- geitje +- conversational +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/BramVanroy/GEITje-7B-ultra-sft + + +static quants are available at https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-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/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-IQ1_S.gguf) | i1-IQ1_S | 1.7 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-IQ1_M.gguf) | i1-IQ1_M | 1.9 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-IQ2_S.gguf) | i1-IQ2_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-IQ2_M.gguf) | i1-IQ2_M | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-Q2_K.gguf) | i1-Q2_K | 2.8 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 2.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.3 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-IQ3_S.gguf) | i1-IQ3_S | 3.3 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-IQ3_M.gguf) | i1-IQ3_M | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.6 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-Q3_K_L.gguf) | i1-Q3_K_L | 3.9 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-Q4_0.gguf) | i1-Q4_0 | 4.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-Q4_1.gguf) | i1-Q4_1 | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/GEITje-7B-ultra-sft-i1-GGUF/resolve/main/GEITje-7B-ultra-sft.i1-Q6_K.gguf) | i1-Q6_K | 6.0 | 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/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..beba91f --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e24dbf404a5275ff5e9ccdc221cafa5924a8ce04780fb3ae45dacb24be85297 +size 4988157