commit 0321177ca3102046b591edc6a6882f9857f55e09 Author: ModelHub XC Date: Tue May 19 21:07:37 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DR-Tulu-SFT-8B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f53781a --- /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 +DR-Tulu-SFT-8B.imatrix.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +DR-Tulu-SFT-8B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DR-Tulu-SFT-8B.i1-IQ1_M.gguf b/DR-Tulu-SFT-8B.i1-IQ1_M.gguf new file mode 100644 index 0000000..32a1b63 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cfe5e8645d7b004025089a2a5502d74dfefc16f3a8eb4657f10106f1c259e8f +size 2256148608 diff --git a/DR-Tulu-SFT-8B.i1-IQ1_S.gguf b/DR-Tulu-SFT-8B.i1-IQ1_S.gguf new file mode 100644 index 0000000..50ef033 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d4d1bb725318f2f4b505d2f723ab2ac4f5e95e2c27a79c161280e8105c3c7ab +size 2115770496 diff --git a/DR-Tulu-SFT-8B.i1-IQ2_M.gguf b/DR-Tulu-SFT-8B.i1-IQ2_M.gguf new file mode 100644 index 0000000..91bc568 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc5eefc81c427545de58270eeb04d13eb6ca1bf8bb53886168768038d391d22c +size 3051915392 diff --git a/DR-Tulu-SFT-8B.i1-IQ2_S.gguf b/DR-Tulu-SFT-8B.i1-IQ2_S.gguf new file mode 100644 index 0000000..c9642d1 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59f75ab57ddd56180701eb2c9d65f259c480f6693f45ff562c668611edac291b +size 2864744576 diff --git a/DR-Tulu-SFT-8B.i1-IQ2_XS.gguf b/DR-Tulu-SFT-8B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..17c406e --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dad9662fc9172a55e125e03f9d0a48f2253749c66723dcf0107ad17f30ea47c5 +size 2696157312 diff --git a/DR-Tulu-SFT-8B.i1-IQ2_XXS.gguf b/DR-Tulu-SFT-8B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..96d0485 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ea793155c786055d1a2298c489da6faef653b039bdd96cd26ede42ae8177a25 +size 2490112128 diff --git a/DR-Tulu-SFT-8B.i1-IQ3_M.gguf b/DR-Tulu-SFT-8B.i1-IQ3_M.gguf new file mode 100644 index 0000000..2b626f0 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f8ee10df8c76ee0957120034d7869e3ffda32d7143b7e2ed5d94223174e77f1 +size 3896621184 diff --git a/DR-Tulu-SFT-8B.i1-IQ3_S.gguf b/DR-Tulu-SFT-8B.i1-IQ3_S.gguf new file mode 100644 index 0000000..dd52cfe --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b355f20eebe34845cafcfa10d7fd01f54d04869d017063d59820033d5b7c447 +size 3789666432 diff --git a/DR-Tulu-SFT-8B.i1-IQ3_XS.gguf b/DR-Tulu-SFT-8B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..eed3be5 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:119084da8be8990949cabf5996e30b67d1099aac11e2092be8a357018695e84b +size 3626875008 diff --git a/DR-Tulu-SFT-8B.i1-IQ3_XXS.gguf b/DR-Tulu-SFT-8B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..48bb34c --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0769f5feb5f0524e1e8094347362ab03f66e391a028ed497190b4260d098259 +size 3369633920 diff --git a/DR-Tulu-SFT-8B.i1-IQ4_NL.gguf b/DR-Tulu-SFT-8B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..2fcd8d1 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bbac8ba4c85da9e4c2833061212532664bf995998d4b546e9d85776effdf934 +size 4793624704 diff --git a/DR-Tulu-SFT-8B.i1-IQ4_XS.gguf b/DR-Tulu-SFT-8B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..66f3585 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6caf2cb309402e80442ae47af71e66746872897496a73cb64b81044211940b5 +size 4561840256 diff --git a/DR-Tulu-SFT-8B.i1-Q2_K.gguf b/DR-Tulu-SFT-8B.i1-Q2_K.gguf new file mode 100644 index 0000000..256509f --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5d44a392b808a8138c92b675d1a7474b709dbc6876895bdf012254fb47c346d +size 3281733760 diff --git a/DR-Tulu-SFT-8B.i1-Q2_K_S.gguf b/DR-Tulu-SFT-8B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..7a75fb7 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:810aaed294a3c2527213ce6e08038c184bb3462bcdb5533a107742ba19d97af7 +size 3083552896 diff --git a/DR-Tulu-SFT-8B.i1-Q3_K_L.gguf b/DR-Tulu-SFT-8B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..701057b --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:491b6377eda01c5fe6372dbf9232b59e2f50d18f3a1135990addd6b775377ac7 +size 4431394944 diff --git a/DR-Tulu-SFT-8B.i1-Q3_K_M.gguf b/DR-Tulu-SFT-8B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..1f57114 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:307fc5afa7a91f154e1dd58825b267626bd099d07baea591164304ced08ab332 +size 4124162176 diff --git a/DR-Tulu-SFT-8B.i1-Q3_K_S.gguf b/DR-Tulu-SFT-8B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..c29db63 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66e835d96c880789794712ff816b1eee21e1e5e6883f20b0aab585982aa942a0 +size 3769612416 diff --git a/DR-Tulu-SFT-8B.i1-Q4_0.gguf b/DR-Tulu-SFT-8B.i1-Q4_0.gguf new file mode 100644 index 0000000..90c9ee1 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67cc2c8de5a5ef779bfea21038172a9cd71eda52575611150cd8bfb4187c214d +size 4787333248 diff --git a/DR-Tulu-SFT-8B.i1-Q4_1.gguf b/DR-Tulu-SFT-8B.i1-Q4_1.gguf new file mode 100644 index 0000000..6e19e80 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e1c8b913d4f5fef88448e7d360bc404961870b6e1523800b3eda67f11bfb8f7 +size 5247756416 diff --git a/DR-Tulu-SFT-8B.i1-Q4_K_M.gguf b/DR-Tulu-SFT-8B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..e1cca10 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75b5b94551262def25beab18f9022bcd602102d5a54233f39f279db3553a7b39 +size 5027784832 diff --git a/DR-Tulu-SFT-8B.i1-Q4_K_S.gguf b/DR-Tulu-SFT-8B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..47157e2 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7447d1dd888c81a327114f1185f705c749d0cf3ba6ed0e99f34957d2d3a42c91 +size 4802013312 diff --git a/DR-Tulu-SFT-8B.i1-Q5_K_M.gguf b/DR-Tulu-SFT-8B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..53a5051 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dd47d5603f7f665f0b6bda883c4d30db78d598b178a6598f763eb342ace0afd +size 5851113600 diff --git a/DR-Tulu-SFT-8B.i1-Q5_K_S.gguf b/DR-Tulu-SFT-8B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..720f252 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ba6bd6998458ed82afb4e909d107ef74291cffeff3bcd1095f2cfcc7463d66d +size 5720762496 diff --git a/DR-Tulu-SFT-8B.i1-Q6_K.gguf b/DR-Tulu-SFT-8B.i1-Q6_K.gguf new file mode 100644 index 0000000..9281996 --- /dev/null +++ b/DR-Tulu-SFT-8B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd73a55a23b097f63040ff9ff1897700a1154f9a0ca1333d6f185ef95667eff3 +size 6725900416 diff --git a/DR-Tulu-SFT-8B.imatrix.gguf b/DR-Tulu-SFT-8B.imatrix.gguf new file mode 100644 index 0000000..633c8f6 --- /dev/null +++ b/DR-Tulu-SFT-8B.imatrix.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d367fc856e2f5c9c3afce3f3d92e56fe6a56d7e594faf847995a2c867158fff9 +size 5347200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f76fc84 --- /dev/null +++ b/README.md @@ -0,0 +1,91 @@ +--- +base_model: rl-research/DR-Tulu-SFT-8B +datasets: +- rl-research/dr-tulu-sft-data +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama-factory +- full +- generated_from_trainer +--- +## About + + + + + + + + + +weighted/imatrix quants of https://huggingface.co/rl-research/DR-Tulu-SFT-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DR-Tulu-SFT-8B-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-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/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.2 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-IQ2_S.gguf) | i1-IQ2_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.2 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-Q2_K.gguf) | i1-Q2_K | 3.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.9 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-IQ3_S.gguf) | i1-IQ3_S | 3.9 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-IQ3_M.gguf) | i1-IQ3_M | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-Q4_0.gguf) | i1-Q4_0 | 4.9 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.9 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-Q4_1.gguf) | i1-Q4_1 | 5.3 | | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/DR-Tulu-SFT-8B-i1-GGUF/resolve/main/DR-Tulu-SFT-8B.i1-Q6_K.gguf) | i1-Q6_K | 6.8 | 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. + +