commit 5a800afd8c67b97b7ff6913159d3ef43a50daeb7 Author: ModelHub XC Date: Thu May 21 00:08:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MedraQ-8b-abliterated-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0d90234 --- /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 +MedraQ-8b-abliterated.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedraQ-8b-abliterated.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MedraQ-8b-abliterated.i1-IQ1_M.gguf b/MedraQ-8b-abliterated.i1-IQ1_M.gguf new file mode 100644 index 0000000..261316d --- /dev/null +++ b/MedraQ-8b-abliterated.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d5869cdfdb6895db84fe64a244e0152047bc0147662ac50ac2360856f44cda3 +size 1254640960 diff --git a/MedraQ-8b-abliterated.i1-IQ1_S.gguf b/MedraQ-8b-abliterated.i1-IQ1_S.gguf new file mode 100644 index 0000000..d0b1b2f --- /dev/null +++ b/MedraQ-8b-abliterated.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e5d6b8cbbe23767363e5dc6185712ed398506d0036160fe4f169dad1e51bd94 +size 1182879040 diff --git a/MedraQ-8b-abliterated.i1-IQ2_M.gguf b/MedraQ-8b-abliterated.i1-IQ2_M.gguf new file mode 100644 index 0000000..2f1a0f6 --- /dev/null +++ b/MedraQ-8b-abliterated.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a66f876e698377c7cd349b64576fde364ab92ffddd06f3b99ad3a05033cd431 +size 1680110400 diff --git a/MedraQ-8b-abliterated.i1-IQ2_S.gguf b/MedraQ-8b-abliterated.i1-IQ2_S.gguf new file mode 100644 index 0000000..6a99078 --- /dev/null +++ b/MedraQ-8b-abliterated.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7328ac259aaffa395719e108bc7e0b1072360b65815c40af5945faf02dd21fa +size 1584427840 diff --git a/MedraQ-8b-abliterated.i1-IQ2_XS.gguf b/MedraQ-8b-abliterated.i1-IQ2_XS.gguf new file mode 100644 index 0000000..43f0eff --- /dev/null +++ b/MedraQ-8b-abliterated.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afa75087af9e5551e80d689ef5d6e0256026a542552a209b81c167bb73dd9088 +size 1481723200 diff --git a/MedraQ-8b-abliterated.i1-IQ2_XXS.gguf b/MedraQ-8b-abliterated.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..c7b3310 --- /dev/null +++ b/MedraQ-8b-abliterated.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8abc5f23789c85706ad48b7eed7a5edaaa8b2f8bd0fa02d2099ab32efa55c317 +size 1374244160 diff --git a/MedraQ-8b-abliterated.i1-IQ3_M.gguf b/MedraQ-8b-abliterated.i1-IQ3_M.gguf new file mode 100644 index 0000000..dca61c2 --- /dev/null +++ b/MedraQ-8b-abliterated.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54da847f27808b79ca06807270ed8c1ce63bbfcb9ac9f8073fd7e8568b468217 +size 2130022720 diff --git a/MedraQ-8b-abliterated.i1-IQ3_S.gguf b/MedraQ-8b-abliterated.i1-IQ3_S.gguf new file mode 100644 index 0000000..e294739 --- /dev/null +++ b/MedraQ-8b-abliterated.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1acaf796b9fc8c1dd1ce4194bd167e4886ecbec08f8d99b5021abfc3813478b0 +size 2066657600 diff --git a/MedraQ-8b-abliterated.i1-IQ3_XS.gguf b/MedraQ-8b-abliterated.i1-IQ3_XS.gguf new file mode 100644 index 0000000..0176cd7 --- /dev/null +++ b/MedraQ-8b-abliterated.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b172c07d5bdf5e0b5a93512b38f9d2bd3e064c04134815dfd99d39e415d4b30d +size 1981501760 diff --git a/MedraQ-8b-abliterated.i1-IQ3_XXS.gguf b/MedraQ-8b-abliterated.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..8f0ff35 --- /dev/null +++ b/MedraQ-8b-abliterated.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a11414ebb9dc8f7b86f56e961128e67b7dc923db55eaa2eee6742c9a9f73b56 +size 1837314880 diff --git a/MedraQ-8b-abliterated.i1-IQ4_NL.gguf b/MedraQ-8b-abliterated.i1-IQ4_NL.gguf new file mode 100644 index 0000000..5e96250 --- /dev/null +++ b/MedraQ-8b-abliterated.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecce0b2f5acdc8aee883168541fd421cba0c0e7fe0f1cc0935c3a20b1221d645 +size 2600128320 diff --git a/MedraQ-8b-abliterated.i1-IQ4_XS.gguf b/MedraQ-8b-abliterated.i1-IQ4_XS.gguf new file mode 100644 index 0000000..956a083 --- /dev/null +++ b/MedraQ-8b-abliterated.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34972d576e49830df65e33db388217b0fb7e030f37a817ee8ce2b69d1b6ffd2f +size 2477381440 diff --git a/MedraQ-8b-abliterated.i1-Q2_K.gguf b/MedraQ-8b-abliterated.i1-Q2_K.gguf new file mode 100644 index 0000000..1a8466f --- /dev/null +++ b/MedraQ-8b-abliterated.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0200767e941950f14ff10baf5812f81fc7cf89e4dd9ad92e11d958b65b8c971 +size 1797122880 diff --git a/MedraQ-8b-abliterated.i1-Q2_K_S.gguf b/MedraQ-8b-abliterated.i1-Q2_K_S.gguf new file mode 100644 index 0000000..28b6ac3 --- /dev/null +++ b/MedraQ-8b-abliterated.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de93122ce20c30e20672a8a3a2d170ad3ba1b037d91b4dba3f5282d33bfef383 +size 1691077440 diff --git a/MedraQ-8b-abliterated.i1-Q3_K_L.gguf b/MedraQ-8b-abliterated.i1-Q3_K_L.gguf new file mode 100644 index 0000000..c675a94 --- /dev/null +++ b/MedraQ-8b-abliterated.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6991d643f3f119a4a53362aa6b03cad3f98d3ec93e81b7bab1d658774f28a46 +size 2406912320 diff --git a/MedraQ-8b-abliterated.i1-Q3_K_M.gguf b/MedraQ-8b-abliterated.i1-Q3_K_M.gguf new file mode 100644 index 0000000..a859bee --- /dev/null +++ b/MedraQ-8b-abliterated.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cd233a20395e1d70cb8e03a0ebca2471503a675179870cec706adee139802c5 +size 2242744640 diff --git a/MedraQ-8b-abliterated.i1-Q3_K_S.gguf b/MedraQ-8b-abliterated.i1-Q3_K_S.gguf new file mode 100644 index 0000000..e7a516f --- /dev/null +++ b/MedraQ-8b-abliterated.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3815acc68d748904b94d91b9080bac6439538ec562c7409c3a85c91b68c6dde0 +size 2054123840 diff --git a/MedraQ-8b-abliterated.i1-Q4_0.gguf b/MedraQ-8b-abliterated.i1-Q4_0.gguf new file mode 100644 index 0000000..dcd2b36 --- /dev/null +++ b/MedraQ-8b-abliterated.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:210f0d03b488669fe1f5d2d498be461967c9bab0ee16307aaa70f61a3ea45524 +size 2594557760 diff --git a/MedraQ-8b-abliterated.i1-Q4_1.gguf b/MedraQ-8b-abliterated.i1-Q4_1.gguf new file mode 100644 index 0000000..1e337aa --- /dev/null +++ b/MedraQ-8b-abliterated.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c08a339f675a8bdb26a7a62f5ae6eb552618701afc84c220185b1872b97d404 +size 2839723840 diff --git a/MedraQ-8b-abliterated.i1-Q4_K_M.gguf b/MedraQ-8b-abliterated.i1-Q4_K_M.gguf new file mode 100644 index 0000000..785c3aa --- /dev/null +++ b/MedraQ-8b-abliterated.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d00cd6b544130038376c0d71aa6ec6d6748568a5a9750a63b6e58d909ba5f2c7 +size 2716065600 diff --git a/MedraQ-8b-abliterated.i1-Q4_K_S.gguf b/MedraQ-8b-abliterated.i1-Q4_K_S.gguf new file mode 100644 index 0000000..60ea874 --- /dev/null +++ b/MedraQ-8b-abliterated.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4c2d4304311fc899ab3e70c9f496f71713b72cd8c5a2e8431bfc72e49760efe +size 2602094400 diff --git a/MedraQ-8b-abliterated.i1-Q5_K_M.gguf b/MedraQ-8b-abliterated.i1-Q5_K_M.gguf new file mode 100644 index 0000000..79d6590 --- /dev/null +++ b/MedraQ-8b-abliterated.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d72db3abc9aa3f8d219a1ccfe72e521f6dc755faa48a4d47e8a73bb7a6a9fcd +size 3156918080 diff --git a/MedraQ-8b-abliterated.i1-Q5_K_S.gguf b/MedraQ-8b-abliterated.i1-Q5_K_S.gguf new file mode 100644 index 0000000..d6f9882 --- /dev/null +++ b/MedraQ-8b-abliterated.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72f778edc6b98afbd8a044434b0e578ed43adf0eb18566137663217f4904a014 +size 3091115840 diff --git a/MedraQ-8b-abliterated.i1-Q6_K.gguf b/MedraQ-8b-abliterated.i1-Q6_K.gguf new file mode 100644 index 0000000..954a70d --- /dev/null +++ b/MedraQ-8b-abliterated.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08437e545fed2fe6f62a257813e0b913e54e1df49135be1fcc6210952b05c6fc +size 3625323840 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d48ea25 --- /dev/null +++ b/README.md @@ -0,0 +1,91 @@ +--- +base_model: drwlf/MedraQ-8b-abliterated +datasets: +- nicoboss/medra-medical +language: +- en +- ro +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation +- medical-ai +- summarization +- diagnostic-reasoning +- gemma-3 +- fine-tuned +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/drwlf/MedraQ-8b-abliterated + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MedraQ-8b-abliterated-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/MedraQ-8b-abliterated-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/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-IQ1_S.gguf) | i1-IQ1_S | 1.3 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-IQ1_M.gguf) | i1-IQ1_M | 1.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-IQ2_S.gguf) | i1-IQ2_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-IQ2_M.gguf) | i1-IQ2_M | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-Q2_K_S.gguf) | i1-Q2_K_S | 1.8 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-Q2_K.gguf) | i1-Q2_K | 1.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-IQ3_XS.gguf) | i1-IQ3_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-Q3_K_S.gguf) | i1-Q3_K_S | 2.2 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-IQ3_S.gguf) | i1-IQ3_S | 2.2 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-IQ3_M.gguf) | i1-IQ3_M | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.3 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-Q4_0.gguf) | i1-Q4_0 | 2.7 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-IQ4_NL.gguf) | i1-IQ4_NL | 2.7 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.7 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-Q4_1.gguf) | i1-Q4_1 | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-Q5_K_S.gguf) | i1-Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-Q5_K_M.gguf) | i1-Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MedraQ-8b-abliterated-i1-GGUF/resolve/main/MedraQ-8b-abliterated.i1-Q6_K.gguf) | i1-Q6_K | 3.7 | 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..4b43aba --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6adb2daa562c9dc35acd1ddb6d82bf6a0d71398bb6026132dac3fddc83646ea +size 3842209