commit 1e686a69744247c30b3174a72c7b8f3affc2dd7a Author: ModelHub XC Date: Wed Apr 22 06:59:53 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e1c502b --- /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 +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ1_M.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ1_M.gguf new file mode 100644 index 0000000..e2358a9 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f914ec102019f9f85697485a8c49d9c09cf50e5d632a66c052e5009a1e7c4e9d +size 317975392 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ1_S.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ1_S.gguf new file mode 100644 index 0000000..a50793d --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8647456c70e72db70cb15bc8a9ba9918131230da9b45407d433ee873a3fd3d52 +size 315830368 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_M.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_M.gguf new file mode 100644 index 0000000..df93dca --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ffd6ca86c1bfca0d6036400768bd354aba68375b30a0ba0ff98f65848f39e5d +size 328598368 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_S.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_S.gguf new file mode 100644 index 0000000..71f78aa --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a969b387d0fec30dd69df172831ab98446e68aaec7ae4eee654deec54b4e935 +size 325738336 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_XS.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_XS.gguf new file mode 100644 index 0000000..604510c --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbd1c451cecf3dc73764e4dfb88a0cde1291741b50e1fbb2ecf6571b5bce2207 +size 324410464 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_XXS.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..65e2153 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83cc95ccf5bbe5e2f3e515f05bd06c2be1b52dcc3cdae9b0be592fdc152dd835 +size 321550432 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_M.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_M.gguf new file mode 100644 index 0000000..7d828ac --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84296c3954900be9ec81c3d3d474367c39a969a31dc745b7798efb682b138c45 +size 342753376 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_S.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_S.gguf new file mode 100644 index 0000000..3882cde --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6662c7c5192d156e683c0b71071a9df3b1764a98d39da1a4a68055f92369d8d +size 338608480 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_XS.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_XS.gguf new file mode 100644 index 0000000..be8eec9 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0767de3b126177de916e04b11f81358daa4faee307358293922c424d68b4662a +size 338608480 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_XXS.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..de759fd --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d163ed0371767693dc9ee88c08b6264f3060cb842d4f84a1c49a8896502601e +size 333705568 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ4_NL.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ4_NL.gguf new file mode 100644 index 0000000..9749098 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dba2ebd7f20a5ed344392cf349d6f310e0af86524bd07149ff9c8b5f5797a453 +size 352672096 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ4_XS.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ4_XS.gguf new file mode 100644 index 0000000..565dce0 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef37bd72be4cc6f76b7f147c995c5456315b4ce1a1caee49c99584c5052c78fd +size 349403488 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q2_K.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q2_K.gguf new file mode 100644 index 0000000..56e439a --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cc689831908cec1fded6c9ef442a1aa8ed43c7ffa95d3832db1fd5d59778bc1 +size 338608480 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q2_K_S.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q2_K_S.gguf new file mode 100644 index 0000000..ee5dc3b --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a1559c74632e28347a4485f68d998aba05d94eac7b4181b78824b5f93b64e22 +size 331049824 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q3_K_L.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q3_K_L.gguf new file mode 100644 index 0000000..8aa63c2 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6460168ae894d7019d7d8598e6ed78500ed4eb88155dd7832e47dca478a01f0 +size 369359200 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q3_K_M.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q3_K_M.gguf new file mode 100644 index 0000000..5087286 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee9330bd8f308f86d12b8d486435d9cc68895fdff2f417a4aae7eae63d548636 +size 355467616 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q3_K_S.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q3_K_S.gguf new file mode 100644 index 0000000..88737b1 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65175e70ac1054990fc3a63bd31533f7864e8fecdee2b3b7f5c529949c49d6d8 +size 338264416 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_0.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_0.gguf new file mode 100644 index 0000000..5a65305 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ada26d806ffd6bdf80a9ad02ba4e29fea1c5aee87b902be7192da9ec793b2552 +size 352973152 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_1.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_1.gguf new file mode 100644 index 0000000..bd2ef74 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36ad766ea221abb1d31525cd6eeb09894baa8ceadc9723788496c9573677b5cd +size 374520160 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_K_M.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_K_M.gguf new file mode 100644 index 0000000..8a24179 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fb9c0c63fdb6df105fbc12aa4832ab0ca6dee6d7cd6e31eef14c9a5bd0d665c +size 397808992 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_K_S.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_K_S.gguf new file mode 100644 index 0000000..5fba97b --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f14b2d867947138825f16d52965654dcfed72bdd0d43e4488b2b91e7a29bc52a +size 385472864 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q5_K_M.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q5_K_M.gguf new file mode 100644 index 0000000..b82b289 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a4b1464555ac629cf9405144eec56c537bdd1145610afc4243e67e0a6ef84b +size 420087136 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q5_K_S.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q5_K_S.gguf new file mode 100644 index 0000000..6427ff7 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35ebfb3372bdb928533e58ca7c6c16eebd805307e2ba64b8ea91531a8c1761a3 +size 412711264 diff --git a/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q6_K.gguf b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q6_K.gguf new file mode 100644 index 0000000..63fae7a --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68531b2ed8a60d0751a13a1305251dfba7c2426e4b31f2754aed4f4b38c67740 +size 505737568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a4da688 --- /dev/null +++ b/README.md @@ -0,0 +1,89 @@ +--- +base_model: huihui-ai/Qwen2.5-0.5B-Instruct-abliterated-SFT +datasets: +- huihui-ai/Guilherme34_uncensor +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- abliterated +- uncensored +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/huihui-ai/Qwen2.5-0.5B-Instruct-abliterated-SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF).*** + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-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/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ1_S.gguf) | i1-IQ1_S | 0.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ1_M.gguf) | i1-IQ1_M | 0.4 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_XS.gguf) | i1-IQ2_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_S.gguf) | i1-IQ2_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ2_M.gguf) | i1-IQ2_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q2_K_S.gguf) | i1-Q2_K_S | 0.4 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q3_K_S.gguf) | i1-Q3_K_S | 0.4 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_S.gguf) | i1-IQ3_S | 0.4 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_XS.gguf) | i1-IQ3_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q2_K.gguf) | i1-Q2_K | 0.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ3_M.gguf) | i1-IQ3_M | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ4_XS.gguf) | i1-IQ4_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-IQ4_NL.gguf) | i1-IQ4_NL | 0.5 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_0.gguf) | i1-Q4_0 | 0.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q3_K_M.gguf) | i1-Q3_K_M | 0.5 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q3_K_L.gguf) | i1-Q3_K_L | 0.5 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_1.gguf) | i1-Q4_1 | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_K_S.gguf) | i1-Q4_K_S | 0.5 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q4_K_M.gguf) | i1-Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q5_K_S.gguf) | i1-Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.i1-Q5_K_M.gguf) | i1-Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-abliterated-SFT-i1-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-abliterated-SFT.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..38dffad --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4c38c55198b5a2c506b04576bfe29f7ee3f3ddf101ac5cab24c93f3920b0df8 +size 988597