commit a6296c9bc8785b6ffb35d00ea39865b2df685266 Author: ModelHub XC Date: Sat Jul 18 05:43:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..159472c --- /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 +Qwen2.5-7B-Instruct-abliterated-v2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ1_M.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ1_M.gguf new file mode 100644 index 0000000..50629be --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14724f9ae6e66d08ce8171362f42e41d82800dbb83ff846de6c63803fe861aa7 +size 2042197248 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ1_S.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ1_S.gguf new file mode 100644 index 0000000..d88ada4 --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7be7cb859a0a3a42fedd1665b5328e614931faf568c783f705d1eb9f226b8cc8 +size 1903668480 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_M.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_M.gguf new file mode 100644 index 0000000..61ed719 --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bce36896d5455d9bf6cb7e7d836af9cd6e431cc3538d7adac5ca0abebe7d5fe +size 2780343552 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_S.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_S.gguf new file mode 100644 index 0000000..ff1098c --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3341a955a164689bbd9c42351cae3fa699fbf8e92d81269d2a9489d8c90f973b +size 2595638528 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_XS.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..8f9dbaa --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89ab1626c6ebdca2f463c9259a46d7a74717b7a1faff391902a8e11275e640d6 +size 2469022976 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_XXS.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..95dca5a --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1fc9576fd49305e259259229c83637b9e835a8c4cc5adca85a05622e4392018 +size 2273078528 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_M.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_M.gguf new file mode 100644 index 0000000..5b37693 --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a1d8cb9f46b283e0a629265dc135f2ae0a06a79de0f5adeb5dbf80e4dec7cab +size 3574013184 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_S.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_S.gguf new file mode 100644 index 0000000..ced842f --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc8e89f3abf7ed8987133409257273beb177228f29f5941de42e4b1115832152 +size 3499193600 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_XS.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..41d477c --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd6af3e0b3baf82351b719855b3b67748c448ab597d7720a781c905b31232066 +size 3346257152 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_XXS.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..32f91ba --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c30cc525705478bfb46f5c37a88027a15bd47fc09651ecda102350fdae25aea +size 3114515712 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ4_XS.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..135aaf7 --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a520480f8c049f0004e7b8cf763877863ae4343b0d0fc50f6fc387eeba16e2d +size 4218473728 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q2_K.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q2_K.gguf new file mode 100644 index 0000000..ac66228 --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc783fa539c8c5942920ad373463a08cec77a04e4b81a9cac8fb533f1feeb954 +size 3015941376 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q3_K_L.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..0781dd2 --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec332e2369f847c8150c8688957082a12ccfaba3cdd7f204bf876508579aad7b +size 4088460544 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q3_K_M.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..ca646ab --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7923c45489ffc7199aa03079dfb94ffe79613a126feacb2a8110540d1486174 +size 3808392448 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q3_K_S.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..49bdffc --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ad88136a3a60a141c0d73b25fe902f90778357e598d0659d8578339baa80744 +size 3492369664 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0.gguf new file mode 100644 index 0000000..df806ee --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a31e36d8fd29f592b54aaf9b169364f5650383529a636bc8eaa041be0c71f544 +size 4444122368 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0_4_4.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..7ad2988 --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b8aaee5afe03de756e871d99c1fb18f48dac0bf14f764227e4fa9ba19e16155 +size 4431392000 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0_4_8.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..d9bc9ea --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27b2a109b4b817504c3d988fab2b55e83761ffa01ac34a676ce7abb037e09a41 +size 4431392000 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0_8_8.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..6ae5595 --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a0d4013b8bc6ed824c4d0cc01846e1622e03a5dc22c9ba5c9f9f39e57a5edcf +size 4431392000 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_K_M.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..327f1c9 --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32143e74e5d8e5d32b7abbbaeecfb813f18477f6edc4aaaaab4b61ac2a8ea69d +size 4683074816 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_K_S.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..4ae7d60 --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e085ab1af9c2348c4f187c9972fa8e20c95bb1a436db76cabdea840a9b613975 +size 4457770240 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q5_K_M.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..92c9cee --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b15def933d4e03a75c8287b7c3d245021246fc497e248f4482aaf88eebd481a +size 5444832512 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q5_K_S.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..9ffc7b7 --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be762f47a398e608a4f8cc9c03c54e70a6c38a4d8a36176a42379157413736f0 +size 5315177728 diff --git a/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q6_K.gguf b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q6_K.gguf new file mode 100644 index 0000000..56dcda5 --- /dev/null +++ b/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1357242c7e1f41fc987bf996b47b7dda9123d9c0db0152a7022c2eea7064547 +size 6254200064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e9c9720 --- /dev/null +++ b/README.md @@ -0,0 +1,93 @@ +--- +base_model: huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2 +language: +- zho +- eng +- fra +- spa +- por +- deu +- ita +- rus +- jpn +- kor +- vie +- tha +- ara +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2/blob/main/LICENSE +quantized_by: mradermacher +tags: +- chat +- abliterated +- uncensored +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/huihui-ai/Qwen2.5-7B-Instruct-abliterated-v2 + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-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/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ1_S.gguf) | i1-IQ1_S | 2.0 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ2_M.gguf) | i1-IQ2_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 4.5 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 4.5 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 4.5 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-abliterated-v2-i1-GGUF/resolve/main/Qwen2.5-7B-Instruct-abliterated-v2.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | 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..34cadc0 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae93579f452aaf643c0838b8435baab2fc6025fc66e50e19c1c51073e337d93a +size 4536665