commit 3ae4f092155119e9a69694fd0686e6a57927c365 Author: ModelHub XC Date: Mon Apr 20 02:57:41 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..09a2aa9 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,59 @@ +*.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 +Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ1_M.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ1_M.gguf new file mode 100644 index 0000000..b9b4a4c --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a127c40865be5a040c63180f3dca5e823aa843f9bc2382539165cfd5bd004dd +size 7932161152 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ1_S.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ1_S.gguf new file mode 100644 index 0000000..31baf01 --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6386c1070903aeb3fcd8a1915a31f8a47b5ab7e6727555385cd7ec9faef42d13 +size 7274507392 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_M.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_M.gguf new file mode 100644 index 0000000..47fd03b --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25d0f41e6cd2cc38a6344a8d0a3767594af12d2c02fea533455d109e560d7a67 +size 11264441472 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_S.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_S.gguf new file mode 100644 index 0000000..363380b --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94515b40bf263cc0a3a2bc24245b44a80212cba3ac1828aa0a1cc38df0015bdb +size 10387569792 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_XS.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_XS.gguf new file mode 100644 index 0000000..891f76d --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c41c3fe2793e7dc12201721057d2cd067852243d4103ac19753e31cd1084475 +size 9957551232 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_XXS.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..bc53016 --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a6d915a10206870fb20f19d4c6987e148072bd0e435fef6c27faf838176157a +size 9028250752 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_M.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_M.gguf new file mode 100644 index 0000000..4cac4f2 --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65a446af9f7f97f8d12b00e46e9f03b6e4a59e860d9037eda4c938bba06b5923 +size 14810123392 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_S.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_S.gguf new file mode 100644 index 0000000..019d876 --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e9c680622bbeb4aa2392e8ba307457ddd305322a1be155b8040ab797fa41615 +size 14436895872 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_XS.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_XS.gguf new file mode 100644 index 0000000..d052504 --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb4a37336abe3b85601bb7cd424953e1c63e7dd706c0a9348c623b197e0ed402 +size 13705514112 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_XXS.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..6187058 --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c89baff53f6166afacab9041bc334fbe7b153274d56fcb5b6be4d1308af37865 +size 12839271552 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ4_XS.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ4_XS.gguf new file mode 100644 index 0000000..766932d --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebda56c3d2e70bb1fc71bead479d8392700cb7eb7926fbc80ba262444ba647af +size 17693154432 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q2_K.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q2_K.gguf new file mode 100644 index 0000000..93bff01 --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23ded29a3e682442c65c8310c5d227f48989a9935bfc5df980233f5b7753a793 +size 12313099392 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q2_K_S.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q2_K_S.gguf new file mode 100644 index 0000000..48947a5 --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:460407a480e26bfcfd2d242a20a5771e36d9bf9e6f341b700b6199a7e978b783 +size 11488001152 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q3_K_L.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q3_K_L.gguf new file mode 100644 index 0000000..e196e02 --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08a84043c5afd3e95903a44e0284663aed3cfad2196c1ad17993fbc9d2b4dbc4 +size 17247079552 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q3_K_M.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q3_K_M.gguf new file mode 100644 index 0000000..551fa51 --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08c845d8ca5c290ceb45b45109329e99efd3238c225a6ec145407d529c51653d +size 15935048832 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q3_K_S.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q3_K_S.gguf new file mode 100644 index 0000000..122136c --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daac89ddcdac5507766062f8707320cf55750b7d0e2e6d16f3263abad82d6a5c +size 14392331392 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_0.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_0.gguf new file mode 100644 index 0000000..5fcf729 --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce704436098b8226dd431e0d9dcc2321e9b0071ea752bd34ad46984f4e8a7ec1 +size 18711010432 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_1.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_1.gguf new file mode 100644 index 0000000..dfb1747 --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab4822a1a534fb2049cce463a833d2a4f77e17eef398784b9d4bdb4099692a0d +size 20639243392 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_K_M.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_K_M.gguf new file mode 100644 index 0000000..f48b434 --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8013d1a4e12baa272159bb1ff177d3036ee74ce95f6b64e4d3776eb61431e074 +size 19851336832 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_K_S.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_K_S.gguf new file mode 100644 index 0000000..abf4ce2 --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57bf0fcfd8fb567a34ccc017a1e7a92fe39ed0e983769619aa842cbdbe8a0c03 +size 18784410752 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q5_K_M.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q5_K_M.gguf new file mode 100644 index 0000000..80fe69a --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a47feaf4669c01b0b24427627997f121e3319b6293c1f97b2cd9527222256ac3 +size 23262157952 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q5_K_S.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q5_K_S.gguf new file mode 100644 index 0000000..42118a5 --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03cc29197b4d1a97a7c87c12b33a984fe1767b1fa67456408fc7db4e57da23f4 +size 22638255232 diff --git a/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q6_K.gguf b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q6_K.gguf new file mode 100644 index 0000000..58f2d69 --- /dev/null +++ b/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93620548c83a438f095af232a10215abbf769d8ec03568fafad5e1a82c9d0886 +size 26886155392 diff --git a/README.md b/README.md new file mode 100644 index 0000000..80c739c --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: zetasepic/Qwen2.5-32B-Instruct-abliterated-pass2 +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/zetasepic/Qwen2.5-32B-Instruct-abliterated-pass2 + + +static quants are available at https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-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/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ1_S.gguf) | i1-IQ1_S | 7.4 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_XS.gguf) | i1-IQ2_XS | 10.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_S.gguf) | i1-IQ2_S | 10.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_XS.gguf) | i1-IQ3_XS | 13.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_S.gguf) | i1-IQ3_S | 14.5 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q3_K_L.gguf) | i1-Q3_K_L | 17.3 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_0.gguf) | i1-Q4_0 | 18.8 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q4_1.gguf) | i1-Q4_1 | 20.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q5_K_S.gguf) | i1-Q5_K_S | 22.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q5_K_M.gguf) | i1-Q5_K_M | 23.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-abliterated-pass2-i1-GGUF/resolve/main/Qwen2.5-32B-Instruct-abliterated-pass2.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | 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..3445e35 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e74dc7af9e5e640724a642b908d59b00172f61f3ff897ffd2b67b2f1e329ea8b +size 14957085