commit 07630045e66c9e4d39aa2478183c02ad44f64750 Author: ModelHub XC Date: Wed May 20 04:13:48 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..828029c --- /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 +Llama-3.2-3B-Instruct-abliterated.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-Q4_0_4_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-Q4_0_8_8.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Instruct-abliterated.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-IQ1_M.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-IQ1_M.gguf new file mode 100644 index 0000000..eb4f694 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b839d67eb9f0c6f416b9b1fd33013b2633f82c7032fddb3d2e58e662e31c5138 +size 1053473984 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-IQ1_S.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-IQ1_S.gguf new file mode 100644 index 0000000..22e1d04 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7beacc87fc614aae8a69cdd8b51a22df5f9bb0a2cdd7f7102d74259764fff6ee +size 997440704 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-IQ2_M.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-IQ2_M.gguf new file mode 100644 index 0000000..f722844 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad4930a663bfed92b7f7d5bd23cdf17c90f4e874fb0175460dd31a2b65c1b083 +size 1398330560 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-IQ2_S.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-IQ2_S.gguf new file mode 100644 index 0000000..4dde181 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58affbf7712ff17f3815dde62a044fc2446d10aa2b1ec022731d3479e0351926 +size 1323619520 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-IQ2_XS.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-IQ2_XS.gguf new file mode 100644 index 0000000..63fc24c --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4963fa64bb612138e9f78b36f42956be75c9a394304fcb084e60a8495750aa16 +size 1229831360 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-IQ2_XXS.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..1ade212 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66413229f50e9f4857722cebd889d356a2d66dff4e57b10ef967ee1445605475 +size 1146862784 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-IQ3_M.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-IQ3_M.gguf new file mode 100644 index 0000000..ddbd017 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01a2253ec93e04e852e2a0c239ecbfb6968caa01dc434911af4b3c06ad64b412 +size 1768967360 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-IQ3_S.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-IQ3_S.gguf new file mode 100644 index 0000000..22e5b4d --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48a3df530a4e5114ea1dbd9106158fc7e066762cb14969e807514985b57942f0 +size 1712147648 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-IQ3_XS.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-IQ3_XS.gguf new file mode 100644 index 0000000..13581aa --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5eae777c85455c27ac0125d944beeca4684a9e937c029b1a0ecfe95e0c4b750 +size 1646087360 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-IQ3_XXS.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..8e6fa61 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7a99c81228782b4511851b19ef201f04abde5f5e44503b5b3fe553f98fd784f +size 1518064832 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-IQ4_XS.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-IQ4_XS.gguf new file mode 100644 index 0000000..54255ac --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46bd36ee995b53efaa9a0341b2fdc7df6fd818721ff77d9c4b8b5ec3ba43fbfd +size 2038424768 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-Q2_K.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-Q2_K.gguf new file mode 100644 index 0000000..d793bf6 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffab6f0d156f13fe455c06d30623384c9d54aaa6491db9f56ef39cb430d26acd +size 1493218496 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-Q3_K_L.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-Q3_K_L.gguf new file mode 100644 index 0000000..3a52813 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7c48c3d6e3af6cdd253549400abfeefc5f87d3f49b2f0bc3445632c928abd10 +size 1984646336 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-Q3_K_M.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-Q3_K_M.gguf new file mode 100644 index 0000000..74e745d --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cefb9ce123d0636ff85730954f03e3cffde925250d9dd6885e970582c3590197 +size 1856457920 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-Q3_K_S.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-Q3_K_S.gguf new file mode 100644 index 0000000..52427a9 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed7d0fa1af38baa314a1e3af72291bbe02e2dfd9a015ce322f43a0f7dfae3869 +size 1712147648 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-Q4_0.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-Q4_0.gguf new file mode 100644 index 0000000..ea5a478 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a5bc55ecfffa5ebc50644294457dd879a993d7939f3b0d9dae4e888e245bc33 +size 2143536320 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-Q4_0_4_4.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-Q4_0_4_4.gguf new file mode 100644 index 0000000..e6dca62 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6545bded108c96003f37e1635c84cebefdd88be9a9303b4df2937735d5d6a0a +size 2138817728 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-Q4_0_4_8.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-Q4_0_4_8.gguf new file mode 100644 index 0000000..ed5c545 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-Q4_0_4_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89fd417110ef504ed6fa747c3e0ecea4660ed04cc1983dd3cfdd982cf3bcc260 +size 2138817728 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-Q4_0_8_8.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-Q4_0_8_8.gguf new file mode 100644 index 0000000..0cbe6c0 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-Q4_0_8_8.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e9d8914c179e14badff55d88bddfa2a7b244a94436cb3c4b68b7edbb121894e +size 2138817728 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-Q4_K_M.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-Q4_K_M.gguf new file mode 100644 index 0000000..8c26d01 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb4c67ad696baa379bf572ebf753d48591fdc26035f4d19c5e60a4d570785b0c +size 2241004736 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-Q4_K_S.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-Q4_K_S.gguf new file mode 100644 index 0000000..0828064 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eef54cc3750b7118a79258160442fe796b0961d3ff2dfaa1a18688cf42bd4c9 +size 2149827776 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-Q5_K_M.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-Q5_K_M.gguf new file mode 100644 index 0000000..bf86b63 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:123565f42211a7caa7abf29eb5f9d9c741dbb83d504b9985f6b02b25b76e8e75 +size 2593031360 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-Q5_K_S.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-Q5_K_S.gguf new file mode 100644 index 0000000..7e150bc --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdeb1d648dff9f27f354b929632aad858b39b0783412d5929b036ca94e448d99 +size 2540389568 diff --git a/Llama-3.2-3B-Instruct-abliterated.i1-Q6_K.gguf b/Llama-3.2-3B-Instruct-abliterated.i1-Q6_K.gguf new file mode 100644 index 0000000..b295cf5 --- /dev/null +++ b/Llama-3.2-3B-Instruct-abliterated.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39387b52c3408cfa1edd2f8450d10ee953fadbe7099050a0f3f12218b6b26b6a +size 2967059648 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f6eb45d --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: huihui-ai/Llama-3.2-3B-Instruct-abliterated +language: +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +tags: +- abliterated +- uncensored +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/huihui-ai/Llama-3.2-3B-Instruct-abliterated + + +static quants are available at https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-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/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-IQ1_S.gguf) | i1-IQ1_S | 1.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-IQ1_M.gguf) | i1-IQ1_M | 1.2 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-IQ2_XS.gguf) | i1-IQ2_XS | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-IQ2_S.gguf) | i1-IQ2_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-IQ2_M.gguf) | i1-IQ2_M | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-Q2_K.gguf) | i1-Q2_K | 1.6 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 1.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-IQ3_XS.gguf) | i1-IQ3_XS | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-IQ3_S.gguf) | i1-IQ3_S | 1.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-Q3_K_S.gguf) | i1-Q3_K_S | 1.8 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-IQ3_M.gguf) | i1-IQ3_M | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-Q3_K_M.gguf) | i1-Q3_K_M | 2.0 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-Q3_K_L.gguf) | i1-Q3_K_L | 2.1 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-IQ4_XS.gguf) | i1-IQ4_XS | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 2.2 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 2.2 | fast on arm+i8mm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 2.2 | fast on arm+sve, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-Q4_0.gguf) | i1-Q4_0 | 2.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-Q4_K_S.gguf) | i1-Q4_K_S | 2.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-Q4_K_M.gguf) | i1-Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-Q5_K_S.gguf) | i1-Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-Q5_K_M.gguf) | i1-Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Instruct-abliterated-i1-GGUF/resolve/main/Llama-3.2-3B-Instruct-abliterated.i1-Q6_K.gguf) | i1-Q6_K | 3.1 | 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..e0b37d6 --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b76e0e85c8c0b90f633da85889e22d5f5b343cd55b8c475f690f15687ab2f530 +size 2988377