commit 7ca1f01838ab45f3f923b7e44e11692168435f62 Author: ModelHub XC Date: Wed Jul 15 04:11:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/mlabonne_Qwen3-8B-abliterated-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7bb1e58 --- /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 +mlabonne_Qwen3-8B-abliterated-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated-bf16.gguf filter=lfs diff=lfs merge=lfs -text +mlabonne_Qwen3-8B-abliterated.imatrix filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..49e44c0 --- /dev/null +++ b/README.md @@ -0,0 +1,179 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +base_model: mlabonne/Qwen3-8B-abliterated +tags: +- abliteration +- abliterated +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen3-8B/blob/main/LICENSE +base_model_relation: quantized +--- + +## Llamacpp imatrix Quantizations of Qwen3-8B-abliterated by mlabonne + +Using llama.cpp release b5415 for quantization. + +Original model: https://huggingface.co/mlabonne/Qwen3-8B-abliterated + +All quants made using imatrix option with dataset from [here](https://gist.github.com/bartowski1182/eb213dccb3571f863da82e99418f81e8) + +Run them in [LM Studio](https://lmstudio.ai/) + +Run them directly with [llama.cpp](https://github.com/ggerganov/llama.cpp), or any other llama.cpp based project + +## Prompt format + +``` +<|im_start|>system +{system_prompt}<|im_end|> +<|im_start|>user +{prompt}<|im_end|> +<|im_start|>assistant +``` + +## What's new: + +Original model updated + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Qwen3-8B-abliterated-bf16.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-bf16.gguf) | bf16 | 16.39GB | false | Full BF16 weights. | +| [Qwen3-8B-abliterated-Q8_0.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-Q8_0.gguf) | Q8_0 | 8.71GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Qwen3-8B-abliterated-Q6_K_L.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-Q6_K_L.gguf) | Q6_K_L | 7.03GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Qwen3-8B-abliterated-Q6_K.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-Q6_K.gguf) | Q6_K | 6.73GB | false | Very high quality, near perfect, *recommended*. | +| [Qwen3-8B-abliterated-Q5_K_L.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-Q5_K_L.gguf) | Q5_K_L | 6.24GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Qwen3-8B-abliterated-Q5_K_M.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-Q5_K_M.gguf) | Q5_K_M | 5.85GB | false | High quality, *recommended*. | +| [Qwen3-8B-abliterated-Q5_K_S.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-Q5_K_S.gguf) | Q5_K_S | 5.72GB | false | High quality, *recommended*. | +| [Qwen3-8B-abliterated-Q4_K_L.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-Q4_K_L.gguf) | Q4_K_L | 5.49GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Qwen3-8B-abliterated-Q4_1.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-Q4_1.gguf) | Q4_1 | 5.25GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Qwen3-8B-abliterated-Q4_K_M.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-Q4_K_M.gguf) | Q4_K_M | 5.03GB | false | Good quality, default size for most use cases, *recommended*. | +| [Qwen3-8B-abliterated-Q3_K_XL.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-Q3_K_XL.gguf) | Q3_K_XL | 4.98GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Qwen3-8B-abliterated-Q4_K_S.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-Q4_K_S.gguf) | Q4_K_S | 4.80GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Qwen3-8B-abliterated-Q4_0.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-Q4_0.gguf) | Q4_0 | 4.79GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Qwen3-8B-abliterated-IQ4_NL.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-IQ4_NL.gguf) | IQ4_NL | 4.79GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Qwen3-8B-abliterated-IQ4_XS.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-IQ4_XS.gguf) | IQ4_XS | 4.56GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Qwen3-8B-abliterated-Q3_K_L.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-Q3_K_L.gguf) | Q3_K_L | 4.43GB | false | Lower quality but usable, good for low RAM availability. | +| [Qwen3-8B-abliterated-Q3_K_M.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-Q3_K_M.gguf) | Q3_K_M | 4.12GB | false | Low quality. | +| [Qwen3-8B-abliterated-IQ3_M.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-IQ3_M.gguf) | IQ3_M | 3.90GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Qwen3-8B-abliterated-Q2_K_L.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-Q2_K_L.gguf) | Q2_K_L | 3.89GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Qwen3-8B-abliterated-Q3_K_S.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-Q3_K_S.gguf) | Q3_K_S | 3.77GB | false | Low quality, not recommended. | +| [Qwen3-8B-abliterated-IQ3_XS.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-IQ3_XS.gguf) | IQ3_XS | 3.63GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Qwen3-8B-abliterated-IQ3_XXS.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-IQ3_XXS.gguf) | IQ3_XXS | 3.37GB | false | Lower quality, new method with decent performance, comparable to Q3 quants. | +| [Qwen3-8B-abliterated-Q2_K.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-Q2_K.gguf) | Q2_K | 3.28GB | false | Very low quality but surprisingly usable. | +| [Qwen3-8B-abliterated-IQ2_M.gguf](https://huggingface.co/bartowski/mlabonne_Qwen3-8B-abliterated-GGUF/blob/main/mlabonne_Qwen3-8B-abliterated-IQ2_M.gguf) | IQ2_M | 3.05GB | false | Relatively low quality, uses SOTA techniques to be surprisingly usable. | + +## Embed/output weights + +Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to. + +## Downloading using huggingface-cli + +
+ Click to view download instructions + +First, make sure you have hugginface-cli installed: + +``` +pip install -U "huggingface_hub[cli]" +``` + +Then, you can target the specific file you want: + +``` +huggingface-cli download bartowski/mlabonne_Qwen3-8B-abliterated-GGUF --include "mlabonne_Qwen3-8B-abliterated-Q4_K_M.gguf" --local-dir ./ +``` + +If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run: + +``` +huggingface-cli download bartowski/mlabonne_Qwen3-8B-abliterated-GGUF --include "mlabonne_Qwen3-8B-abliterated-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (mlabonne_Qwen3-8B-abliterated-Q8_0) or download them all in place (./) + +
+ +## ARM/AVX information + +Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass. + +Now, however, there is something called "online repacking" for weights. details in [this PR](https://github.com/ggerganov/llama.cpp/pull/9921). If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly. + +As of llama.cpp build [b4282](https://github.com/ggerganov/llama.cpp/releases/tag/b4282) you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0. + +Additionally, if you want to get slightly better quality for , you can use IQ4_NL thanks to [this PR](https://github.com/ggerganov/llama.cpp/pull/10541) which will also repack the weights for ARM, though only the 4_4 for now. The loading time may be slower but it will result in an overall speed incrase. + +
+ Click to view Q4_0_X_X information (deprecated + +I'm keeping this section to show the potential theoretical uplift in performance from using the Q4_0 with online repacking. + +
+ Click to view benchmarks on an AVX2 system (EPYC7702) + +| model | size | params | backend | threads | test | t/s | % (vs Q4_0) | +| ------------------------------ | ---------: | ---------: | ---------- | ------: | ------------: | -------------------: |-------------: | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp512 | 204.03 ± 1.03 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp1024 | 282.92 ± 0.19 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | pp2048 | 259.49 ± 0.44 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg128 | 39.12 ± 0.27 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg256 | 39.31 ± 0.69 | 100% | +| qwen2 3B Q4_0 | 1.70 GiB | 3.09 B | CPU | 64 | tg512 | 40.52 ± 0.03 | 100% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp512 | 301.02 ± 1.74 | 147% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp1024 | 287.23 ± 0.20 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | pp2048 | 262.77 ± 1.81 | 101% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg128 | 18.80 ± 0.99 | 48% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg256 | 24.46 ± 3.04 | 83% | +| qwen2 3B Q4_K_M | 1.79 GiB | 3.09 B | CPU | 64 | tg512 | 36.32 ± 3.59 | 90% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp512 | 271.71 ± 3.53 | 133% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp1024 | 279.86 ± 45.63 | 100% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | pp2048 | 320.77 ± 5.00 | 124% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg128 | 43.51 ± 0.05 | 111% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg256 | 43.35 ± 0.09 | 110% | +| qwen2 3B Q4_0_8_8 | 1.69 GiB | 3.09 B | CPU | 64 | tg512 | 42.60 ± 0.31 | 105% | + +Q4_0_8_8 offers a nice bump to prompt processing and a small bump to text generation + +
+ +
+ +## Which file should I choose? + +
+ Click here for details + +A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) + +The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. + +If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. + +If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. + +Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. + +If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. + +If you want to get more into the weeds, you can check out this extremely useful feature chart: + +[llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix) + +But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. + +These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. + +
+ +## Credits + +Thank you kalomaze and Dampf for assistance in creating the imatrix calibration dataset. + +Thank you ZeroWw for the inspiration to experiment with embed/output. + +Thank you to LM Studio for sponsoring my work. + +Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski diff --git a/mlabonne_Qwen3-8B-abliterated-IQ2_M.gguf b/mlabonne_Qwen3-8B-abliterated-IQ2_M.gguf new file mode 100644 index 0000000..08663a6 --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32097cdb4325d8d28e5c12a3bda10667dbcf15b459dbf410918501237591fdfc +size 3051914848 diff --git a/mlabonne_Qwen3-8B-abliterated-IQ3_M.gguf b/mlabonne_Qwen3-8B-abliterated-IQ3_M.gguf new file mode 100644 index 0000000..10f0ea6 --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4baf67b175ae0e40fc1e0c33adffc4a761fe686cbf29162325af8fdfc3b5e986 +size 3896620640 diff --git a/mlabonne_Qwen3-8B-abliterated-IQ3_XS.gguf b/mlabonne_Qwen3-8B-abliterated-IQ3_XS.gguf new file mode 100644 index 0000000..1bcc04c --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a44e167bd596698295c8fe9a306837ea94652b6665ddc833233209e9d6750a11 +size 3626874464 diff --git a/mlabonne_Qwen3-8B-abliterated-IQ3_XXS.gguf b/mlabonne_Qwen3-8B-abliterated-IQ3_XXS.gguf new file mode 100644 index 0000000..783d25f --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd351fd97e9913dd4191066b3cd025fe505a19d54ee8f15ca344f3a5e06c11a6 +size 3369633376 diff --git a/mlabonne_Qwen3-8B-abliterated-IQ4_NL.gguf b/mlabonne_Qwen3-8B-abliterated-IQ4_NL.gguf new file mode 100644 index 0000000..a531919 --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39a227e542c701c9582e1f8dd410c32327cafbf36b1dcd8f3ec5ea37ae2970fa +size 4793624160 diff --git a/mlabonne_Qwen3-8B-abliterated-IQ4_XS.gguf b/mlabonne_Qwen3-8B-abliterated-IQ4_XS.gguf new file mode 100644 index 0000000..f75c2a2 --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca1c98286a03e3914ff7b3ddd8c43423f25cf6e4b17c679482b33707f1daa606 +size 4561839712 diff --git a/mlabonne_Qwen3-8B-abliterated-Q2_K.gguf b/mlabonne_Qwen3-8B-abliterated-Q2_K.gguf new file mode 100644 index 0000000..a24a80f --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97096bb4bcffdab535d21849fe862d537b2eb5a3e1d6c58484f59f8e4428ad8c +size 3281733216 diff --git a/mlabonne_Qwen3-8B-abliterated-Q2_K_L.gguf b/mlabonne_Qwen3-8B-abliterated-Q2_K_L.gguf new file mode 100644 index 0000000..956bb1f --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e356c845bb2b3513f07f40da08fb1c515afd7bb4f072b260f53b511dbb88aa45 +size 3889477216 diff --git a/mlabonne_Qwen3-8B-abliterated-Q3_K_L.gguf b/mlabonne_Qwen3-8B-abliterated-Q3_K_L.gguf new file mode 100644 index 0000000..eef99fe --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89c5cb47c804f28917a1f88d1bd92b5c6f5b1e7940091406e8783d1dc69417f3 +size 4431394400 diff --git a/mlabonne_Qwen3-8B-abliterated-Q3_K_M.gguf b/mlabonne_Qwen3-8B-abliterated-Q3_K_M.gguf new file mode 100644 index 0000000..fe08a52 --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e53fabce4da0f40ac7d4079f7a48510aa29234763d4bf7bf9cbdd0f0a26d3803 +size 4124161632 diff --git a/mlabonne_Qwen3-8B-abliterated-Q3_K_S.gguf b/mlabonne_Qwen3-8B-abliterated-Q3_K_S.gguf new file mode 100644 index 0000000..9939aaf --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:180d6451b83110ef243181248b2c2962dff55fab7f4ad37a5e7f6289bbdded83 +size 3769611872 diff --git a/mlabonne_Qwen3-8B-abliterated-Q3_K_XL.gguf b/mlabonne_Qwen3-8B-abliterated-Q3_K_XL.gguf new file mode 100644 index 0000000..cfac6af --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd076baa210f160b71f0c695c0cc7d2cb868b82a19e8ec6e5a4890997be3abd4 +size 4975933024 diff --git a/mlabonne_Qwen3-8B-abliterated-Q4_0.gguf b/mlabonne_Qwen3-8B-abliterated-Q4_0.gguf new file mode 100644 index 0000000..3e02409 --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3138a1953df0d6009c49ea09adef62f7f0245d4b03d0125c918afc424666806 +size 4787332704 diff --git a/mlabonne_Qwen3-8B-abliterated-Q4_1.gguf b/mlabonne_Qwen3-8B-abliterated-Q4_1.gguf new file mode 100644 index 0000000..fbd11b0 --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:565ed2b774e5be2db900780114418d411e904f9ee62984cacb9689c69b733923 +size 5247755872 diff --git a/mlabonne_Qwen3-8B-abliterated-Q4_K_L.gguf b/mlabonne_Qwen3-8B-abliterated-Q4_K_L.gguf new file mode 100644 index 0000000..9ed190e --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d4d68a6b870e6b1337b05cd3d74094bdecd3255f89e0b7f262218815094e2fb +size 5489669728 diff --git a/mlabonne_Qwen3-8B-abliterated-Q4_K_M.gguf b/mlabonne_Qwen3-8B-abliterated-Q4_K_M.gguf new file mode 100644 index 0000000..36142b6 --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:361557e69ad101ee22b1baf427283b7ddcf81bc7532b8cee8ac2c6b4d1b81ead +size 5027784288 diff --git a/mlabonne_Qwen3-8B-abliterated-Q4_K_S.gguf b/mlabonne_Qwen3-8B-abliterated-Q4_K_S.gguf new file mode 100644 index 0000000..786022a --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2df915c14e6bd6139ec1a33bdd103253882a3d78dda3727ee1c17ceea8f8e2e +size 4802012768 diff --git a/mlabonne_Qwen3-8B-abliterated-Q5_K_L.gguf b/mlabonne_Qwen3-8B-abliterated-Q5_K_L.gguf new file mode 100644 index 0000000..e48b2de --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d03b8aadc69f887663648829ff273a67edb40d5531401a115ab82195a293ea27 +size 6235207264 diff --git a/mlabonne_Qwen3-8B-abliterated-Q5_K_M.gguf b/mlabonne_Qwen3-8B-abliterated-Q5_K_M.gguf new file mode 100644 index 0000000..1fab532 --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dec7daafa1fa3df665ccb79577d4b71d0f8bea0e7bc74c07f5b0a40cdfbb8fa +size 5851113056 diff --git a/mlabonne_Qwen3-8B-abliterated-Q5_K_S.gguf b/mlabonne_Qwen3-8B-abliterated-Q5_K_S.gguf new file mode 100644 index 0000000..2005f48 --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1ae3debc0a3f276a6328d8e538bd79df202b37153473038f389bfbfcc1ee229 +size 5720761952 diff --git a/mlabonne_Qwen3-8B-abliterated-Q6_K.gguf b/mlabonne_Qwen3-8B-abliterated-Q6_K.gguf new file mode 100644 index 0000000..829856d --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e1b047d8cf005dc57985727ce2cbd5d59c4e23cbda0cb8fca4448250add25c7 +size 6725899872 diff --git a/mlabonne_Qwen3-8B-abliterated-Q6_K_L.gguf b/mlabonne_Qwen3-8B-abliterated-Q6_K_L.gguf new file mode 100644 index 0000000..3fee7e3 --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a7153136bf6e6e4723cdb188e50f47b626d12b6b4d96f9c6d306cd6e4a1029e +size 7027340896 diff --git a/mlabonne_Qwen3-8B-abliterated-Q8_0.gguf b/mlabonne_Qwen3-8B-abliterated-Q8_0.gguf new file mode 100644 index 0000000..402df42 --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94cb715802d16be9c082b3c6ae0350014e36dbcbfe78ad2d5122f42f2e2b5599 +size 8709518944 diff --git a/mlabonne_Qwen3-8B-abliterated-bf16.gguf b/mlabonne_Qwen3-8B-abliterated-bf16.gguf new file mode 100644 index 0000000..67cb7a6 --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbb6edf8edfc2b387cf830d9fb7efd0b7cc6e6093957f152875fcba66279f7cd +size 16388044096 diff --git a/mlabonne_Qwen3-8B-abliterated.imatrix b/mlabonne_Qwen3-8B-abliterated.imatrix new file mode 100644 index 0000000..108e87c --- /dev/null +++ b/mlabonne_Qwen3-8B-abliterated.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5422e60242f956b1ba04d94cfe71d8322ae84b42d56bf1bfc9bc797f39ab9b1e +size 5316782