commit 45021b6ae641a6db15c79684937be60e09f1d12d Author: ModelHub XC Date: Wed Jul 15 04:20:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9570117 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,58 @@ +*.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 +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q6_K_L.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q5_K_L.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_K_L.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q2_K_L.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-bf16.gguf filter=lfs diff=lfs merge=lfs -text +huihui-ai_Huihui-gemma-3n-E4B-it-abliterated.imatrix filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..a09cdeb --- /dev/null +++ b/README.md @@ -0,0 +1,185 @@ +--- +quantized_by: bartowski +pipeline_tag: text-generation +extra_gated_prompt: To access Gemma on Hugging Face, you’re required to review and + agree to Google’s usage license. To do this, please ensure you’re logged in to Hugging + Face and click below. Requests are processed immediately. +tags: +- automatic-speech-recognition +- automatic-speech-translation +- audio-text-to-text +- video-text-to-text +- abliterated +- uncensored +base_model: huihui-ai/Huihui-gemma-3n-E4B-it-abliterated +base_model_relation: quantized +license: gemma +extra_gated_heading: Access Gemma on Hugging Face +extra_gated_button_content: Acknowledge license +--- + +## Llamacpp imatrix Quantizations of Huihui-gemma-3n-E4B-it-abliterated by huihui-ai + +Using llama.cpp release b5856 for quantization. + +Original model: https://huggingface.co/huihui-ai/Huihui-gemma-3n-E4B-it-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 + +No chat template specified so default is used. This may be incorrect, check original model card for details. + +``` +user +{system_prompt} + +{prompt} +model + +model +``` + +## Download a file (not the whole branch) from below: + +| Filename | Quant type | File Size | Split | Description | +| -------- | ---------- | --------- | ----- | ----------- | +| [Huihui-gemma-3n-E4B-it-abliterated-bf16.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-bf16.gguf) | bf16 | 13.74GB | false | Full BF16 weights. | +| [Huihui-gemma-3n-E4B-it-abliterated-Q8_0.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q8_0.gguf) | Q8_0 | 7.35GB | false | Extremely high quality, generally unneeded but max available quant. | +| [Huihui-gemma-3n-E4B-it-abliterated-Q6_K_L.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q6_K_L.gguf) | Q6_K_L | 6.40GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. | +| [Huihui-gemma-3n-E4B-it-abliterated-Q5_K_L.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q5_K_L.gguf) | Q5_K_L | 5.96GB | false | Uses Q8_0 for embed and output weights. High quality, *recommended*. | +| [Huihui-gemma-3n-E4B-it-abliterated-Q6_K.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q6_K.gguf) | Q6_K | 5.70GB | false | Very high quality, near perfect, *recommended*. | +| [Huihui-gemma-3n-E4B-it-abliterated-Q4_K_L.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_K_L.gguf) | Q4_K_L | 5.54GB | false | Uses Q8_0 for embed and output weights. Good quality, *recommended*. | +| [Huihui-gemma-3n-E4B-it-abliterated-Q3_K_XL.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_XL.gguf) | Q3_K_XL | 5.22GB | false | Uses Q8_0 for embed and output weights. Lower quality but usable, good for low RAM availability. | +| [Huihui-gemma-3n-E4B-it-abliterated-Q5_K_M.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q5_K_M.gguf) | Q5_K_M | 4.95GB | false | High quality, *recommended*. | +| [Huihui-gemma-3n-E4B-it-abliterated-Q5_K_S.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q5_K_S.gguf) | Q5_K_S | 4.87GB | false | High quality, *recommended*. | +| [Huihui-gemma-3n-E4B-it-abliterated-Q2_K_L.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q2_K_L.gguf) | Q2_K_L | 4.61GB | false | Uses Q8_0 for embed and output weights. Very low quality but surprisingly usable. | +| [Huihui-gemma-3n-E4B-it-abliterated-Q4_1.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_1.gguf) | Q4_1 | 4.48GB | false | Legacy format, similar performance to Q4_K_S but with improved tokens/watt on Apple silicon. | +| [Huihui-gemma-3n-E4B-it-abliterated-Q4_K_M.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_K_M.gguf) | Q4_K_M | 4.24GB | false | Good quality, default size for most use cases, *recommended*. | +| [Huihui-gemma-3n-E4B-it-abliterated-Q4_K_S.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_K_S.gguf) | Q4_K_S | 4.10GB | false | Slightly lower quality with more space savings, *recommended*. | +| [Huihui-gemma-3n-E4B-it-abliterated-Q4_0.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_0.gguf) | Q4_0 | 4.09GB | false | Legacy format, offers online repacking for ARM and AVX CPU inference. | +| [Huihui-gemma-3n-E4B-it-abliterated-IQ4_NL.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ4_NL.gguf) | IQ4_NL | 4.09GB | false | Similar to IQ4_XS, but slightly larger. Offers online repacking for ARM CPU inference. | +| [Huihui-gemma-3n-E4B-it-abliterated-IQ4_XS.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ4_XS.gguf) | IQ4_XS | 3.90GB | false | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | +| [Huihui-gemma-3n-E4B-it-abliterated-Q3_K_L.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_L.gguf) | Q3_K_L | 3.60GB | false | Lower quality but usable, good for low RAM availability. | +| [Huihui-gemma-3n-E4B-it-abliterated-Q3_K_M.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_M.gguf) | Q3_K_M | 3.44GB | false | Low quality. | +| [Huihui-gemma-3n-E4B-it-abliterated-IQ3_M.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ3_M.gguf) | IQ3_M | 3.29GB | false | Medium-low quality, new method with decent performance comparable to Q3_K_M. | +| [Huihui-gemma-3n-E4B-it-abliterated-Q3_K_S.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_S.gguf) | Q3_K_S | 3.25GB | false | Low quality, not recommended. | +| [Huihui-gemma-3n-E4B-it-abliterated-IQ3_XS.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ3_XS.gguf) | IQ3_XS | 3.17GB | false | Lower quality, new method with decent performance, slightly better than Q3_K_S. | +| [Huihui-gemma-3n-E4B-it-abliterated-Q2_K.gguf](https://huggingface.co/bartowski/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF/blob/main/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q2_K.gguf) | Q2_K | 2.76GB | false | Very low quality but 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/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF --include "huihui-ai_Huihui-gemma-3n-E4B-it-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/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-GGUF --include "huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q8_0/*" --local-dir ./ +``` + +You can either specify a new local-dir (huihui-ai_Huihui-gemma-3n-E4B-it-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/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ3_M.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ3_M.gguf new file mode 100644 index 0000000..64c7026 --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bc269673469f974e6aa7128cc3b537a141f4540638dcb4f00a5fbca70598db7 +size 3294107648 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ3_XS.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ3_XS.gguf new file mode 100644 index 0000000..40180e9 --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aec38012151f7ee99e2514a3cf3483b48d2514e475964ab628bed457525eda02 +size 3166394368 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ4_NL.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ4_NL.gguf new file mode 100644 index 0000000..a00a433 --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4ea418676b3aca05f5bf7edf86dfedffea9d6139b9e48f3edc8cc016bfdf86e +size 4089993216 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ4_XS.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ4_XS.gguf new file mode 100644 index 0000000..b30fc91 --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4798aedca19326b9d38fdd529d7e0b3008e918a596f41082d581c978694414ff +size 3895023616 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q2_K.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q2_K.gguf new file mode 100644 index 0000000..f8fb884 --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f7bc62c252b5c387849f2671a04c476913037047e39ff12f175e99849600ec4 +size 2757318656 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q2_K_L.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q2_K_L.gguf new file mode 100644 index 0000000..ea7029a --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q2_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50c2fbafc97b0f3bcb8dfd7dc8e8f62e74ac04831fd6d9451be0165ee0aa884b +size 4612249600 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_L.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_L.gguf new file mode 100644 index 0000000..fefcbe3 --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e7fb8fb4e6faf453bdde6b753b3461d77a71ae27697f1e3be2545d333b50e23 +size 3601995776 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_M.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_M.gguf new file mode 100644 index 0000000..7decfc9 --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b7e8f8bd74cc2abec6833f01584ad961c2b548ea46016e886917d567d4e7e4 +size 3440908288 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_S.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_S.gguf new file mode 100644 index 0000000..8ed99bc --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f32c94b82730ef568e5d71fa87866edae30cdbeb9f234415647a8bf8191e975 +size 3251910656 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_XL.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_XL.gguf new file mode 100644 index 0000000..2d97181 --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58bcf322c54f1612c6e4add5271e55baf7181a9bc9054e88b28fb5b67a74363c +size 5218375680 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_0.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_0.gguf new file mode 100644 index 0000000..a13d821 --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ae26ec4f6deadee4c2648ea8fda85adacefccf4ec5d305a9feb7197068536b8 +size 4093794304 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_1.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_1.gguf new file mode 100644 index 0000000..cb6d590 --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f9c07aa01f884fd7c28ee39c1afe00720c1ed48ef2ea4322fa190daec55d257 +size 4477638656 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_K_L.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_K_L.gguf new file mode 100644 index 0000000..5750781 --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:528473be2cb9a09e4d9f4844f224860e75a1bfd450cfabe017d277d11e1e44cf +size 5541492736 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_K_M.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_K_M.gguf new file mode 100644 index 0000000..58b06fe --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf3f41f5d90c30777054d5cc23c10a31f08a833e774a014733f918b5c73f2265 +size 4237064192 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_K_S.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_K_S.gguf new file mode 100644 index 0000000..5b76c9d --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33771ed0dc774badaed690f13230fadd475a2dc2b2f45cb58333ec794b8ba052 +size 4102707200 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q5_K_L.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q5_K_L.gguf new file mode 100644 index 0000000..de10876 --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q5_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85ca58bc53c2d7ed826c1bb98a947ebb46fce50fba1c2c8929a9c854db59dfed +size 5958825984 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q5_K_M.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q5_K_M.gguf new file mode 100644 index 0000000..374ee67 --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1becd929c03776a8b75f6e5cdac8cca02ac2154c4ad1921f872944478bb7e9ac +size 4947998720 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q5_K_S.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q5_K_S.gguf new file mode 100644 index 0000000..4df751c --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a4d2a838a250e6809adf997234bf4cc51651cd891191ead0f058b5e40df407a +size 4869871616 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q6_K.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q6_K.gguf new file mode 100644 index 0000000..e1e7c7a --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23ee86ce074b772639d21b7e56e0102cf2f4196de10955843795311ebf16b32b +size 5703366656 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q6_K_L.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q6_K_L.gguf new file mode 100644 index 0000000..7db7b87 --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q6_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deb5fa3ab2d2377936dc34dbdf17ec86d55a24a09f98200a33978463d6059cb9 +size 6402242560 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q8_0.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q8_0.gguf new file mode 100644 index 0000000..13c879e --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4980dba55c9d9892a99d527a4ebb791f54996abdb93783f8e2d9cbec381ee35d +size 7353292800 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-bf16.gguf b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-bf16.gguf new file mode 100644 index 0000000..e38b6ca --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated-bf16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c00edf1e08c781e07370db0f2f6dc3e81dec7a9920da6d93a268caf33f2d69fb +size 13740103360 diff --git a/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated.imatrix b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated.imatrix new file mode 100644 index 0000000..c2bd13e --- /dev/null +++ b/huihui-ai_Huihui-gemma-3n-E4B-it-abliterated.imatrix @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:313a07754a7c6c200fd90ebdd6789adce66c028ed78c5867008a09ef7e326442 +size 4690533