commit 0d3035930f94ec304e0f42d2d3eef632b0d917f0 Author: ModelHub XC Date: Thu May 21 01:40:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-8B-abliterated-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e68c936 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +Llama-3-8B-abliterated.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-abliterated.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-abliterated.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-abliterated.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-abliterated.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-abliterated.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-abliterated.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-abliterated.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-abliterated.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-abliterated.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-abliterated.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-8B-abliterated.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-8B-abliterated.IQ4_XS.gguf b/Llama-3-8B-abliterated.IQ4_XS.gguf new file mode 100644 index 0000000..34010c4 --- /dev/null +++ b/Llama-3-8B-abliterated.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68f2fdaea8753cf5c82a5773b9b812652948774804f8ebc3c8007a5161c04bba +size 4484363936 diff --git a/Llama-3-8B-abliterated.Q2_K.gguf b/Llama-3-8B-abliterated.Q2_K.gguf new file mode 100644 index 0000000..7bb470e --- /dev/null +++ b/Llama-3-8B-abliterated.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e301adb3f4c16e8debd95da67b0f7d9cfc266dbc4fa6998bd2f1bb7a92840662 +size 3179132576 diff --git a/Llama-3-8B-abliterated.Q3_K_L.gguf b/Llama-3-8B-abliterated.Q3_K_L.gguf new file mode 100644 index 0000000..d2f7b26 --- /dev/null +++ b/Llama-3-8B-abliterated.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d99d314469f5472cfa9b779ac82ab13e123d4e04faf6cfe8640bea3425a9e19 +size 4321957536 diff --git a/Llama-3-8B-abliterated.Q3_K_M.gguf b/Llama-3-8B-abliterated.Q3_K_M.gguf new file mode 100644 index 0000000..f539b09 --- /dev/null +++ b/Llama-3-8B-abliterated.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb6510e7f72bd500c57c1a664fd3b83217a0e5e4a09e0ec8497cd360aa4e8d86 +size 4018919072 diff --git a/Llama-3-8B-abliterated.Q3_K_S.gguf b/Llama-3-8B-abliterated.Q3_K_S.gguf new file mode 100644 index 0000000..b6c6299 --- /dev/null +++ b/Llama-3-8B-abliterated.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f02b79b4efc8e76b6dc3405e2d6cadcab570537c99534e4783914669fb50735e +size 3664500384 diff --git a/Llama-3-8B-abliterated.Q4_K_M.gguf b/Llama-3-8B-abliterated.Q4_K_M.gguf new file mode 100644 index 0000000..0eee137 --- /dev/null +++ b/Llama-3-8B-abliterated.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17ef9313f68c2107d72a851adb052ae285fbac2fd4dbabf7773208bfc456c494 +size 4920735392 diff --git a/Llama-3-8B-abliterated.Q4_K_S.gguf b/Llama-3-8B-abliterated.Q4_K_S.gguf new file mode 100644 index 0000000..2768c4d --- /dev/null +++ b/Llama-3-8B-abliterated.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f19c5de7ebed25d305ee640ad23c84159aaf8c80f8ef36ca2d41ad119d0df7 +size 4692670112 diff --git a/Llama-3-8B-abliterated.Q5_K_M.gguf b/Llama-3-8B-abliterated.Q5_K_M.gguf new file mode 100644 index 0000000..198258b --- /dev/null +++ b/Llama-3-8B-abliterated.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b24491db0ea5af3a7d1d59b8bd4e15ab9b25e3c915cc399c568d05afe557321 +size 5732988576 diff --git a/Llama-3-8B-abliterated.Q5_K_S.gguf b/Llama-3-8B-abliterated.Q5_K_S.gguf new file mode 100644 index 0000000..29584d7 --- /dev/null +++ b/Llama-3-8B-abliterated.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eecf9d37eece617664577255ea5ba6e60c684d579fe63064c6ae3e3955b8e8a +size 5599295136 diff --git a/Llama-3-8B-abliterated.Q6_K.gguf b/Llama-3-8B-abliterated.Q6_K.gguf new file mode 100644 index 0000000..ab6609d --- /dev/null +++ b/Llama-3-8B-abliterated.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c31d1921de03f591f8095719d6a52acc1cd58c385143ae96024fccd97bde76de +size 6596007584 diff --git a/Llama-3-8B-abliterated.Q8_0.gguf b/Llama-3-8B-abliterated.Q8_0.gguf new file mode 100644 index 0000000..5f54d70 --- /dev/null +++ b/Llama-3-8B-abliterated.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9baab9858fd4663150fa7e15d42a0b66bbf3e4c4b8af908604ee1a6f8fe73335 +size 8540772000 diff --git a/Llama-3-8B-abliterated.f16.gguf b/Llama-3-8B-abliterated.f16.gguf new file mode 100644 index 0000000..8376e14 --- /dev/null +++ b/Llama-3-8B-abliterated.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87fcab320f37948276fab053c786f97714b1623a5cc8498edccc3f17998f67dc +size 16068892320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fc3b0f7 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: adriaflores/Llama-3-8B-abliterated +language: +- en +library_name: transformers +license: llama3 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- abliteration +- uncensored +- mechanistic-interpretability +- llama-3 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/adriaflores/Llama-3-8B-abliterated + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3-8B-abliterated-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3-8B-abliterated-i1-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-3-8B-abliterated-GGUF/resolve/main/Llama-3-8B-abliterated.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-abliterated-GGUF/resolve/main/Llama-3-8B-abliterated.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-abliterated-GGUF/resolve/main/Llama-3-8B-abliterated.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-abliterated-GGUF/resolve/main/Llama-3-8B-abliterated.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-abliterated-GGUF/resolve/main/Llama-3-8B-abliterated.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-abliterated-GGUF/resolve/main/Llama-3-8B-abliterated.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-abliterated-GGUF/resolve/main/Llama-3-8B-abliterated.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-abliterated-GGUF/resolve/main/Llama-3-8B-abliterated.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-abliterated-GGUF/resolve/main/Llama-3-8B-abliterated.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-abliterated-GGUF/resolve/main/Llama-3-8B-abliterated.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-abliterated-GGUF/resolve/main/Llama-3-8B-abliterated.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-abliterated-GGUF/resolve/main/Llama-3-8B-abliterated.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | + +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. + +