commit bf684fb1c815d948c199184cb5a55828cddc52af Author: ModelHub XC Date: Mon May 18 16:45:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-Fluxed-uncensored-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f549af0 --- /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-3.2-3B-Fluxed-uncensored.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Fluxed-uncensored.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Fluxed-uncensored.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Fluxed-uncensored.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Fluxed-uncensored.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Fluxed-uncensored.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Fluxed-uncensored.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Fluxed-uncensored.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Fluxed-uncensored.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Fluxed-uncensored.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Fluxed-uncensored.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-Fluxed-uncensored.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Fluxed-uncensored.IQ4_XS.gguf b/Llama-3.2-3B-Fluxed-uncensored.IQ4_XS.gguf new file mode 100644 index 0000000..d48d6a8 --- /dev/null +++ b/Llama-3.2-3B-Fluxed-uncensored.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a643d8bf2e9f376029a2aaefb80c5af48dc1b3807077d4ff15f5a1d83ae657a2 +size 1840908064 diff --git a/Llama-3.2-3B-Fluxed-uncensored.Q2_K.gguf b/Llama-3.2-3B-Fluxed-uncensored.Q2_K.gguf new file mode 100644 index 0000000..6174d37 --- /dev/null +++ b/Llama-3.2-3B-Fluxed-uncensored.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a23210af6de1ede71f0c1d847fababd4d5330df48d1f417b60d2f8cc0dae89c2 +size 1363937056 diff --git a/Llama-3.2-3B-Fluxed-uncensored.Q3_K_L.gguf b/Llama-3.2-3B-Fluxed-uncensored.Q3_K_L.gguf new file mode 100644 index 0000000..a07b68e --- /dev/null +++ b/Llama-3.2-3B-Fluxed-uncensored.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a3d1c0f7d228a52fb22d6a8f1c0476e56e1e4117b1cbd0569ef00af1c76e49d +size 1815349024 diff --git a/Llama-3.2-3B-Fluxed-uncensored.Q3_K_M.gguf b/Llama-3.2-3B-Fluxed-uncensored.Q3_K_M.gguf new file mode 100644 index 0000000..7942dae --- /dev/null +++ b/Llama-3.2-3B-Fluxed-uncensored.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a24130ee88d32b25d20d46b4332d9a7d63208186312d9754a181d182c097e14 +size 1687160608 diff --git a/Llama-3.2-3B-Fluxed-uncensored.Q3_K_S.gguf b/Llama-3.2-3B-Fluxed-uncensored.Q3_K_S.gguf new file mode 100644 index 0000000..e8cb75d --- /dev/null +++ b/Llama-3.2-3B-Fluxed-uncensored.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ee67589753bd0f3479092c5269bda1cdd2ca8bc21cb762ccd9d60d939b38471 +size 1542850336 diff --git a/Llama-3.2-3B-Fluxed-uncensored.Q4_K_M.gguf b/Llama-3.2-3B-Fluxed-uncensored.Q4_K_M.gguf new file mode 100644 index 0000000..a7f28b4 --- /dev/null +++ b/Llama-3.2-3B-Fluxed-uncensored.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e658aad408b1661f3408ff7caad1df9808d4ddd65cf5c0e7f2b8bb28d06e1c3 +size 2019378976 diff --git a/Llama-3.2-3B-Fluxed-uncensored.Q4_K_S.gguf b/Llama-3.2-3B-Fluxed-uncensored.Q4_K_S.gguf new file mode 100644 index 0000000..417173e --- /dev/null +++ b/Llama-3.2-3B-Fluxed-uncensored.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:468c48ef006a6b8a6dfd75b5387d866e1441548e7551d148c8f5b029230d3cd0 +size 1928202016 diff --git a/Llama-3.2-3B-Fluxed-uncensored.Q5_K_M.gguf b/Llama-3.2-3B-Fluxed-uncensored.Q5_K_M.gguf new file mode 100644 index 0000000..b2d5d97 --- /dev/null +++ b/Llama-3.2-3B-Fluxed-uncensored.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6c2e6ea25fcb6fcad0ea1caa13698a94fca69148ffd060132ca03890be7b532 +size 2322155296 diff --git a/Llama-3.2-3B-Fluxed-uncensored.Q5_K_S.gguf b/Llama-3.2-3B-Fluxed-uncensored.Q5_K_S.gguf new file mode 100644 index 0000000..b353616 --- /dev/null +++ b/Llama-3.2-3B-Fluxed-uncensored.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8f2e5090e4d0fb3eb9b4092b52cc09678aeeb7c2f3a5a0ddead5ef0b2e0eb85 +size 2269513504 diff --git a/Llama-3.2-3B-Fluxed-uncensored.Q6_K.gguf b/Llama-3.2-3B-Fluxed-uncensored.Q6_K.gguf new file mode 100644 index 0000000..ca55877 --- /dev/null +++ b/Llama-3.2-3B-Fluxed-uncensored.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a054062f494e5723a54147351e93e42f83b90b359f6d8ce032a8635c193d62d2 +size 2643855136 diff --git a/Llama-3.2-3B-Fluxed-uncensored.Q8_0.gguf b/Llama-3.2-3B-Fluxed-uncensored.Q8_0.gguf new file mode 100644 index 0000000..9db294e --- /dev/null +++ b/Llama-3.2-3B-Fluxed-uncensored.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d3455bd4d7d5c58842b2c4d68df3f1b71b277809579662d533be3603d1e5487 +size 3421900576 diff --git a/Llama-3.2-3B-Fluxed-uncensored.f16.gguf b/Llama-3.2-3B-Fluxed-uncensored.f16.gguf new file mode 100644 index 0000000..91bbad2 --- /dev/null +++ b/Llama-3.2-3B-Fluxed-uncensored.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5ca96347555f1af97d0ca7a8347fd9d617c41074fdc7bd534e8ae747e6388f3 +size 6433689376 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7135388 --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: VincentGOURBIN/Llama-3.2-3B-Fluxed-uncensored +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +--- +## About + + + + + + +static quants of https://huggingface.co/VincentGOURBIN/Llama-3.2-3B-Fluxed-uncensored + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama-3.2-3B-Fluxed-uncensored-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## 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-Fluxed-uncensored-GGUF/resolve/main/Llama-3.2-3B-Fluxed-uncensored.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Fluxed-uncensored-GGUF/resolve/main/Llama-3.2-3B-Fluxed-uncensored.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Fluxed-uncensored-GGUF/resolve/main/Llama-3.2-3B-Fluxed-uncensored.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Fluxed-uncensored-GGUF/resolve/main/Llama-3.2-3B-Fluxed-uncensored.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Fluxed-uncensored-GGUF/resolve/main/Llama-3.2-3B-Fluxed-uncensored.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Fluxed-uncensored-GGUF/resolve/main/Llama-3.2-3B-Fluxed-uncensored.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Fluxed-uncensored-GGUF/resolve/main/Llama-3.2-3B-Fluxed-uncensored.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Fluxed-uncensored-GGUF/resolve/main/Llama-3.2-3B-Fluxed-uncensored.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Fluxed-uncensored-GGUF/resolve/main/Llama-3.2-3B-Fluxed-uncensored.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Fluxed-uncensored-GGUF/resolve/main/Llama-3.2-3B-Fluxed-uncensored.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Fluxed-uncensored-GGUF/resolve/main/Llama-3.2-3B-Fluxed-uncensored.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-Fluxed-uncensored-GGUF/resolve/main/Llama-3.2-3B-Fluxed-uncensored.f16.gguf) | f16 | 6.5 | 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. + +