commit 137274d1c3605f758a6d1de0a5fc864d2f9c74d3 Author: ModelHub XC Date: Tue Jun 23 09:32:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3-Toxic-8B-Float16-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..88efb1d --- /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 +Llama3-Toxic-8B-Float16.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Toxic-8B-Float16.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Toxic-8B-Float16.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Toxic-8B-Float16.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Toxic-8B-Float16.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Toxic-8B-Float16.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Toxic-8B-Float16.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Toxic-8B-Float16.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Toxic-8B-Float16.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Toxic-8B-Float16.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Toxic-8B-Float16.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Toxic-8B-Float16.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3-Toxic-8B-Float16.IQ4_XS.gguf b/Llama3-Toxic-8B-Float16.IQ4_XS.gguf new file mode 100644 index 0000000..5c3f3a9 --- /dev/null +++ b/Llama3-Toxic-8B-Float16.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa2938b73607699c016ea7a8d0ac96713d741cb44103036978892b22f77bffe9 +size 4484363328 diff --git a/Llama3-Toxic-8B-Float16.Q2_K.gguf b/Llama3-Toxic-8B-Float16.Q2_K.gguf new file mode 100644 index 0000000..1014163 --- /dev/null +++ b/Llama3-Toxic-8B-Float16.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d984e488c6f0b9875e5a50c577f4f89669dffc7bd2570d14caaca4f47b285408 +size 3179131968 diff --git a/Llama3-Toxic-8B-Float16.Q3_K_L.gguf b/Llama3-Toxic-8B-Float16.Q3_K_L.gguf new file mode 100644 index 0000000..7c6dc42 --- /dev/null +++ b/Llama3-Toxic-8B-Float16.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a5ec46aae78d8ab5c51d0ac6720b850fe699a93078a70b04c74c3f58cfc90b9 +size 4321956928 diff --git a/Llama3-Toxic-8B-Float16.Q3_K_M.gguf b/Llama3-Toxic-8B-Float16.Q3_K_M.gguf new file mode 100644 index 0000000..0ec4d7c --- /dev/null +++ b/Llama3-Toxic-8B-Float16.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:470de7e703012cb3772f9bce082c7accd189334bf0789fe76c752601b267985a +size 4018918464 diff --git a/Llama3-Toxic-8B-Float16.Q3_K_S.gguf b/Llama3-Toxic-8B-Float16.Q3_K_S.gguf new file mode 100644 index 0000000..7123247 --- /dev/null +++ b/Llama3-Toxic-8B-Float16.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f00fd2aa84de5d90f6c43a2e5c4e197c6784e0a420b545c22a2a4c2af9aec3ad +size 3664499776 diff --git a/Llama3-Toxic-8B-Float16.Q4_K_M.gguf b/Llama3-Toxic-8B-Float16.Q4_K_M.gguf new file mode 100644 index 0000000..38073ae --- /dev/null +++ b/Llama3-Toxic-8B-Float16.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26ec1a67fe5065bbd4242900cd1d1a6fad299291aab73655daa3a9ad764e8c7a +size 4920734784 diff --git a/Llama3-Toxic-8B-Float16.Q4_K_S.gguf b/Llama3-Toxic-8B-Float16.Q4_K_S.gguf new file mode 100644 index 0000000..86cec56 --- /dev/null +++ b/Llama3-Toxic-8B-Float16.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c935470e98d24d4392c8920149e9f2bf0d897499790257b0617f4b212d954659 +size 4692669504 diff --git a/Llama3-Toxic-8B-Float16.Q5_K_M.gguf b/Llama3-Toxic-8B-Float16.Q5_K_M.gguf new file mode 100644 index 0000000..7572098 --- /dev/null +++ b/Llama3-Toxic-8B-Float16.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5aeccd6dfd2548246846fe7f52c70adb09ab2c0dd6b8424ce4ab23b8bf654eee +size 5732987968 diff --git a/Llama3-Toxic-8B-Float16.Q5_K_S.gguf b/Llama3-Toxic-8B-Float16.Q5_K_S.gguf new file mode 100644 index 0000000..b692975 --- /dev/null +++ b/Llama3-Toxic-8B-Float16.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05fb0d41bebb48fc4f0f129d4fe1937bba9087ad7afa05d7a543569b6c63859d +size 5599294528 diff --git a/Llama3-Toxic-8B-Float16.Q6_K.gguf b/Llama3-Toxic-8B-Float16.Q6_K.gguf new file mode 100644 index 0000000..661873c --- /dev/null +++ b/Llama3-Toxic-8B-Float16.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fde9060df634263b5bde6e1690329429a073e72bd1cfd934a3d2f9c4b4541354 +size 6596006976 diff --git a/Llama3-Toxic-8B-Float16.Q8_0.gguf b/Llama3-Toxic-8B-Float16.Q8_0.gguf new file mode 100644 index 0000000..ecf9aa6 --- /dev/null +++ b/Llama3-Toxic-8B-Float16.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c1629a6aa70454338d5d6cad93feb8b68fa2b4788f0ab2b7273dbfec02f0203 +size 8540771392 diff --git a/Llama3-Toxic-8B-Float16.f16.gguf b/Llama3-Toxic-8B-Float16.f16.gguf new file mode 100644 index 0000000..750719c --- /dev/null +++ b/Llama3-Toxic-8B-Float16.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ef1e2f7242b1ecce8e5c92e950ebaa217f1266025d4e9f1cf60e76c62ddc46 +size 16068891712 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7fabaea --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: theminji/Llama3-Toxic-8B-Float16 +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/theminji/Llama3-Toxic-8B-Float16 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama3-Toxic-8B-Float16-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/Llama3-Toxic-8B-Float16-GGUF/resolve/main/Llama3-Toxic-8B-Float16.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Toxic-8B-Float16-GGUF/resolve/main/Llama3-Toxic-8B-Float16.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Toxic-8B-Float16-GGUF/resolve/main/Llama3-Toxic-8B-Float16.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Toxic-8B-Float16-GGUF/resolve/main/Llama3-Toxic-8B-Float16.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Toxic-8B-Float16-GGUF/resolve/main/Llama3-Toxic-8B-Float16.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Toxic-8B-Float16-GGUF/resolve/main/Llama3-Toxic-8B-Float16.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Toxic-8B-Float16-GGUF/resolve/main/Llama3-Toxic-8B-Float16.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Toxic-8B-Float16-GGUF/resolve/main/Llama3-Toxic-8B-Float16.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Toxic-8B-Float16-GGUF/resolve/main/Llama3-Toxic-8B-Float16.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Toxic-8B-Float16-GGUF/resolve/main/Llama3-Toxic-8B-Float16.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Toxic-8B-Float16-GGUF/resolve/main/Llama3-Toxic-8B-Float16.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Toxic-8B-Float16-GGUF/resolve/main/Llama3-Toxic-8B-Float16.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. 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. + +