commit 3f4d8f44df832dbc2e4ee7dba36f801880b5b721 Author: ModelHub XC Date: Mon Oct 19 12:40:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/wazuh-llama-3.1-8b-assistant-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..35f844a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,46 @@ +*.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 +wazuh-llama-3.1-8b-assistant.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +wazuh-llama-3.1-8b-assistant.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +wazuh-llama-3.1-8b-assistant.f16.gguf filter=lfs diff=lfs merge=lfs -text +wazuh-llama-3.1-8b-assistant.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +wazuh-llama-3.1-8b-assistant.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +wazuh-llama-3.1-8b-assistant.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +wazuh-llama-3.1-8b-assistant.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +wazuh-llama-3.1-8b-assistant.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +wazuh-llama-3.1-8b-assistant.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +wazuh-llama-3.1-8b-assistant.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +wazuh-llama-3.1-8b-assistant.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6fb9d33 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: pyToshka/wazuh-llama-3.1-8b-assistant +language: +- en +- ru +- es +library_name: transformers +license: llama3.1 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- cybersecurity +- security-analysis +- wazuh +- threat-detection +- llama +- peft +- lora +--- +## About + + + + + + + + + +static quants of https://huggingface.co/pyToshka/wazuh-llama-3.1-8b-assistant + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#wazuh-llama-3.1-8b-assistant-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/wazuh-llama-3.1-8b-assistant-GGUF/resolve/main/wazuh-llama-3.1-8b-assistant.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/wazuh-llama-3.1-8b-assistant-GGUF/resolve/main/wazuh-llama-3.1-8b-assistant.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/wazuh-llama-3.1-8b-assistant-GGUF/resolve/main/wazuh-llama-3.1-8b-assistant.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/wazuh-llama-3.1-8b-assistant-GGUF/resolve/main/wazuh-llama-3.1-8b-assistant.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/wazuh-llama-3.1-8b-assistant-GGUF/resolve/main/wazuh-llama-3.1-8b-assistant.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/wazuh-llama-3.1-8b-assistant-GGUF/resolve/main/wazuh-llama-3.1-8b-assistant.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/wazuh-llama-3.1-8b-assistant-GGUF/resolve/main/wazuh-llama-3.1-8b-assistant.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/wazuh-llama-3.1-8b-assistant-GGUF/resolve/main/wazuh-llama-3.1-8b-assistant.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/wazuh-llama-3.1-8b-assistant-GGUF/resolve/main/wazuh-llama-3.1-8b-assistant.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/wazuh-llama-3.1-8b-assistant-GGUF/resolve/main/wazuh-llama-3.1-8b-assistant.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/wazuh-llama-3.1-8b-assistant-GGUF/resolve/main/wazuh-llama-3.1-8b-assistant.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/wazuh-llama-3.1-8b-assistant-GGUF/resolve/main/wazuh-llama-3.1-8b-assistant.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. + + diff --git a/wazuh-llama-3.1-8b-assistant.IQ4_XS.gguf b/wazuh-llama-3.1-8b-assistant.IQ4_XS.gguf new file mode 100644 index 0000000..cd4e317 --- /dev/null +++ b/wazuh-llama-3.1-8b-assistant.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b23f8d5c5878b1cfd6228a86a85c645828e56b6295fbdd2a6075a779285c9dc1 +size 4484368384 diff --git a/wazuh-llama-3.1-8b-assistant.Q2_K.gguf b/wazuh-llama-3.1-8b-assistant.Q2_K.gguf new file mode 100644 index 0000000..c1ca46d --- /dev/null +++ b/wazuh-llama-3.1-8b-assistant.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f6e762ff998d85cb1236c5acbc0beb135432308fea5ca660ecc782ba15aad80 +size 3179137024 diff --git a/wazuh-llama-3.1-8b-assistant.Q3_K_L.gguf b/wazuh-llama-3.1-8b-assistant.Q3_K_L.gguf new file mode 100644 index 0000000..7b1b2af --- /dev/null +++ b/wazuh-llama-3.1-8b-assistant.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3199db1fa34d6dd4cf9404743bb0865c3a0317efc74a5fe2a3bffe4c6268d958 +size 4321961984 diff --git a/wazuh-llama-3.1-8b-assistant.Q3_K_M.gguf b/wazuh-llama-3.1-8b-assistant.Q3_K_M.gguf new file mode 100644 index 0000000..d948085 --- /dev/null +++ b/wazuh-llama-3.1-8b-assistant.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df13535d0be593c7ffa12626f0c4d4d128a41a3d18f39fba6735473c4beced76 +size 4018923520 diff --git a/wazuh-llama-3.1-8b-assistant.Q3_K_S.gguf b/wazuh-llama-3.1-8b-assistant.Q3_K_S.gguf new file mode 100644 index 0000000..dbce0e0 --- /dev/null +++ b/wazuh-llama-3.1-8b-assistant.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1266bc977b08873074c726bcdc53dac49669c670013f69c77271b867e5e7cce1 +size 3664504832 diff --git a/wazuh-llama-3.1-8b-assistant.Q4_K_M.gguf b/wazuh-llama-3.1-8b-assistant.Q4_K_M.gguf new file mode 100644 index 0000000..f95c25c --- /dev/null +++ b/wazuh-llama-3.1-8b-assistant.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95d2c635eb3a62c33f1d430091c2f408f61301e291d85483b7188936be67beae +size 4920739840 diff --git a/wazuh-llama-3.1-8b-assistant.Q4_K_S.gguf b/wazuh-llama-3.1-8b-assistant.Q4_K_S.gguf new file mode 100644 index 0000000..3e843f6 --- /dev/null +++ b/wazuh-llama-3.1-8b-assistant.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea457725dd24361abb43916badb4367d73fc9ce386fab0cfb0f671d475c1d5cb +size 4692674560 diff --git a/wazuh-llama-3.1-8b-assistant.Q5_K_M.gguf b/wazuh-llama-3.1-8b-assistant.Q5_K_M.gguf new file mode 100644 index 0000000..24b0782 --- /dev/null +++ b/wazuh-llama-3.1-8b-assistant.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:515f4f393e6e246f67c0efc0c4272e0ef2ad08a6bfb9049cc7093933297e305c +size 5732993024 diff --git a/wazuh-llama-3.1-8b-assistant.Q5_K_S.gguf b/wazuh-llama-3.1-8b-assistant.Q5_K_S.gguf new file mode 100644 index 0000000..4d1c16b --- /dev/null +++ b/wazuh-llama-3.1-8b-assistant.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:548cf0f4c3e64143956f2584a487a09d0f08abd38c9b800243fee229f08d8323 +size 5599299584 diff --git a/wazuh-llama-3.1-8b-assistant.Q6_K.gguf b/wazuh-llama-3.1-8b-assistant.Q6_K.gguf new file mode 100644 index 0000000..3ca6c54 --- /dev/null +++ b/wazuh-llama-3.1-8b-assistant.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9031ba27eda79ae39e5677d06394551554570f034ec6467b58f7d3260e824e7d +size 6596012032 diff --git a/wazuh-llama-3.1-8b-assistant.Q8_0.gguf b/wazuh-llama-3.1-8b-assistant.Q8_0.gguf new file mode 100644 index 0000000..78e07b1 --- /dev/null +++ b/wazuh-llama-3.1-8b-assistant.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7181c88569c97b90ed864d824fbaadf3fcd34065f1b7cf43bf4d9a608c4657d7 +size 8540776448 diff --git a/wazuh-llama-3.1-8b-assistant.f16.gguf b/wazuh-llama-3.1-8b-assistant.f16.gguf new file mode 100644 index 0000000..29322bb --- /dev/null +++ b/wazuh-llama-3.1-8b-assistant.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93f8ba222d0ecbc62316dd94074d9cd1b5ff7ca3f62163a82c7f044dd88d804e +size 16068896768