commit 8551f27f0e93b06c81570b43f6c8295b13d3c77a Author: ModelHub XC Date: Sat Apr 11 23:17:00 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/AZERG-MixTask-Mistral-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4c947a6 --- /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 +AZERG-MixTask-Mistral.f16.gguf filter=lfs diff=lfs merge=lfs -text +AZERG-MixTask-Mistral.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AZERG-MixTask-Mistral.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +AZERG-MixTask-Mistral.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +AZERG-MixTask-Mistral.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +AZERG-MixTask-Mistral.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AZERG-MixTask-Mistral.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AZERG-MixTask-Mistral.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +AZERG-MixTask-Mistral.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AZERG-MixTask-Mistral.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +AZERG-MixTask-Mistral.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +AZERG-MixTask-Mistral.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/AZERG-MixTask-Mistral.IQ4_XS.gguf b/AZERG-MixTask-Mistral.IQ4_XS.gguf new file mode 100644 index 0000000..5557bdb --- /dev/null +++ b/AZERG-MixTask-Mistral.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad1dc2e2f7143d18873a156100fc6cd1b67e1cc0d8edd3cc2522f1912febb5a0 +size 3948667904 diff --git a/AZERG-MixTask-Mistral.Q2_K.gguf b/AZERG-MixTask-Mistral.Q2_K.gguf new file mode 100644 index 0000000..fd848ff --- /dev/null +++ b/AZERG-MixTask-Mistral.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea20b1f1d2748956fd4b6523852698fcda53d8ae893300c4e3adb8785190c893 +size 2722882560 diff --git a/AZERG-MixTask-Mistral.Q3_K_L.gguf b/AZERG-MixTask-Mistral.Q3_K_L.gguf new file mode 100644 index 0000000..96308f4 --- /dev/null +++ b/AZERG-MixTask-Mistral.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:244fa433091785247ea1226a470a23bf7ab771d40a0681a8255f7be5a395cfc3 +size 3825984512 diff --git a/AZERG-MixTask-Mistral.Q3_K_M.gguf b/AZERG-MixTask-Mistral.Q3_K_M.gguf new file mode 100644 index 0000000..ee27a1d --- /dev/null +++ b/AZERG-MixTask-Mistral.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d84e08f0639d6de0f8e4893e7c140cecc6640d91025e40102fdc8881759c24b2 +size 3522946048 diff --git a/AZERG-MixTask-Mistral.Q3_K_S.gguf b/AZERG-MixTask-Mistral.Q3_K_S.gguf new file mode 100644 index 0000000..ac2395f --- /dev/null +++ b/AZERG-MixTask-Mistral.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20ac451140c2adc1d025fbb1221ef957d4d9f6f66d92919ea5c8908572a9a06c +size 3168527360 diff --git a/AZERG-MixTask-Mistral.Q4_K_M.gguf b/AZERG-MixTask-Mistral.Q4_K_M.gguf new file mode 100644 index 0000000..8431fc6 --- /dev/null +++ b/AZERG-MixTask-Mistral.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb008f44b1733f6093fcf2ee6990f256968270aa07d26c5647335efe2132d7f8 +size 4372816896 diff --git a/AZERG-MixTask-Mistral.Q4_K_S.gguf b/AZERG-MixTask-Mistral.Q4_K_S.gguf new file mode 100644 index 0000000..71dc3bf --- /dev/null +++ b/AZERG-MixTask-Mistral.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3cf4ca0b00965e7ca0bdad43d2521dc98a33c6fb088f3c28d1ee9ce5c371435 +size 4144751616 diff --git a/AZERG-MixTask-Mistral.Q5_K_M.gguf b/AZERG-MixTask-Mistral.Q5_K_M.gguf new file mode 100644 index 0000000..6a8db9d --- /dev/null +++ b/AZERG-MixTask-Mistral.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4a61f06c16d498dfb75eec069cb204e4e77cecdce42f2efd35e1b75af436ba9 +size 5136180224 diff --git a/AZERG-MixTask-Mistral.Q5_K_S.gguf b/AZERG-MixTask-Mistral.Q5_K_S.gguf new file mode 100644 index 0000000..bf77864 --- /dev/null +++ b/AZERG-MixTask-Mistral.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc6e42382679e6b63ef7c84f8a889419db16c488e0eb0db971a3e40ff7aed553 +size 5002486784 diff --git a/AZERG-MixTask-Mistral.Q6_K.gguf b/AZERG-MixTask-Mistral.Q6_K.gguf new file mode 100644 index 0000000..f8d19c9 --- /dev/null +++ b/AZERG-MixTask-Mistral.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54286b06b8d3fbb831c07f3f10fb1b54d44b22ed501e60e3c55a105ac81fc4e6 +size 5947253760 diff --git a/AZERG-MixTask-Mistral.Q8_0.gguf b/AZERG-MixTask-Mistral.Q8_0.gguf new file mode 100644 index 0000000..f3e1e37 --- /dev/null +++ b/AZERG-MixTask-Mistral.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4100200010bb2a2b4eabe5f69b8a055f19f802dc91fdc31245d783fce07e62d5 +size 7702569984 diff --git a/AZERG-MixTask-Mistral.f16.gguf b/AZERG-MixTask-Mistral.f16.gguf new file mode 100644 index 0000000..10d9c79 --- /dev/null +++ b/AZERG-MixTask-Mistral.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32492a414aca0a9e782887cd73018e17c7839a604236b2be0057ace6065972c3 +size 14497342464 diff --git a/README.md b/README.md new file mode 100644 index 0000000..f6bb29b --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: QCRI/AZERG-MixTask-Mistral +datasets: +- QCRI/AZERG-Dataset +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- STIX standard +- threat intelligence +- MITRE ATT&CK +--- +## About + + + + + + + + + +static quants of https://huggingface.co/QCRI/AZERG-MixTask-Mistral + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#AZERG-MixTask-Mistral-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/AZERG-MixTask-Mistral-GGUF/resolve/main/AZERG-MixTask-Mistral.Q2_K.gguf) | Q2_K | 2.8 | | +| [GGUF](https://huggingface.co/mradermacher/AZERG-MixTask-Mistral-GGUF/resolve/main/AZERG-MixTask-Mistral.Q3_K_S.gguf) | Q3_K_S | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/AZERG-MixTask-Mistral-GGUF/resolve/main/AZERG-MixTask-Mistral.Q3_K_M.gguf) | Q3_K_M | 3.6 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/AZERG-MixTask-Mistral-GGUF/resolve/main/AZERG-MixTask-Mistral.Q3_K_L.gguf) | Q3_K_L | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/AZERG-MixTask-Mistral-GGUF/resolve/main/AZERG-MixTask-Mistral.IQ4_XS.gguf) | IQ4_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/AZERG-MixTask-Mistral-GGUF/resolve/main/AZERG-MixTask-Mistral.Q4_K_S.gguf) | Q4_K_S | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AZERG-MixTask-Mistral-GGUF/resolve/main/AZERG-MixTask-Mistral.Q4_K_M.gguf) | Q4_K_M | 4.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/AZERG-MixTask-Mistral-GGUF/resolve/main/AZERG-MixTask-Mistral.Q5_K_S.gguf) | Q5_K_S | 5.1 | | +| [GGUF](https://huggingface.co/mradermacher/AZERG-MixTask-Mistral-GGUF/resolve/main/AZERG-MixTask-Mistral.Q5_K_M.gguf) | Q5_K_M | 5.2 | | +| [GGUF](https://huggingface.co/mradermacher/AZERG-MixTask-Mistral-GGUF/resolve/main/AZERG-MixTask-Mistral.Q6_K.gguf) | Q6_K | 6.0 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/AZERG-MixTask-Mistral-GGUF/resolve/main/AZERG-MixTask-Mistral.Q8_0.gguf) | Q8_0 | 7.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/AZERG-MixTask-Mistral-GGUF/resolve/main/AZERG-MixTask-Mistral.f16.gguf) | f16 | 14.6 | 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. + +