commit b9a3891db1ed54c38a40cc7a80cc6c89dc590c18 Author: ModelHub XC Date: Thu Aug 6 12:23:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3-CAS-Audit8B-AP-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3534fe8 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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-CAS-Audit8B-AP.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-CAS-Audit8B-AP.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-CAS-Audit8B-AP.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-CAS-Audit8B-AP.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-CAS-Audit8B-AP.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-CAS-Audit8B-AP.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-CAS-Audit8B-AP.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-CAS-Audit8B-AP.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-CAS-Audit8B-AP.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-CAS-Audit8B-AP.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-CAS-Audit8B-AP.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-CAS-Audit8B-AP.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-CAS-Audit8B-AP.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-CAS-Audit8B-AP.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-CAS-Audit8B-AP.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3-CAS-Audit8B-AP.IQ3_M.gguf b/Llama3-CAS-Audit8B-AP.IQ3_M.gguf new file mode 100644 index 0000000..379d7b7 --- /dev/null +++ b/Llama3-CAS-Audit8B-AP.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7de2a663caade405a1dfb766d50776c223f63aad2b0ae66b5e8324f007a1e69c +size 3784823520 diff --git a/Llama3-CAS-Audit8B-AP.IQ3_S.gguf b/Llama3-CAS-Audit8B-AP.IQ3_S.gguf new file mode 100644 index 0000000..1026032 --- /dev/null +++ b/Llama3-CAS-Audit8B-AP.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:488b5b824c35a513948eccf35036d4f01c10e0c7315aa9a33fe93235de6dce77 +size 3682325216 diff --git a/Llama3-CAS-Audit8B-AP.IQ3_XS.gguf b/Llama3-CAS-Audit8B-AP.IQ3_XS.gguf new file mode 100644 index 0000000..061a6ef --- /dev/null +++ b/Llama3-CAS-Audit8B-AP.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9d1c8c5f0ac3aeafbe10170f42887b503015032e918d113c401a438c8eeb3bf +size 3518747360 diff --git a/Llama3-CAS-Audit8B-AP.IQ4_XS.gguf b/Llama3-CAS-Audit8B-AP.IQ4_XS.gguf new file mode 100644 index 0000000..a41e8cd --- /dev/null +++ b/Llama3-CAS-Audit8B-AP.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3f1a08c96145cbbd6a5e7c93a1325174a334de649d88433f484d739a271adad +size 4484362976 diff --git a/Llama3-CAS-Audit8B-AP.Q2_K.gguf b/Llama3-CAS-Audit8B-AP.Q2_K.gguf new file mode 100644 index 0000000..d7eee51 --- /dev/null +++ b/Llama3-CAS-Audit8B-AP.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e850e2233f5192332dc0ae1bccae607abcfc83829955735d5875fe73963e5b2 +size 3179131616 diff --git a/Llama3-CAS-Audit8B-AP.Q3_K_L.gguf b/Llama3-CAS-Audit8B-AP.Q3_K_L.gguf new file mode 100644 index 0000000..15dab86 --- /dev/null +++ b/Llama3-CAS-Audit8B-AP.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86f0be760169016822c9218e6d0707607b340f7dde00afc99bb844a60a739aaf +size 4321956576 diff --git a/Llama3-CAS-Audit8B-AP.Q3_K_M.gguf b/Llama3-CAS-Audit8B-AP.Q3_K_M.gguf new file mode 100644 index 0000000..768304d --- /dev/null +++ b/Llama3-CAS-Audit8B-AP.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20f062d0f940c6f8160da5e154f63a5b110a0277f7d1249421c4b1a7559738d6 +size 4018918112 diff --git a/Llama3-CAS-Audit8B-AP.Q3_K_S.gguf b/Llama3-CAS-Audit8B-AP.Q3_K_S.gguf new file mode 100644 index 0000000..e209479 --- /dev/null +++ b/Llama3-CAS-Audit8B-AP.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aec3faaefaa9ba804356e2746958bddcea180a6dc192a706bd38e505b0bf3d67 +size 3664499424 diff --git a/Llama3-CAS-Audit8B-AP.Q4_K_M.gguf b/Llama3-CAS-Audit8B-AP.Q4_K_M.gguf new file mode 100644 index 0000000..e1862c0 --- /dev/null +++ b/Llama3-CAS-Audit8B-AP.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a66fa81c930020fe619d655c03a0fa1084e6d1df45429ae11f26acb0cf9913ef +size 4920734432 diff --git a/Llama3-CAS-Audit8B-AP.Q4_K_S.gguf b/Llama3-CAS-Audit8B-AP.Q4_K_S.gguf new file mode 100644 index 0000000..065021b --- /dev/null +++ b/Llama3-CAS-Audit8B-AP.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6f2c6648d21f82be5e71adb6ad28757b670d2756000cc5f9ea8e7d9e38161b0 +size 4692669152 diff --git a/Llama3-CAS-Audit8B-AP.Q5_K_M.gguf b/Llama3-CAS-Audit8B-AP.Q5_K_M.gguf new file mode 100644 index 0000000..1eaa7f0 --- /dev/null +++ b/Llama3-CAS-Audit8B-AP.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a172ab9105cca02bbb825c0097f1ce3dea0b58800c377ab6cae161263b07073 +size 5732987616 diff --git a/Llama3-CAS-Audit8B-AP.Q5_K_S.gguf b/Llama3-CAS-Audit8B-AP.Q5_K_S.gguf new file mode 100644 index 0000000..530ae2f --- /dev/null +++ b/Llama3-CAS-Audit8B-AP.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53c3338196483da36251afb86d6bf930b38729c0d5bdd282f8fc1108079b0278 +size 5599294176 diff --git a/Llama3-CAS-Audit8B-AP.Q6_K.gguf b/Llama3-CAS-Audit8B-AP.Q6_K.gguf new file mode 100644 index 0000000..7978085 --- /dev/null +++ b/Llama3-CAS-Audit8B-AP.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61f8a656e6a6917bf8daf0d47b4a4df9b7371860679a6db3730d796cbd032898 +size 6596006624 diff --git a/Llama3-CAS-Audit8B-AP.Q8_0.gguf b/Llama3-CAS-Audit8B-AP.Q8_0.gguf new file mode 100644 index 0000000..ab5d867 --- /dev/null +++ b/Llama3-CAS-Audit8B-AP.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba4db7be3657b620741fd4e39e5500ee26e151394acf8db875dd1d15e2992c00 +size 8540771040 diff --git a/Llama3-CAS-Audit8B-AP.f16.gguf b/Llama3-CAS-Audit8B-AP.f16.gguf new file mode 100644 index 0000000..d07cc69 --- /dev/null +++ b/Llama3-CAS-Audit8B-AP.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c33db920f4c03a1ff6acb988976cb46f5bd62179f88ed86cc627a7c42721b5bb +size 16068891360 diff --git a/README.md b/README.md new file mode 100644 index 0000000..6d978c9 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: jamesohe/Llama3-CAS-Audit8B-AP +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/jamesohe/Llama3-CAS-Audit8B-AP + + +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/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-CAS-Audit8B-AP-GGUF/resolve/main/Llama3-CAS-Audit8B-AP.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. + +