commit 4f0cb2e2237523fed77899f9225df7f7b233245e Author: ModelHub XC Date: Fri Jun 12 02:02:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3.1-8B-AI4PRIVACY-16bit-merged-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0cfb18d --- /dev/null +++ b/.gitattributes @@ -0,0 +1,44 @@ +*.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 +llama3.1-8B-AI4PRIVACY-16bit-merged.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-AI4PRIVACY-16bit-merged.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-AI4PRIVACY-16bit-merged.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-AI4PRIVACY-16bit-merged.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-AI4PRIVACY-16bit-merged.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-AI4PRIVACY-16bit-merged.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-AI4PRIVACY-16bit-merged.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-AI4PRIVACY-16bit-merged.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.1-8B-AI4PRIVACY-16bit-merged.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..1711f32 --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: Parth/llama3.1-8B-AI4PRIVACY-16bit-merged +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/Parth/llama3.1-8B-AI4PRIVACY-16bit-merged + + +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/llama3.1-8B-AI4PRIVACY-16bit-merged-GGUF/resolve/main/llama3.1-8B-AI4PRIVACY-16bit-merged.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-AI4PRIVACY-16bit-merged-GGUF/resolve/main/llama3.1-8B-AI4PRIVACY-16bit-merged.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-AI4PRIVACY-16bit-merged-GGUF/resolve/main/llama3.1-8B-AI4PRIVACY-16bit-merged.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-AI4PRIVACY-16bit-merged-GGUF/resolve/main/llama3.1-8B-AI4PRIVACY-16bit-merged.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-AI4PRIVACY-16bit-merged-GGUF/resolve/main/llama3.1-8B-AI4PRIVACY-16bit-merged.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-AI4PRIVACY-16bit-merged-GGUF/resolve/main/llama3.1-8B-AI4PRIVACY-16bit-merged.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-AI4PRIVACY-16bit-merged-GGUF/resolve/main/llama3.1-8B-AI4PRIVACY-16bit-merged.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-AI4PRIVACY-16bit-merged-GGUF/resolve/main/llama3.1-8B-AI4PRIVACY-16bit-merged.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-AI4PRIVACY-16bit-merged-GGUF/resolve/main/llama3.1-8B-AI4PRIVACY-16bit-merged.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-AI4PRIVACY-16bit-merged-GGUF/resolve/main/llama3.1-8B-AI4PRIVACY-16bit-merged.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-AI4PRIVACY-16bit-merged-GGUF/resolve/main/llama3.1-8B-AI4PRIVACY-16bit-merged.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.1-8B-AI4PRIVACY-16bit-merged-GGUF/resolve/main/llama3.1-8B-AI4PRIVACY-16bit-merged.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/llama3.1-8B-AI4PRIVACY-16bit-merged.IQ4_XS.gguf b/llama3.1-8B-AI4PRIVACY-16bit-merged.IQ4_XS.gguf new file mode 100644 index 0000000..cfb03df --- /dev/null +++ b/llama3.1-8B-AI4PRIVACY-16bit-merged.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eceedfa1c80eed5a05ec3ce99f3a71a3298b2384a7f047aa9031fc8214a077da +size 4484368448 diff --git a/llama3.1-8B-AI4PRIVACY-16bit-merged.Q2_K.gguf b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q2_K.gguf new file mode 100644 index 0000000..f6f8b82 --- /dev/null +++ b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:912347fec423e985a3738368ef19a39c014632951a0cd3316371cf3fbccf46b3 +size 3179137088 diff --git a/llama3.1-8B-AI4PRIVACY-16bit-merged.Q3_K_L.gguf b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q3_K_L.gguf new file mode 100644 index 0000000..83404e3 --- /dev/null +++ b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1dea7d0d3c91eb60e96d07f4eb2dd41d0534e51eda6b34f6237284848722721 +size 4321962048 diff --git a/llama3.1-8B-AI4PRIVACY-16bit-merged.Q3_K_M.gguf b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q3_K_M.gguf new file mode 100644 index 0000000..acc4425 --- /dev/null +++ b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c090921488613f4502eaa6ab91dfef87e6cd8b25e456fa795794fbdd27a1389c +size 4018923584 diff --git a/llama3.1-8B-AI4PRIVACY-16bit-merged.Q3_K_S.gguf b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q3_K_S.gguf new file mode 100644 index 0000000..a4730b1 --- /dev/null +++ b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39b67bab74086dfb98cc7ad850cd9ca813e7c90618f188ae4de5fef2667cda13 +size 3664504896 diff --git a/llama3.1-8B-AI4PRIVACY-16bit-merged.Q4_K_M.gguf b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q4_K_M.gguf new file mode 100644 index 0000000..0d7c84b --- /dev/null +++ b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:692f42a1a14ad41e25ecb56e3b59ae94a685c17c16a34f7fd24349408b82c9de +size 4920739904 diff --git a/llama3.1-8B-AI4PRIVACY-16bit-merged.Q4_K_S.gguf b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q4_K_S.gguf new file mode 100644 index 0000000..db980ff --- /dev/null +++ b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7b0fb025d51a921245ee4a20f253cf50d38bfbeefab876d3bba6157e358e6c5 +size 4692674624 diff --git a/llama3.1-8B-AI4PRIVACY-16bit-merged.Q5_K_M.gguf b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q5_K_M.gguf new file mode 100644 index 0000000..676e90b --- /dev/null +++ b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98b8f480a8620015e49f6ceb604402857e0902b8aedf27f5a171bf63ab820e1e +size 5732993088 diff --git a/llama3.1-8B-AI4PRIVACY-16bit-merged.Q5_K_S.gguf b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q5_K_S.gguf new file mode 100644 index 0000000..d3e6991 --- /dev/null +++ b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0925ee981b27fd02dd105a76beea53aa6aaf5d7ca1f0eb9d9bffc3666e95ac0 +size 5599299648 diff --git a/llama3.1-8B-AI4PRIVACY-16bit-merged.Q6_K.gguf b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q6_K.gguf new file mode 100644 index 0000000..1772064 --- /dev/null +++ b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c56e5dcf39794e2c033e5630eb43b8a27c627ec2770321679b82ea839683ed1 +size 6596012096 diff --git a/llama3.1-8B-AI4PRIVACY-16bit-merged.Q8_0.gguf b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q8_0.gguf new file mode 100644 index 0000000..c43034c --- /dev/null +++ b/llama3.1-8B-AI4PRIVACY-16bit-merged.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:317c7af6e214f1155ba7d6fe5d990b503d5e83b856b5aa6f8b16fddc78eade75 +size 8540776512 diff --git a/llama3.1-8B-AI4PRIVACY-16bit-merged.f16.gguf b/llama3.1-8B-AI4PRIVACY-16bit-merged.f16.gguf new file mode 100644 index 0000000..cc40044 --- /dev/null +++ b/llama3.1-8B-AI4PRIVACY-16bit-merged.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2760abe0a4370771750ae6cd6a4ce7aee561ab534b87a0aa57b34e893a4290c +size 16068896832