commit bfe6055c39be2a3b7ab3b1412fb9509de2eafe65 Author: ModelHub XC Date: Wed Jul 8 04:18:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3-wissenschaft-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4817b40 --- /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 +llama-3-wissenschaft-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-wissenschaft-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-wissenschaft-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-wissenschaft-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-wissenschaft-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-wissenschaft-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-wissenschaft-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-wissenschaft-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-wissenschaft-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-wissenschaft-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-wissenschaft-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-wissenschaft-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4bd3571 --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: nbeerbower/llama-3-wissenschaft-8B +language: +- en +library_name: transformers +license: other +license_name: llama3 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + + +static quants of https://huggingface.co/nbeerbower/llama-3-wissenschaft-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/llama-3-wissenschaft-8B-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/llama-3-wissenschaft-8B-GGUF/resolve/main/llama-3-wissenschaft-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-wissenschaft-8B-GGUF/resolve/main/llama-3-wissenschaft-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-wissenschaft-8B-GGUF/resolve/main/llama-3-wissenschaft-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-wissenschaft-8B-GGUF/resolve/main/llama-3-wissenschaft-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-wissenschaft-8B-GGUF/resolve/main/llama-3-wissenschaft-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-wissenschaft-8B-GGUF/resolve/main/llama-3-wissenschaft-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-wissenschaft-8B-GGUF/resolve/main/llama-3-wissenschaft-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3-wissenschaft-8B-GGUF/resolve/main/llama-3-wissenschaft-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-wissenschaft-8B-GGUF/resolve/main/llama-3-wissenschaft-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3-wissenschaft-8B-GGUF/resolve/main/llama-3-wissenschaft-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-wissenschaft-8B-GGUF/resolve/main/llama-3-wissenschaft-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3-wissenschaft-8B-GGUF/resolve/main/llama-3-wissenschaft-8B.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. + + diff --git a/llama-3-wissenschaft-8B.IQ4_XS.gguf b/llama-3-wissenschaft-8B.IQ4_XS.gguf new file mode 100644 index 0000000..ad5d7ae --- /dev/null +++ b/llama-3-wissenschaft-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83540d227fde41e3b0f98bdb6f35f66d3bb043c07b4c7595cb3d6bed65e7c825 +size 4484364352 diff --git a/llama-3-wissenschaft-8B.Q2_K.gguf b/llama-3-wissenschaft-8B.Q2_K.gguf new file mode 100644 index 0000000..5e017d8 --- /dev/null +++ b/llama-3-wissenschaft-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6a1ff38f47b0cfd4d8c4c4b90ef51b84571298480be2a759abb20f025af2408 +size 3179132992 diff --git a/llama-3-wissenschaft-8B.Q3_K_L.gguf b/llama-3-wissenschaft-8B.Q3_K_L.gguf new file mode 100644 index 0000000..1029ffe --- /dev/null +++ b/llama-3-wissenschaft-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac348b4653a6ff3f7c0896694c796b96b4ec746cd087fba84e5e71306f38a71f +size 4321957952 diff --git a/llama-3-wissenschaft-8B.Q3_K_M.gguf b/llama-3-wissenschaft-8B.Q3_K_M.gguf new file mode 100644 index 0000000..367b153 --- /dev/null +++ b/llama-3-wissenschaft-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd25e69d830329726740663c670003861beffe3d7bd7b3595c463f7775c94d41 +size 4018919488 diff --git a/llama-3-wissenschaft-8B.Q3_K_S.gguf b/llama-3-wissenschaft-8B.Q3_K_S.gguf new file mode 100644 index 0000000..27be7b3 --- /dev/null +++ b/llama-3-wissenschaft-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8434d45b8b6973ab782d9497346a3bb7d2f4f72a8ecb85ea235e4ef9e386f522 +size 3664500800 diff --git a/llama-3-wissenschaft-8B.Q4_K_M.gguf b/llama-3-wissenschaft-8B.Q4_K_M.gguf new file mode 100644 index 0000000..2707308 --- /dev/null +++ b/llama-3-wissenschaft-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:373afbe99e512f75c8b2f183f7e5ca6ca0edd4c60ea3a4942ca535fd13bdbc86 +size 4920735808 diff --git a/llama-3-wissenschaft-8B.Q4_K_S.gguf b/llama-3-wissenschaft-8B.Q4_K_S.gguf new file mode 100644 index 0000000..c07de4b --- /dev/null +++ b/llama-3-wissenschaft-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c2315c7f22228e36899dca61a95c32d9dfbf399cce8ab9d199b54c7d5139b0 +size 4692670528 diff --git a/llama-3-wissenschaft-8B.Q5_K_M.gguf b/llama-3-wissenschaft-8B.Q5_K_M.gguf new file mode 100644 index 0000000..07d2314 --- /dev/null +++ b/llama-3-wissenschaft-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:843721e3e9e97adf56eeb0e826c6c1a4b5db2ee59b2abae11a54bf01367695c1 +size 5732988992 diff --git a/llama-3-wissenschaft-8B.Q5_K_S.gguf b/llama-3-wissenschaft-8B.Q5_K_S.gguf new file mode 100644 index 0000000..c41d94a --- /dev/null +++ b/llama-3-wissenschaft-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d07ac4db4a26dbd3eb672b25648a13467f7cdb7143473d2fde1ddb192cf0ec1a +size 5599295552 diff --git a/llama-3-wissenschaft-8B.Q6_K.gguf b/llama-3-wissenschaft-8B.Q6_K.gguf new file mode 100644 index 0000000..746b2a6 --- /dev/null +++ b/llama-3-wissenschaft-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0428b8ceb4e9f08ff70a43ccc82a9560d988051a21a6de30e7d358948469700f +size 6596008000 diff --git a/llama-3-wissenschaft-8B.Q8_0.gguf b/llama-3-wissenschaft-8B.Q8_0.gguf new file mode 100644 index 0000000..5422f18 --- /dev/null +++ b/llama-3-wissenschaft-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a03d547fd187accc89d4c32119053d0c3783ee8870ab7305868a536d9a9fbd26 +size 8540772416 diff --git a/llama-3-wissenschaft-8B.f16.gguf b/llama-3-wissenschaft-8B.f16.gguf new file mode 100644 index 0000000..16924d0 --- /dev/null +++ b/llama-3-wissenschaft-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:826c004721d0127b4e84aafbd3ef18449b795b83046c0a54e0c12d94600e23ea +size 16068892736