commit 5ad9cbb5fbe257933e946bfd8f94ed91f7bed8d6 Author: ModelHub XC Date: Sat May 9 05:29:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GENIE_zh_7b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..08d95a9 --- /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 +GENIE_zh_7b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_zh_7b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_zh_7b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_zh_7b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_zh_7b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_zh_7b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_zh_7b.f16.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_zh_7b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_zh_7b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_zh_7b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_zh_7b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GENIE_zh_7b.IQ4_XS.gguf b/GENIE_zh_7b.IQ4_XS.gguf new file mode 100644 index 0000000..0088060 --- /dev/null +++ b/GENIE_zh_7b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94eaf53f675fe723d6e7e7b987e6843bd2ab43f0cc209a04051e99e49855981d +size 4250298944 diff --git a/GENIE_zh_7b.Q2_K.gguf b/GENIE_zh_7b.Q2_K.gguf new file mode 100644 index 0000000..35f5a65 --- /dev/null +++ b/GENIE_zh_7b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f995f952ca5656513509c9d8abfe93f14dd5bb4fb603da196894933737d3f7db +size 3015940672 diff --git a/GENIE_zh_7b.Q3_K_L.gguf b/GENIE_zh_7b.Q3_K_L.gguf new file mode 100644 index 0000000..1f1e3a8 --- /dev/null +++ b/GENIE_zh_7b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3180da12872b9ddfc1dc6442d9f5188ff249bd64b69d0fa135798d894bc4f6af +size 4088459840 diff --git a/GENIE_zh_7b.Q3_K_M.gguf b/GENIE_zh_7b.Q3_K_M.gguf new file mode 100644 index 0000000..9adaf80 --- /dev/null +++ b/GENIE_zh_7b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de7c8974d4517cab964c84c87657e6f2f22b59c87b846a1aa6c341b48ca72469 +size 3808391744 diff --git a/GENIE_zh_7b.Q3_K_S.gguf b/GENIE_zh_7b.Q3_K_S.gguf new file mode 100644 index 0000000..cbbb032 --- /dev/null +++ b/GENIE_zh_7b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9f0a48d30f299df023bc115a347eaee71d434624c9733b517598c2576bdd350 +size 3492368960 diff --git a/GENIE_zh_7b.Q4_K_M.gguf b/GENIE_zh_7b.Q4_K_M.gguf new file mode 100644 index 0000000..3d33e41 --- /dev/null +++ b/GENIE_zh_7b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dc38a2a18c6d9b8639ff1277c46e775826bab119a0447f829d9cd7ff9130dba +size 4683074112 diff --git a/GENIE_zh_7b.Q4_K_S.gguf b/GENIE_zh_7b.Q4_K_S.gguf new file mode 100644 index 0000000..480b662 --- /dev/null +++ b/GENIE_zh_7b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4d2d4b83e0938788662a3650968dc62c2bf5e05adea26936a5a71a5e078c96d +size 4457769536 diff --git a/GENIE_zh_7b.Q5_K_M.gguf b/GENIE_zh_7b.Q5_K_M.gguf new file mode 100644 index 0000000..0f16447 --- /dev/null +++ b/GENIE_zh_7b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97ede0593981c65d9d0c4e1e33f70b970f44d67e468f2045c86bead62ed65a7a +size 5444831808 diff --git a/GENIE_zh_7b.Q5_K_S.gguf b/GENIE_zh_7b.Q5_K_S.gguf new file mode 100644 index 0000000..00ecebe --- /dev/null +++ b/GENIE_zh_7b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:523514bc99d5f9a991b0609821359184d02d6a7df34366bae41d07327fd5655f +size 5315177024 diff --git a/GENIE_zh_7b.Q6_K.gguf b/GENIE_zh_7b.Q6_K.gguf new file mode 100644 index 0000000..a5828b4 --- /dev/null +++ b/GENIE_zh_7b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63109535f385d2d094182e828be9d49084e894e85c36fa9145feab5487ab7f05 +size 6254199360 diff --git a/GENIE_zh_7b.Q8_0.gguf b/GENIE_zh_7b.Q8_0.gguf new file mode 100644 index 0000000..22e7026 --- /dev/null +++ b/GENIE_zh_7b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3778e62937191242b44e83f80120acb8d0fc7b426b02d8b94dfef4e26adc98c6 +size 8098525760 diff --git a/GENIE_zh_7b.f16.gguf b/GENIE_zh_7b.f16.gguf new file mode 100644 index 0000000..c671530 --- /dev/null +++ b/GENIE_zh_7b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d753f881b05753d3e6beca60bab1f19b5a3f4e37988861d3fd74316b1460021 +size 15237853760 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0ed9caa --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: THUMedInfo/GENIE_zh_7b +language: +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- structuring +- EHR +- medical +- IE +--- +## About + + + + + + +static quants of https://huggingface.co/THUMedInfo/GENIE_zh_7b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GENIE_zh_7b-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/GENIE_zh_7b-GGUF/resolve/main/GENIE_zh_7b.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/GENIE_zh_7b-GGUF/resolve/main/GENIE_zh_7b.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/GENIE_zh_7b-GGUF/resolve/main/GENIE_zh_7b.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GENIE_zh_7b-GGUF/resolve/main/GENIE_zh_7b.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/GENIE_zh_7b-GGUF/resolve/main/GENIE_zh_7b.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/GENIE_zh_7b-GGUF/resolve/main/GENIE_zh_7b.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GENIE_zh_7b-GGUF/resolve/main/GENIE_zh_7b.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GENIE_zh_7b-GGUF/resolve/main/GENIE_zh_7b.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/GENIE_zh_7b-GGUF/resolve/main/GENIE_zh_7b.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/GENIE_zh_7b-GGUF/resolve/main/GENIE_zh_7b.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GENIE_zh_7b-GGUF/resolve/main/GENIE_zh_7b.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GENIE_zh_7b-GGUF/resolve/main/GENIE_zh_7b.f16.gguf) | f16 | 15.3 | 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. + +