commit 1b301dbd8c1620ccf1d806acfb4a6b1457b5de5c Author: ModelHub XC Date: Sun Jun 21 17:28:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/GENIE_en_8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6fd1a9 --- /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 +GENIE_en_8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_en_8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_en_8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_en_8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_en_8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_en_8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_en_8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_en_8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_en_8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_en_8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_en_8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +GENIE_en_8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/GENIE_en_8b.IQ4_XS.gguf b/GENIE_en_8b.IQ4_XS.gguf new file mode 100644 index 0000000..b24bd97 --- /dev/null +++ b/GENIE_en_8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cb316115ec10b269abb46d8e5bea73abd5b35fcda49f8e113744d20119d1438 +size 4484363232 diff --git a/GENIE_en_8b.Q2_K.gguf b/GENIE_en_8b.Q2_K.gguf new file mode 100644 index 0000000..39dd1a6 --- /dev/null +++ b/GENIE_en_8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8695a9c9500eba968dfc6adb05bc746330882fad3e6dcb2ce5d259cd36db4f2 +size 3179131872 diff --git a/GENIE_en_8b.Q3_K_L.gguf b/GENIE_en_8b.Q3_K_L.gguf new file mode 100644 index 0000000..1168347 --- /dev/null +++ b/GENIE_en_8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c3e4e4be1dd810166ca51a04595cd8c34633bed8c965b5c1256fc4ceedb2de6 +size 4321956832 diff --git a/GENIE_en_8b.Q3_K_M.gguf b/GENIE_en_8b.Q3_K_M.gguf new file mode 100644 index 0000000..b243ea1 --- /dev/null +++ b/GENIE_en_8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef74725b082361d65896b50fef00765dbcb02c2111bd69e8266afd563315e474 +size 4018918368 diff --git a/GENIE_en_8b.Q3_K_S.gguf b/GENIE_en_8b.Q3_K_S.gguf new file mode 100644 index 0000000..5c40419 --- /dev/null +++ b/GENIE_en_8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:642f2b5d59af4cda5b850f0b665e2467322cec73b6f9ee6ba98fb38d1eea8d4e +size 3664499680 diff --git a/GENIE_en_8b.Q4_K_M.gguf b/GENIE_en_8b.Q4_K_M.gguf new file mode 100644 index 0000000..b5a3ee8 --- /dev/null +++ b/GENIE_en_8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f56dae1936d753065322aaaaa73102ed6ed32763680a8794d31a54ae79306693 +size 4920734688 diff --git a/GENIE_en_8b.Q4_K_S.gguf b/GENIE_en_8b.Q4_K_S.gguf new file mode 100644 index 0000000..edd8555 --- /dev/null +++ b/GENIE_en_8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1dc74e60d92074211c50b7ac57111c2521c56154902bba0e32700818e3451f0 +size 4692669408 diff --git a/GENIE_en_8b.Q5_K_M.gguf b/GENIE_en_8b.Q5_K_M.gguf new file mode 100644 index 0000000..433eb0c --- /dev/null +++ b/GENIE_en_8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd41e28623418835bbdddd0b9f2f30acdd63e40628cfa5fce1f728d21323fa9f +size 5732987872 diff --git a/GENIE_en_8b.Q5_K_S.gguf b/GENIE_en_8b.Q5_K_S.gguf new file mode 100644 index 0000000..ccfc7b7 --- /dev/null +++ b/GENIE_en_8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9be98dc06d1e445ee6f6628cc1fdb0f425fb346b6f21eec40d2aa3346dafc83 +size 5599294432 diff --git a/GENIE_en_8b.Q6_K.gguf b/GENIE_en_8b.Q6_K.gguf new file mode 100644 index 0000000..44860b7 --- /dev/null +++ b/GENIE_en_8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f40f50eb3a95fef125117482e04ad2d022808669e961237d1a066b3bc29b28d1 +size 6596006880 diff --git a/GENIE_en_8b.Q8_0.gguf b/GENIE_en_8b.Q8_0.gguf new file mode 100644 index 0000000..f63e08d --- /dev/null +++ b/GENIE_en_8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87b5e84ba2eaf270a801d2eb3ad70b9f1fb847cb2a5ac5df4812ec7bfad5db5e +size 8540771296 diff --git a/GENIE_en_8b.f16.gguf b/GENIE_en_8b.f16.gguf new file mode 100644 index 0000000..39aed84 --- /dev/null +++ b/GENIE_en_8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64d7b76410316941916216e764d9fad25ccc2ac1d86cf47320dfedeb5fa600e1 +size 16068891616 diff --git a/README.md b/README.md new file mode 100644 index 0000000..28cee70 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: THUMedInfo/GENIE_en_8b +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- structurization +- EHR +- medical +- information extraction +--- +## About + + + + + + +static quants of https://huggingface.co/THUMedInfo/GENIE_en_8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#GENIE_en_8b-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_en_8b-GGUF/resolve/main/GENIE_en_8b.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/GENIE_en_8b-GGUF/resolve/main/GENIE_en_8b.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/GENIE_en_8b-GGUF/resolve/main/GENIE_en_8b.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/GENIE_en_8b-GGUF/resolve/main/GENIE_en_8b.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/GENIE_en_8b-GGUF/resolve/main/GENIE_en_8b.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/GENIE_en_8b-GGUF/resolve/main/GENIE_en_8b.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GENIE_en_8b-GGUF/resolve/main/GENIE_en_8b.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/GENIE_en_8b-GGUF/resolve/main/GENIE_en_8b.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/GENIE_en_8b-GGUF/resolve/main/GENIE_en_8b.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/GENIE_en_8b-GGUF/resolve/main/GENIE_en_8b.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/GENIE_en_8b-GGUF/resolve/main/GENIE_en_8b.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/GENIE_en_8b-GGUF/resolve/main/GENIE_en_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. + +