commit 1bd884160b017613c6ec2ef8633e871dfe85dfc9 Author: ModelHub XC Date: Fri Apr 17 11:16:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/hari-q3-8b-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3d366ba --- /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 +hari-q3-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +hari-q3-8b.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +hari-q3-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +hari-q3-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +hari-q3-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +hari-q3-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text +hari-q3-8b.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +hari-q3-8b.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +hari-q3-8b.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +hari-q3-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +hari-q3-8b.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +hari-q3-8b.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f1c3d63 --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: snuh/hari-q3-8b +language: +- ko +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- medical +- clinical +- QA +- benchmark +- healthcare +- korean +- reasoning +--- +## About + + + + + + + + + +static quants of https://huggingface.co/snuh/hari-q3-8b + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#hari-q3-8b-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/hari-q3-8b-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/hari-q3-8b-GGUF/resolve/main/hari-q3-8b.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/hari-q3-8b-GGUF/resolve/main/hari-q3-8b.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/hari-q3-8b-GGUF/resolve/main/hari-q3-8b.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/hari-q3-8b-GGUF/resolve/main/hari-q3-8b.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/hari-q3-8b-GGUF/resolve/main/hari-q3-8b.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/hari-q3-8b-GGUF/resolve/main/hari-q3-8b.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/hari-q3-8b-GGUF/resolve/main/hari-q3-8b.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/hari-q3-8b-GGUF/resolve/main/hari-q3-8b.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/hari-q3-8b-GGUF/resolve/main/hari-q3-8b.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/hari-q3-8b-GGUF/resolve/main/hari-q3-8b.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/hari-q3-8b-GGUF/resolve/main/hari-q3-8b.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/hari-q3-8b-GGUF/resolve/main/hari-q3-8b.f16.gguf) | f16 | 16.5 | 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/hari-q3-8b.IQ4_XS.gguf b/hari-q3-8b.IQ4_XS.gguf new file mode 100644 index 0000000..6118ea6 --- /dev/null +++ b/hari-q3-8b.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e545305c3d396897f3a7ce525d872e22f9c67da4d69e065327e9aef757404096 +size 4593297120 diff --git a/hari-q3-8b.Q2_K.gguf b/hari-q3-8b.Q2_K.gguf new file mode 100644 index 0000000..395a3c7 --- /dev/null +++ b/hari-q3-8b.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bfa08395d6fa7b46892ea5043c05512fa95dfca47fbcb83c80bc28f8a389029 +size 3281733344 diff --git a/hari-q3-8b.Q3_K_L.gguf b/hari-q3-8b.Q3_K_L.gguf new file mode 100644 index 0000000..3e1127c --- /dev/null +++ b/hari-q3-8b.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0c78b392ffb24080809d1103e7612e5fce956e2491058ec6cd3d1a7195309ec +size 4431394528 diff --git a/hari-q3-8b.Q3_K_M.gguf b/hari-q3-8b.Q3_K_M.gguf new file mode 100644 index 0000000..67a751b --- /dev/null +++ b/hari-q3-8b.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ac415700e2dfc35c18d7dfdc53921f43f850223251d748e547857c7d4659168 +size 4124161760 diff --git a/hari-q3-8b.Q3_K_S.gguf b/hari-q3-8b.Q3_K_S.gguf new file mode 100644 index 0000000..a6808bc --- /dev/null +++ b/hari-q3-8b.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d10c99618f450fce7411292386802c9c10505d8c55f428d8ecc7ca3dd7b499c +size 3769612000 diff --git a/hari-q3-8b.Q4_K_M.gguf b/hari-q3-8b.Q4_K_M.gguf new file mode 100644 index 0000000..56d417d --- /dev/null +++ b/hari-q3-8b.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8c4419ea36a9a8b1395237b5cef170d8aedd61c24e707d32468f8cbbca4f9b3 +size 5027784416 diff --git a/hari-q3-8b.Q4_K_S.gguf b/hari-q3-8b.Q4_K_S.gguf new file mode 100644 index 0000000..f49caea --- /dev/null +++ b/hari-q3-8b.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da6ee2c1f4bf9ec95c09aadf1114abd31b9580316509e9cbd73af557365cec24 +size 4802012896 diff --git a/hari-q3-8b.Q5_K_M.gguf b/hari-q3-8b.Q5_K_M.gguf new file mode 100644 index 0000000..7deb928 --- /dev/null +++ b/hari-q3-8b.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8619ed995b7f2b6d87fd304d266ce8a5366fc4b1b9fbf8d478194fefa85bfc1b +size 5851113184 diff --git a/hari-q3-8b.Q5_K_S.gguf b/hari-q3-8b.Q5_K_S.gguf new file mode 100644 index 0000000..cf02a47 --- /dev/null +++ b/hari-q3-8b.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b362bc7f28893e51faf06ea6fc9b33aa3f4aad4c9cdf7e44e40ac0cdba40e28d +size 5720762080 diff --git a/hari-q3-8b.Q6_K.gguf b/hari-q3-8b.Q6_K.gguf new file mode 100644 index 0000000..05ca023 --- /dev/null +++ b/hari-q3-8b.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de65b87483d5d4960bcfb9dd37469444c936feebf6f1586c0c3543895639407a +size 6725900000 diff --git a/hari-q3-8b.Q8_0.gguf b/hari-q3-8b.Q8_0.gguf new file mode 100644 index 0000000..b384ee5 --- /dev/null +++ b/hari-q3-8b.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f811fe6498e9b6229307365621406729c2de426886f4433c2e0173d5c9f96b68 +size 8709519072 diff --git a/hari-q3-8b.f16.gguf b/hari-q3-8b.f16.gguf new file mode 100644 index 0000000..b5c0bf0 --- /dev/null +++ b/hari-q3-8b.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f08d95e685d2f91748867678f782e3e58ba8bf75ef1b12377f991896d06de2b +size 16388044512