commit 98a89c7fd70535544239a38a0dfe1f686f3e3cf7 Author: ModelHub XC Date: Mon May 25 10:30:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-MedIT-SUN-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ff8f210 --- /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-3.1-MedIT-SUN-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-MedIT-SUN-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-MedIT-SUN-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-MedIT-SUN-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-MedIT-SUN-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-MedIT-SUN-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-MedIT-SUN-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-MedIT-SUN-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-MedIT-SUN-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-MedIT-SUN-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-MedIT-SUN-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-MedIT-SUN-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-MedIT-SUN-8B.IQ4_XS.gguf b/Llama-3.1-MedIT-SUN-8B.IQ4_XS.gguf new file mode 100644 index 0000000..ebc0eee --- /dev/null +++ b/Llama-3.1-MedIT-SUN-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:717f9137cccdf3707107e4c9e4e4406f29784bece8c0696bb1579d517fb406ef +size 4484367648 diff --git a/Llama-3.1-MedIT-SUN-8B.Q2_K.gguf b/Llama-3.1-MedIT-SUN-8B.Q2_K.gguf new file mode 100644 index 0000000..d01d824 --- /dev/null +++ b/Llama-3.1-MedIT-SUN-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58be24c09b31bd3f91838d60d5470106e01242acec9e7ecb7752ff9c9ac62438 +size 3179136288 diff --git a/Llama-3.1-MedIT-SUN-8B.Q3_K_L.gguf b/Llama-3.1-MedIT-SUN-8B.Q3_K_L.gguf new file mode 100644 index 0000000..87ecb9d --- /dev/null +++ b/Llama-3.1-MedIT-SUN-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6249b42132b678da43ef20749385adc2b34399cee0f74af989fafbebdd6261d1 +size 4321961248 diff --git a/Llama-3.1-MedIT-SUN-8B.Q3_K_M.gguf b/Llama-3.1-MedIT-SUN-8B.Q3_K_M.gguf new file mode 100644 index 0000000..ede2883 --- /dev/null +++ b/Llama-3.1-MedIT-SUN-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efbe76c7fa35ed6596a6a65b1608380c54e38794ab689a35388c7e5e9b95d045 +size 4018922784 diff --git a/Llama-3.1-MedIT-SUN-8B.Q3_K_S.gguf b/Llama-3.1-MedIT-SUN-8B.Q3_K_S.gguf new file mode 100644 index 0000000..eebe5e2 --- /dev/null +++ b/Llama-3.1-MedIT-SUN-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5caa621a6d58d8f40c1427e672ebe04783f4f7adc3cad55a9f8e15e8371c2875 +size 3664504096 diff --git a/Llama-3.1-MedIT-SUN-8B.Q4_K_M.gguf b/Llama-3.1-MedIT-SUN-8B.Q4_K_M.gguf new file mode 100644 index 0000000..6785c39 --- /dev/null +++ b/Llama-3.1-MedIT-SUN-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24fe040584ed11d0f575ecdaab9d7fd17874025ba4679bb8a84accfd50c7023a +size 4920739104 diff --git a/Llama-3.1-MedIT-SUN-8B.Q4_K_S.gguf b/Llama-3.1-MedIT-SUN-8B.Q4_K_S.gguf new file mode 100644 index 0000000..bbee2be --- /dev/null +++ b/Llama-3.1-MedIT-SUN-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6ee45ae166510c80f41d831bac617f876b001d4f4cbc534241e12637d33e3c7 +size 4692673824 diff --git a/Llama-3.1-MedIT-SUN-8B.Q5_K_M.gguf b/Llama-3.1-MedIT-SUN-8B.Q5_K_M.gguf new file mode 100644 index 0000000..afe146a --- /dev/null +++ b/Llama-3.1-MedIT-SUN-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95a6c1811411882ea92807aa8d24300353ca8d090e0dff5e40465f82c6f8b97c +size 5732992288 diff --git a/Llama-3.1-MedIT-SUN-8B.Q5_K_S.gguf b/Llama-3.1-MedIT-SUN-8B.Q5_K_S.gguf new file mode 100644 index 0000000..25e4e39 --- /dev/null +++ b/Llama-3.1-MedIT-SUN-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f257bdcca9a2666420d288e0749cc52305f616db40992bcb9698c50638d99c1 +size 5599298848 diff --git a/Llama-3.1-MedIT-SUN-8B.Q6_K.gguf b/Llama-3.1-MedIT-SUN-8B.Q6_K.gguf new file mode 100644 index 0000000..bce051b --- /dev/null +++ b/Llama-3.1-MedIT-SUN-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:720e51f3be3595072f440c0cdb104d125569d0a71401ed7f28bb2a962a0ef221 +size 6596011296 diff --git a/Llama-3.1-MedIT-SUN-8B.Q8_0.gguf b/Llama-3.1-MedIT-SUN-8B.Q8_0.gguf new file mode 100644 index 0000000..b9d680e --- /dev/null +++ b/Llama-3.1-MedIT-SUN-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97703c69f7babef80ab48ba247844ae69a486a8ff4e43f0b1a0184bcf53dc279 +size 8540775712 diff --git a/Llama-3.1-MedIT-SUN-8B.f16.gguf b/Llama-3.1-MedIT-SUN-8B.f16.gguf new file mode 100644 index 0000000..654796e --- /dev/null +++ b/Llama-3.1-MedIT-SUN-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a12acc5bf231eb0aa1426fea9e4b50cf557df413416f4e49f57f7c4d95be81a1 +size 16068896032 diff --git a/README.md b/README.md new file mode 100644 index 0000000..409c2a6 --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: meditsolutions/Llama-3.1-MedIT-SUN-8B +language: +- en +library_name: transformers +license: llama3.1 +quantized_by: mradermacher +tags: +- medit-mesh +--- +## About + + + + + + +static quants of https://huggingface.co/meditsolutions/Llama-3.1-MedIT-SUN-8B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-MedIT-SUN-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-3.1-MedIT-SUN-8B-GGUF/resolve/main/Llama-3.1-MedIT-SUN-8B.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-MedIT-SUN-8B-GGUF/resolve/main/Llama-3.1-MedIT-SUN-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-MedIT-SUN-8B-GGUF/resolve/main/Llama-3.1-MedIT-SUN-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-MedIT-SUN-8B-GGUF/resolve/main/Llama-3.1-MedIT-SUN-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-MedIT-SUN-8B-GGUF/resolve/main/Llama-3.1-MedIT-SUN-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-MedIT-SUN-8B-GGUF/resolve/main/Llama-3.1-MedIT-SUN-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-MedIT-SUN-8B-GGUF/resolve/main/Llama-3.1-MedIT-SUN-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-MedIT-SUN-8B-GGUF/resolve/main/Llama-3.1-MedIT-SUN-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-MedIT-SUN-8B-GGUF/resolve/main/Llama-3.1-MedIT-SUN-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-MedIT-SUN-8B-GGUF/resolve/main/Llama-3.1-MedIT-SUN-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-MedIT-SUN-8B-GGUF/resolve/main/Llama-3.1-MedIT-SUN-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-MedIT-SUN-8B-GGUF/resolve/main/Llama-3.1-MedIT-SUN-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. + +