commit b1f661078b70e4750207880ca512bf771f77ed65 Author: ModelHub XC Date: Thu Jul 16 21:01:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MedClaria-4b-v0.5-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..908e75f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +MedClaria-4b-v0.5.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MedClaria-4b-v0.5.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +MedClaria-4b-v0.5.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MedClaria-4b-v0.5.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MedClaria-4b-v0.5.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MedClaria-4b-v0.5.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedClaria-4b-v0.5.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedClaria-4b-v0.5.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedClaria-4b-v0.5.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedClaria-4b-v0.5.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedClaria-4b-v0.5.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedClaria-4b-v0.5.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MedClaria-4b-v0.5.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MedClaria-4b-v0.5.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MedClaria-4b-v0.5.IQ4_XS.gguf b/MedClaria-4b-v0.5.IQ4_XS.gguf new file mode 100644 index 0000000..ceff7d6 --- /dev/null +++ b/MedClaria-4b-v0.5.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8566f94ff6b926de9691df2f04b5c60271ff7a003588cb77cb593ea507ac03a5 +size 2279626496 diff --git a/MedClaria-4b-v0.5.Q2_K.gguf b/MedClaria-4b-v0.5.Q2_K.gguf new file mode 100644 index 0000000..e27a841 --- /dev/null +++ b/MedClaria-4b-v0.5.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbe50cb7785610fd2f710ed213e6d2e7bcdd64213d731dd815e49131bb26c1b3 +size 1729165056 diff --git a/MedClaria-4b-v0.5.Q3_K_L.gguf b/MedClaria-4b-v0.5.Q3_K_L.gguf new file mode 100644 index 0000000..9b3f7cc --- /dev/null +++ b/MedClaria-4b-v0.5.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd32ccabd8c5af820af6978ac87b29b6e66fa117e5aa54de1a4db1a448cc478c +size 2236086016 diff --git a/MedClaria-4b-v0.5.Q3_K_M.gguf b/MedClaria-4b-v0.5.Q3_K_M.gguf new file mode 100644 index 0000000..7541f26 --- /dev/null +++ b/MedClaria-4b-v0.5.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82d48ce68d0006b4b14b2c4d13fedc76a68ff5c54e79a73d61be83487eb35491 +size 2098460416 diff --git a/MedClaria-4b-v0.5.Q3_K_S.gguf b/MedClaria-4b-v0.5.Q3_K_S.gguf new file mode 100644 index 0000000..bd46f6e --- /dev/null +++ b/MedClaria-4b-v0.5.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dac962f30d22dceaf8562a22dbdff97b5c85b626062b593f8efa908c2893bbc9 +size 1937364736 diff --git a/MedClaria-4b-v0.5.Q4_K_M.gguf b/MedClaria-4b-v0.5.Q4_K_M.gguf new file mode 100644 index 0000000..11207f1 --- /dev/null +++ b/MedClaria-4b-v0.5.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be66fe537706c1bf7dde4674b075fcdaba0183e4e77ab7ad0fee3c2126d1b23f +size 2489894656 diff --git a/MedClaria-4b-v0.5.Q4_K_S.gguf b/MedClaria-4b-v0.5.Q4_K_S.gguf new file mode 100644 index 0000000..56d262d --- /dev/null +++ b/MedClaria-4b-v0.5.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44f635dfce396fab5cd58997bd8e3c78a23f2347b9902bb9cdfc848c914537da +size 2377930496 diff --git a/MedClaria-4b-v0.5.Q5_K_M.gguf b/MedClaria-4b-v0.5.Q5_K_M.gguf new file mode 100644 index 0000000..6d5650a --- /dev/null +++ b/MedClaria-4b-v0.5.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a8a95ff012c6195e3d11473762ee7747089a618151667138723a396cdb9302d +size 2829698816 diff --git a/MedClaria-4b-v0.5.Q5_K_S.gguf b/MedClaria-4b-v0.5.Q5_K_S.gguf new file mode 100644 index 0000000..142a54d --- /dev/null +++ b/MedClaria-4b-v0.5.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f37cfcbf983edc1553400f2353963e67226e1b0b2aeae27e5a4a742f4b498d2d +size 2764592896 diff --git a/MedClaria-4b-v0.5.Q6_K.gguf b/MedClaria-4b-v0.5.Q6_K.gguf new file mode 100644 index 0000000..a78bc13 --- /dev/null +++ b/MedClaria-4b-v0.5.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44eca5d8c85a7ca2e2d70cff29cdbff8a33f3af9664604c5be8aba5c1f0630a5 +size 3190740736 diff --git a/MedClaria-4b-v0.5.Q8_0.gguf b/MedClaria-4b-v0.5.Q8_0.gguf new file mode 100644 index 0000000..28251d0 --- /dev/null +++ b/MedClaria-4b-v0.5.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:811661f1dad5287d5879c7e0d984045cc2cd01443da8b65c05da11111be1d2b0 +size 4130402816 diff --git a/MedClaria-4b-v0.5.f16.gguf b/MedClaria-4b-v0.5.f16.gguf new file mode 100644 index 0000000..5216d4d --- /dev/null +++ b/MedClaria-4b-v0.5.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b47e43178169063836e880b75e4c16871ef4d45decf414c29c318dd0cf5a0c9 +size 7767804416 diff --git a/MedClaria-4b-v0.5.mmproj-Q8_0.gguf b/MedClaria-4b-v0.5.mmproj-Q8_0.gguf new file mode 100644 index 0000000..b08e1f0 --- /dev/null +++ b/MedClaria-4b-v0.5.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e743780ec835dad69691db97fa7f857caaa8225708a9dd1d2d3968da4d0cafd +size 591378016 diff --git a/MedClaria-4b-v0.5.mmproj-f16.gguf b/MedClaria-4b-v0.5.mmproj-f16.gguf new file mode 100644 index 0000000..3c8c0c6 --- /dev/null +++ b/MedClaria-4b-v0.5.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:788bbd423da6f1014a6a58670e92b4682581f61ef456b3077f130cdd90101bea +size 851251936 diff --git a/README.md b/README.md new file mode 100644 index 0000000..48cea74 --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: drwlf/MedClaria-4b-v0.5 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- trl +- sft +- medical +- psychology +- medgemma +- gemma3 +--- +## About + + + + + + +static quants of https://huggingface.co/drwlf/MedClaria-4b-v0.5 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MedClaria-4b-v0.5-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MedClaria-4b-v0.5-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/MedClaria-4b-v0.5-GGUF/resolve/main/MedClaria-4b-v0.5.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.7 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/MedClaria-4b-v0.5-GGUF/resolve/main/MedClaria-4b-v0.5.mmproj-f16.gguf) | mmproj-f16 | 1.0 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/MedClaria-4b-v0.5-GGUF/resolve/main/MedClaria-4b-v0.5.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/MedClaria-4b-v0.5-GGUF/resolve/main/MedClaria-4b-v0.5.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/MedClaria-4b-v0.5-GGUF/resolve/main/MedClaria-4b-v0.5.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MedClaria-4b-v0.5-GGUF/resolve/main/MedClaria-4b-v0.5.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MedClaria-4b-v0.5-GGUF/resolve/main/MedClaria-4b-v0.5.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/MedClaria-4b-v0.5-GGUF/resolve/main/MedClaria-4b-v0.5.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedClaria-4b-v0.5-GGUF/resolve/main/MedClaria-4b-v0.5.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedClaria-4b-v0.5-GGUF/resolve/main/MedClaria-4b-v0.5.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/MedClaria-4b-v0.5-GGUF/resolve/main/MedClaria-4b-v0.5.Q5_K_M.gguf) | Q5_K_M | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/MedClaria-4b-v0.5-GGUF/resolve/main/MedClaria-4b-v0.5.Q6_K.gguf) | Q6_K | 3.3 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MedClaria-4b-v0.5-GGUF/resolve/main/MedClaria-4b-v0.5.Q8_0.gguf) | Q8_0 | 4.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MedClaria-4b-v0.5-GGUF/resolve/main/MedClaria-4b-v0.5.f16.gguf) | f16 | 7.9 | 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. + +