commit 5b28b720e7723af4fa4e4e06a403a5c76e793a03 Author: ModelHub XC Date: Sun Jun 14 14:10:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MedPsy-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..04699af --- /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 +MedPsy-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MedPsy-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MedPsy-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MedPsy-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedPsy-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedPsy-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedPsy-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedPsy-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedPsy-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedPsy-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MedPsy-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MedPsy-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MedPsy-4B.IQ4_XS.gguf b/MedPsy-4B.IQ4_XS.gguf new file mode 100644 index 0000000..0ceb31a --- /dev/null +++ b/MedPsy-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9710614762e81ee7da564c58ee8cc874eec86da8025ea35c2768a192b525945f +size 2492950144 diff --git a/MedPsy-4B.Q2_K.gguf b/MedPsy-4B.Q2_K.gguf new file mode 100644 index 0000000..aa6658f --- /dev/null +++ b/MedPsy-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46d2b3208618369491380a86d2bc5ba9ea0a6a922b26ef2b0d9ed057cae8ac51 +size 1797126784 diff --git a/MedPsy-4B.Q3_K_L.gguf b/MedPsy-4B.Q3_K_L.gguf new file mode 100644 index 0000000..3a78cce --- /dev/null +++ b/MedPsy-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43eadac321727fe5d339fa88be9319de59f869f6820200bb6bd66424fe67380f +size 2406916224 diff --git a/MedPsy-4B.Q3_K_M.gguf b/MedPsy-4B.Q3_K_M.gguf new file mode 100644 index 0000000..1756c25 --- /dev/null +++ b/MedPsy-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6ca7cde3e76740cffe64268b4a3e86d4a298d40b42df545ee638082fc87a8b1 +size 2242748544 diff --git a/MedPsy-4B.Q3_K_S.gguf b/MedPsy-4B.Q3_K_S.gguf new file mode 100644 index 0000000..1293c0e --- /dev/null +++ b/MedPsy-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c4efc5d27161ff405ee849f2faebb5f6803f7ea87c24e477a59661c18d421e1 +size 2054127744 diff --git a/MedPsy-4B.Q4_K_M.gguf b/MedPsy-4B.Q4_K_M.gguf new file mode 100644 index 0000000..ab67e41 --- /dev/null +++ b/MedPsy-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:922934e7f529830f3b17463020aa3c41fd7c4785f8fb4500ff6720ee84f17242 +size 2716069504 diff --git a/MedPsy-4B.Q4_K_S.gguf b/MedPsy-4B.Q4_K_S.gguf new file mode 100644 index 0000000..086d704 --- /dev/null +++ b/MedPsy-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fa0a99d89a7232036e294dd0fe0a84ddb8d86dd53c3b8bd4d621056862e2056 +size 2602098304 diff --git a/MedPsy-4B.Q5_K_M.gguf b/MedPsy-4B.Q5_K_M.gguf new file mode 100644 index 0000000..29a1754 --- /dev/null +++ b/MedPsy-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6325dbfc1140a884e58abf080da8572b87510549d83c202bcc4e2f483a4d764a +size 3156921984 diff --git a/MedPsy-4B.Q5_K_S.gguf b/MedPsy-4B.Q5_K_S.gguf new file mode 100644 index 0000000..c9f5e81 --- /dev/null +++ b/MedPsy-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c5b61fbd32ac9b465fdffcb2885cbd69392ce881eb20fa547aa6cd41e56117d +size 3091119744 diff --git a/MedPsy-4B.Q6_K.gguf b/MedPsy-4B.Q6_K.gguf new file mode 100644 index 0000000..d0a53cf --- /dev/null +++ b/MedPsy-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88489301ecd4413f80482cfcae4928957d651fa0ab8bb7a21edce73ee22019b7 +size 3625327744 diff --git a/MedPsy-4B.Q8_0.gguf b/MedPsy-4B.Q8_0.gguf new file mode 100644 index 0000000..4877341 --- /dev/null +++ b/MedPsy-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df056e05848aec3f11d4827c38c2bb1052257b42823cfde5b2f9bdec96aab7cb +size 4693672064 diff --git a/MedPsy-4B.f16.gguf b/MedPsy-4B.f16.gguf new file mode 100644 index 0000000..3dfc29e --- /dev/null +++ b/MedPsy-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:402f89ffb0e1e064301382a6c7e2c0d1733b3fcbbbbd697b20898103fe42579b +size 8829198464 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e89a111 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: qvac/MedPsy-4B +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/qvac/MedPsy-4B/blob/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- medical +- healthcare +- clinical +- edge +- qwen3 +- tether-ai +- text-generation +- on-device +--- +## About + + + + + + + + + +static quants of https://huggingface.co/qvac/MedPsy-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MedPsy-4B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/MedPsy-4B-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/MedPsy-4B-GGUF/resolve/main/MedPsy-4B.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/MedPsy-4B-GGUF/resolve/main/MedPsy-4B.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/MedPsy-4B-GGUF/resolve/main/MedPsy-4B.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MedPsy-4B-GGUF/resolve/main/MedPsy-4B.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/MedPsy-4B-GGUF/resolve/main/MedPsy-4B.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/MedPsy-4B-GGUF/resolve/main/MedPsy-4B.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedPsy-4B-GGUF/resolve/main/MedPsy-4B.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedPsy-4B-GGUF/resolve/main/MedPsy-4B.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/MedPsy-4B-GGUF/resolve/main/MedPsy-4B.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MedPsy-4B-GGUF/resolve/main/MedPsy-4B.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MedPsy-4B-GGUF/resolve/main/MedPsy-4B.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MedPsy-4B-GGUF/resolve/main/MedPsy-4B.f16.gguf) | f16 | 8.9 | 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. + +