commit 55b2b38e024c37c61d99b8c19c2c166b19dc4d2d Author: ModelHub XC Date: Mon Jun 29 07:45:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MedQwen-3B-SFT-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..66f8903 --- /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 +MedQwen-3B-SFT-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen-3B-SFT-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen-3B-SFT-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen-3B-SFT-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen-3B-SFT-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen-3B-SFT-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen-3B-SFT-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen-3B-SFT-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen-3B-SFT-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen-3B-SFT-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen-3B-SFT-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MedQwen-3B-SFT-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MedQwen-3B-SFT-v2.IQ4_XS.gguf b/MedQwen-3B-SFT-v2.IQ4_XS.gguf new file mode 100644 index 0000000..aa0bcbe --- /dev/null +++ b/MedQwen-3B-SFT-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f398c226e7468a283a22580f21dd06ed21c66c78c02717adc3f6984c709ac347 +size 1753185536 diff --git a/MedQwen-3B-SFT-v2.Q2_K.gguf b/MedQwen-3B-SFT-v2.Q2_K.gguf new file mode 100644 index 0000000..b558150 --- /dev/null +++ b/MedQwen-3B-SFT-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbfe694bde735713122725ff573087e4b031358c1532eaeb11328cb8376095d7 +size 1274756352 diff --git a/MedQwen-3B-SFT-v2.Q3_K_L.gguf b/MedQwen-3B-SFT-v2.Q3_K_L.gguf new file mode 100644 index 0000000..9c84b7e --- /dev/null +++ b/MedQwen-3B-SFT-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a6116110cb2ff27216a86ba84640718ae5a3319f33d714df5befc8ef6fb2bf5 +size 1707392256 diff --git a/MedQwen-3B-SFT-v2.Q3_K_M.gguf b/MedQwen-3B-SFT-v2.Q3_K_M.gguf new file mode 100644 index 0000000..54c721e --- /dev/null +++ b/MedQwen-3B-SFT-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5d4bee1d9b5ebaa2adf1c4a65f32dac6c01a901796d500a21ca65b481e0a0d8 +size 1590476032 diff --git a/MedQwen-3B-SFT-v2.Q3_K_S.gguf b/MedQwen-3B-SFT-v2.Q3_K_S.gguf new file mode 100644 index 0000000..3c88ed6 --- /dev/null +++ b/MedQwen-3B-SFT-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e92257a006bbe4f64ce717c906514cd2273a61e7da8ca73c458527f875122a49 +size 1454357760 diff --git a/MedQwen-3B-SFT-v2.Q4_K_M.gguf b/MedQwen-3B-SFT-v2.Q4_K_M.gguf new file mode 100644 index 0000000..e2e282d --- /dev/null +++ b/MedQwen-3B-SFT-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a83ef855f0fd684787c8e19563767569eb03e54c1416525b2bb2c0892614d8b0 +size 1929903360 diff --git a/MedQwen-3B-SFT-v2.Q4_K_S.gguf b/MedQwen-3B-SFT-v2.Q4_K_S.gguf new file mode 100644 index 0000000..8e1627d --- /dev/null +++ b/MedQwen-3B-SFT-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d70c9ae364a24205625fe3bd483eb774543bfcbb910242e35dcc098a707ba122 +size 1834384640 diff --git a/MedQwen-3B-SFT-v2.Q5_K_M.gguf b/MedQwen-3B-SFT-v2.Q5_K_M.gguf new file mode 100644 index 0000000..48b957a --- /dev/null +++ b/MedQwen-3B-SFT-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:472f129e59a199cc0b1574137b259b8175c0a1864b10f5b680035aaafeaec9e6 +size 2224815360 diff --git a/MedQwen-3B-SFT-v2.Q5_K_S.gguf b/MedQwen-3B-SFT-v2.Q5_K_S.gguf new file mode 100644 index 0000000..49f94a1 --- /dev/null +++ b/MedQwen-3B-SFT-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac17626193512d3a416a1c08b9d7873153f3857e7f51e331ae7c5aa7db1acbdd +size 2169666816 diff --git a/MedQwen-3B-SFT-v2.Q6_K.gguf b/MedQwen-3B-SFT-v2.Q6_K.gguf new file mode 100644 index 0000000..a7282af --- /dev/null +++ b/MedQwen-3B-SFT-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23f47c114a04f34c7e101c448e0004b0fd7ed2d57f0cd511949b179216f6dec9 +size 2538159360 diff --git a/MedQwen-3B-SFT-v2.Q8_0.gguf b/MedQwen-3B-SFT-v2.Q8_0.gguf new file mode 100644 index 0000000..a178bad --- /dev/null +++ b/MedQwen-3B-SFT-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0689e06c3600c6bd3fd92ce7ef05a51d93f23e4eb5bae6448cb6c66fa0134e40 +size 3285476608 diff --git a/MedQwen-3B-SFT-v2.f16.gguf b/MedQwen-3B-SFT-v2.f16.gguf new file mode 100644 index 0000000..b65b407 --- /dev/null +++ b/MedQwen-3B-SFT-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4658ea530783cda1a0e6e40a79e16275576c9dc6f9ac81c25936469a4ebcd1d +size 6178317568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3886b09 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: ntkhoi/MedQwen-3B-SFT-v2 +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/ntkhoi/MedQwen-3B-SFT-v2 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MedQwen-3B-SFT-v2-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/MedQwen-3B-SFT-v2-GGUF/resolve/main/MedQwen-3B-SFT-v2.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/MedQwen-3B-SFT-v2-GGUF/resolve/main/MedQwen-3B-SFT-v2.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/MedQwen-3B-SFT-v2-GGUF/resolve/main/MedQwen-3B-SFT-v2.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MedQwen-3B-SFT-v2-GGUF/resolve/main/MedQwen-3B-SFT-v2.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/MedQwen-3B-SFT-v2-GGUF/resolve/main/MedQwen-3B-SFT-v2.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/MedQwen-3B-SFT-v2-GGUF/resolve/main/MedQwen-3B-SFT-v2.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedQwen-3B-SFT-v2-GGUF/resolve/main/MedQwen-3B-SFT-v2.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedQwen-3B-SFT-v2-GGUF/resolve/main/MedQwen-3B-SFT-v2.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MedQwen-3B-SFT-v2-GGUF/resolve/main/MedQwen-3B-SFT-v2.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/MedQwen-3B-SFT-v2-GGUF/resolve/main/MedQwen-3B-SFT-v2.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MedQwen-3B-SFT-v2-GGUF/resolve/main/MedQwen-3B-SFT-v2.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MedQwen-3B-SFT-v2-GGUF/resolve/main/MedQwen-3B-SFT-v2.f16.gguf) | f16 | 6.3 | 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. + +