commit b50ef5d19e467931c4066c5c48e1cf124e6c38e6 Author: ModelHub XC Date: Tue Apr 28 04:09:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Medical-NER-Qwen-4B-Thinking-merged-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0e4f26b --- /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 +Medical-NER-Qwen-4B-Thinking-merged.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Medical-NER-Qwen-4B-Thinking-merged.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Medical-NER-Qwen-4B-Thinking-merged.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Medical-NER-Qwen-4B-Thinking-merged.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Medical-NER-Qwen-4B-Thinking-merged.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Medical-NER-Qwen-4B-Thinking-merged.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Medical-NER-Qwen-4B-Thinking-merged.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Medical-NER-Qwen-4B-Thinking-merged.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Medical-NER-Qwen-4B-Thinking-merged.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Medical-NER-Qwen-4B-Thinking-merged.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Medical-NER-Qwen-4B-Thinking-merged.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Medical-NER-Qwen-4B-Thinking-merged.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Medical-NER-Qwen-4B-Thinking-merged.IQ4_XS.gguf b/Medical-NER-Qwen-4B-Thinking-merged.IQ4_XS.gguf new file mode 100644 index 0000000..b302da7 --- /dev/null +++ b/Medical-NER-Qwen-4B-Thinking-merged.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:597063efa57082360ad03b9818d24b9130e074e05feb35bf9e3e04cb9817b23c +size 2286316768 diff --git a/Medical-NER-Qwen-4B-Thinking-merged.Q2_K.gguf b/Medical-NER-Qwen-4B-Thinking-merged.Q2_K.gguf new file mode 100644 index 0000000..c86ed48 --- /dev/null +++ b/Medical-NER-Qwen-4B-Thinking-merged.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba50bcab8891c87e8e7433b37fa60a92cd509e8705a649d47c2b772478588128 +size 1669500128 diff --git a/Medical-NER-Qwen-4B-Thinking-merged.Q3_K_L.gguf b/Medical-NER-Qwen-4B-Thinking-merged.Q3_K_L.gguf new file mode 100644 index 0000000..45a9cd3 --- /dev/null +++ b/Medical-NER-Qwen-4B-Thinking-merged.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d82c0998755244ef1dd9f0d871629ce4b7bf2b3ce5c5fc873b6a792052dd1e2 +size 2239786208 diff --git a/Medical-NER-Qwen-4B-Thinking-merged.Q3_K_M.gguf b/Medical-NER-Qwen-4B-Thinking-merged.Q3_K_M.gguf new file mode 100644 index 0000000..29effe6 --- /dev/null +++ b/Medical-NER-Qwen-4B-Thinking-merged.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b58c86869fdfaa860a9554de0a75e45a809f38bd2ec89b6c3acbb55e3373fe47 +size 2075618528 diff --git a/Medical-NER-Qwen-4B-Thinking-merged.Q3_K_S.gguf b/Medical-NER-Qwen-4B-Thinking-merged.Q3_K_S.gguf new file mode 100644 index 0000000..02af74f --- /dev/null +++ b/Medical-NER-Qwen-4B-Thinking-merged.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d475afeedb74098217c5aad992b24e84105028e26bdf745a6128f74088cbe851 +size 1886997728 diff --git a/Medical-NER-Qwen-4B-Thinking-merged.Q4_K_M.gguf b/Medical-NER-Qwen-4B-Thinking-merged.Q4_K_M.gguf new file mode 100644 index 0000000..0de088b --- /dev/null +++ b/Medical-NER-Qwen-4B-Thinking-merged.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ce6483a8847a56324223d49af831a1e6b7167e180ebc7597731036bb99543b +size 2497281248 diff --git a/Medical-NER-Qwen-4B-Thinking-merged.Q4_K_S.gguf b/Medical-NER-Qwen-4B-Thinking-merged.Q4_K_S.gguf new file mode 100644 index 0000000..107eff5 --- /dev/null +++ b/Medical-NER-Qwen-4B-Thinking-merged.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:507b452df1a929b2d4b7ae9468f116be18e0c1c51b8827c8f00e48e234d03453 +size 2383310048 diff --git a/Medical-NER-Qwen-4B-Thinking-merged.Q5_K_M.gguf b/Medical-NER-Qwen-4B-Thinking-merged.Q5_K_M.gguf new file mode 100644 index 0000000..188e776 --- /dev/null +++ b/Medical-NER-Qwen-4B-Thinking-merged.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1de77a024b6b50209fede02f9325d664f8ec266ec252bce6319cab4a9abe05d1 +size 2889514208 diff --git a/Medical-NER-Qwen-4B-Thinking-merged.Q5_K_S.gguf b/Medical-NER-Qwen-4B-Thinking-merged.Q5_K_S.gguf new file mode 100644 index 0000000..172e3ed --- /dev/null +++ b/Medical-NER-Qwen-4B-Thinking-merged.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1815762ae0f9a87eca0e24fb3a8c4103075f6cc6f90b4c9dcc00a00d81b29ea5 +size 2823711968 diff --git a/Medical-NER-Qwen-4B-Thinking-merged.Q6_K.gguf b/Medical-NER-Qwen-4B-Thinking-merged.Q6_K.gguf new file mode 100644 index 0000000..2c749ac --- /dev/null +++ b/Medical-NER-Qwen-4B-Thinking-merged.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f548b580657ffbdc7035a6c275f083e06884cb74900e83fe5d6608f5df3e586 +size 3306261728 diff --git a/Medical-NER-Qwen-4B-Thinking-merged.Q8_0.gguf b/Medical-NER-Qwen-4B-Thinking-merged.Q8_0.gguf new file mode 100644 index 0000000..bd7d194 --- /dev/null +++ b/Medical-NER-Qwen-4B-Thinking-merged.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4fc9e5644236e5caec4ad3f1bbbbfd8dcabdbadfca2cd170fc62fdc356b718c +size 4280405728 diff --git a/Medical-NER-Qwen-4B-Thinking-merged.f16.gguf b/Medical-NER-Qwen-4B-Thinking-merged.f16.gguf new file mode 100644 index 0000000..b90ee16 --- /dev/null +++ b/Medical-NER-Qwen-4B-Thinking-merged.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8de34ed841486e5b7f1a6ad8bb6f6cdf4f2e7dc0d9f8c1cc6d71f7c48c0f52a6 +size 8051285728 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d7e5057 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: xingqiang/Medical-NER-Qwen-4B-Thinking-merged +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/xingqiang/Medical-NER-Qwen-4B-Thinking-merged + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Medical-NER-Qwen-4B-Thinking-merged-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/Medical-NER-Qwen-4B-Thinking-merged-GGUF/resolve/main/Medical-NER-Qwen-4B-Thinking-merged.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Medical-NER-Qwen-4B-Thinking-merged-GGUF/resolve/main/Medical-NER-Qwen-4B-Thinking-merged.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Medical-NER-Qwen-4B-Thinking-merged-GGUF/resolve/main/Medical-NER-Qwen-4B-Thinking-merged.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Medical-NER-Qwen-4B-Thinking-merged-GGUF/resolve/main/Medical-NER-Qwen-4B-Thinking-merged.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Medical-NER-Qwen-4B-Thinking-merged-GGUF/resolve/main/Medical-NER-Qwen-4B-Thinking-merged.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Medical-NER-Qwen-4B-Thinking-merged-GGUF/resolve/main/Medical-NER-Qwen-4B-Thinking-merged.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Medical-NER-Qwen-4B-Thinking-merged-GGUF/resolve/main/Medical-NER-Qwen-4B-Thinking-merged.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Medical-NER-Qwen-4B-Thinking-merged-GGUF/resolve/main/Medical-NER-Qwen-4B-Thinking-merged.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Medical-NER-Qwen-4B-Thinking-merged-GGUF/resolve/main/Medical-NER-Qwen-4B-Thinking-merged.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Medical-NER-Qwen-4B-Thinking-merged-GGUF/resolve/main/Medical-NER-Qwen-4B-Thinking-merged.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Medical-NER-Qwen-4B-Thinking-merged-GGUF/resolve/main/Medical-NER-Qwen-4B-Thinking-merged.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Medical-NER-Qwen-4B-Thinking-merged-GGUF/resolve/main/Medical-NER-Qwen-4B-Thinking-merged.f16.gguf) | f16 | 8.2 | 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. + +