commit 1dc367da29f7bde4f87bdceee3958515033acca5 Author: ModelHub XC Date: Sun Aug 9 11:55:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-Embedding-Medical-0.6B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..92d9094 --- /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 +Qwen3-Embedding-Medical-0.6B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Embedding-Medical-0.6B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Embedding-Medical-0.6B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Embedding-Medical-0.6B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Embedding-Medical-0.6B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Embedding-Medical-0.6B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Embedding-Medical-0.6B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Embedding-Medical-0.6B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Embedding-Medical-0.6B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Embedding-Medical-0.6B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Embedding-Medical-0.6B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-Embedding-Medical-0.6B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-Embedding-Medical-0.6B.IQ4_XS.gguf b/Qwen3-Embedding-Medical-0.6B.IQ4_XS.gguf new file mode 100644 index 0000000..bfcac7f --- /dev/null +++ b/Qwen3-Embedding-Medical-0.6B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e938625b856d96f2b4b15a6a3958155d8a073594f1f76260dbae4cac771076f +size 369048640 diff --git a/Qwen3-Embedding-Medical-0.6B.Q2_K.gguf b/Qwen3-Embedding-Medical-0.6B.Q2_K.gguf new file mode 100644 index 0000000..e1e60bd --- /dev/null +++ b/Qwen3-Embedding-Medical-0.6B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75c2028903081b793235646f2abe5cf869a21b117d7f6d096fcdc862b2f69533 +size 296008768 diff --git a/Qwen3-Embedding-Medical-0.6B.Q3_K_L.gguf b/Qwen3-Embedding-Medical-0.6B.Q3_K_L.gguf new file mode 100644 index 0000000..68d5a44 --- /dev/null +++ b/Qwen3-Embedding-Medical-0.6B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ea7c41d4d1ba177e88d2a24112db3dee3e1c5315b9818e3b143c37d392bc206 +size 368262208 diff --git a/Qwen3-Embedding-Medical-0.6B.Q3_K_M.gguf b/Qwen3-Embedding-Medical-0.6B.Q3_K_M.gguf new file mode 100644 index 0000000..a35c90d --- /dev/null +++ b/Qwen3-Embedding-Medical-0.6B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34068931d534d776b0190f8528cd9fcd602c899f86cf4f45e05559bcc3665af8 +size 346897472 diff --git a/Qwen3-Embedding-Medical-0.6B.Q3_K_S.gguf b/Qwen3-Embedding-Medical-0.6B.Q3_K_S.gguf new file mode 100644 index 0000000..c660fde --- /dev/null +++ b/Qwen3-Embedding-Medical-0.6B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8218082c7f15029741a1dc39717898b59ebf36d4991947c1d460b2d2d620979 +size 322845760 diff --git a/Qwen3-Embedding-Medical-0.6B.Q4_K_M.gguf b/Qwen3-Embedding-Medical-0.6B.Q4_K_M.gguf new file mode 100644 index 0000000..1712103 --- /dev/null +++ b/Qwen3-Embedding-Medical-0.6B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e44fb9583d600dd7d8336a22904d9a5327f93dd710168d63804b49e849fa54ad +size 396475456 diff --git a/Qwen3-Embedding-Medical-0.6B.Q4_K_S.gguf b/Qwen3-Embedding-Medical-0.6B.Q4_K_S.gguf new file mode 100644 index 0000000..e078c6a --- /dev/null +++ b/Qwen3-Embedding-Medical-0.6B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56b1310885b0c2f950a2f46495c30d24436f89362c678c978df43a1d0acadd16 +size 383040576 diff --git a/Qwen3-Embedding-Medical-0.6B.Q5_K_M.gguf b/Qwen3-Embedding-Medical-0.6B.Q5_K_M.gguf new file mode 100644 index 0000000..001c5ac --- /dev/null +++ b/Qwen3-Embedding-Medical-0.6B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fb7bc8ba7b969ea5a395f6d6e2939f3d72c8d7d265e91291c9e16e055107b4a +size 444185664 diff --git a/Qwen3-Embedding-Medical-0.6B.Q5_K_S.gguf b/Qwen3-Embedding-Medical-0.6B.Q5_K_S.gguf new file mode 100644 index 0000000..32bfa37 --- /dev/null +++ b/Qwen3-Embedding-Medical-0.6B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a3c3bfa4c80d3bf8f42202c4017e42d68658f8c14c620df78dbd6a3c45e56d0 +size 436386880 diff --git a/Qwen3-Embedding-Medical-0.6B.Q6_K.gguf b/Qwen3-Embedding-Medical-0.6B.Q6_K.gguf new file mode 100644 index 0000000..da0af54 --- /dev/null +++ b/Qwen3-Embedding-Medical-0.6B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b90920423945a338aeca94a824ac08e73ab653adeb39a96719e4c0b451056cc +size 494877760 diff --git a/Qwen3-Embedding-Medical-0.6B.Q8_0.gguf b/Qwen3-Embedding-Medical-0.6B.Q8_0.gguf new file mode 100644 index 0000000..ba00f6a --- /dev/null +++ b/Qwen3-Embedding-Medical-0.6B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c6fa23afd4f4117679e4d4314d441d6b2d5d018a5b08e91d352887cf78080db +size 639151488 diff --git a/Qwen3-Embedding-Medical-0.6B.f16.gguf b/Qwen3-Embedding-Medical-0.6B.f16.gguf new file mode 100644 index 0000000..abe56c6 --- /dev/null +++ b/Qwen3-Embedding-Medical-0.6B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f437a78598f6ff94ce1dd091348e7cc6bfbea55094a414c74bff9e7370350d93 +size 1197630528 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b2652f1 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: lastmass/Qwen3-Embedding-Medical-0.6B +datasets: +- FreedomIntelligence/huatuo_encyclopedia_qa +language: +- zh +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- sentence-transformers +- sentence-similarity +- feature-extraction +- dense +- generated_from_trainer +- dataset_size:362420 +- loss:MultipleNegativesRankingLoss +--- +## About + + + + + + + + + +static quants of https://huggingface.co/lastmass/Qwen3-Embedding-Medical-0.6B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-Embedding-Medical-0.6B-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/Qwen3-Embedding-Medical-0.6B-GGUF/resolve/main/Qwen3-Embedding-Medical-0.6B.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Embedding-Medical-0.6B-GGUF/resolve/main/Qwen3-Embedding-Medical-0.6B.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Embedding-Medical-0.6B-GGUF/resolve/main/Qwen3-Embedding-Medical-0.6B.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Embedding-Medical-0.6B-GGUF/resolve/main/Qwen3-Embedding-Medical-0.6B.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Embedding-Medical-0.6B-GGUF/resolve/main/Qwen3-Embedding-Medical-0.6B.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Embedding-Medical-0.6B-GGUF/resolve/main/Qwen3-Embedding-Medical-0.6B.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Embedding-Medical-0.6B-GGUF/resolve/main/Qwen3-Embedding-Medical-0.6B.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Embedding-Medical-0.6B-GGUF/resolve/main/Qwen3-Embedding-Medical-0.6B.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Embedding-Medical-0.6B-GGUF/resolve/main/Qwen3-Embedding-Medical-0.6B.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Embedding-Medical-0.6B-GGUF/resolve/main/Qwen3-Embedding-Medical-0.6B.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Embedding-Medical-0.6B-GGUF/resolve/main/Qwen3-Embedding-Medical-0.6B.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-Embedding-Medical-0.6B-GGUF/resolve/main/Qwen3-Embedding-Medical-0.6B.f16.gguf) | f16 | 1.3 | 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. + +