commit ddadd5968eed159227332a658428903c9e59533d Author: ModelHub XC Date: Mon Apr 13 21:33:06 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen-encoder-0.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6345c6 --- /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 +Qwen-encoder-0.5B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-encoder-0.5B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-encoder-0.5B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-encoder-0.5B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-encoder-0.5B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-encoder-0.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-encoder-0.5B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-encoder-0.5B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-encoder-0.5B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-encoder-0.5B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-encoder-0.5B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen-encoder-0.5B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen-encoder-0.5B.IQ4_XS.gguf b/Qwen-encoder-0.5B.IQ4_XS.gguf new file mode 100644 index 0000000..6dd1c1d --- /dev/null +++ b/Qwen-encoder-0.5B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d52a2c6ed0ba16205aec5b8e80d267443d95d63d89c4ef5993dbfd81b148475 +size 351443424 diff --git a/Qwen-encoder-0.5B.Q2_K.gguf b/Qwen-encoder-0.5B.Q2_K.gguf new file mode 100644 index 0000000..013d5a9 --- /dev/null +++ b/Qwen-encoder-0.5B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476ada8c650cfbe8776df6c4d1265f301c5206b15ae913df4756f1c7994602eb +size 338605536 diff --git a/Qwen-encoder-0.5B.Q3_K_L.gguf b/Qwen-encoder-0.5B.Q3_K_L.gguf new file mode 100644 index 0000000..a549b19 --- /dev/null +++ b/Qwen-encoder-0.5B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afdd276763bdab4b53bc86c566a73471fb0cd67706907c192e2d881a04f2361f +size 369356256 diff --git a/Qwen-encoder-0.5B.Q3_K_M.gguf b/Qwen-encoder-0.5B.Q3_K_M.gguf new file mode 100644 index 0000000..71b73dd --- /dev/null +++ b/Qwen-encoder-0.5B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6a533a8dc3d11f3c0a095958b6f229d856ddf1a718000040868524ea2645dc6 +size 355464672 diff --git a/Qwen-encoder-0.5B.Q3_K_S.gguf b/Qwen-encoder-0.5B.Q3_K_S.gguf new file mode 100644 index 0000000..fcbdf5c --- /dev/null +++ b/Qwen-encoder-0.5B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9c98b8e9a6020347a6b3ce4e8195f412b79d94c80599342596c9114a840fd57 +size 338261472 diff --git a/Qwen-encoder-0.5B.Q4_K_M.gguf b/Qwen-encoder-0.5B.Q4_K_M.gguf new file mode 100644 index 0000000..084e3ee --- /dev/null +++ b/Qwen-encoder-0.5B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1df367a0838de6d145315696a3dc2289a7cfaaf5b9a039b3985a0c9d1e5ff22 +size 397806048 diff --git a/Qwen-encoder-0.5B.Q4_K_S.gguf b/Qwen-encoder-0.5B.Q4_K_S.gguf new file mode 100644 index 0000000..a2e40dc --- /dev/null +++ b/Qwen-encoder-0.5B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0acc35910a7b4b45bf1890c987185a8530083ad438e70c781ab413afeddf16ef +size 385469920 diff --git a/Qwen-encoder-0.5B.Q5_K_M.gguf b/Qwen-encoder-0.5B.Q5_K_M.gguf new file mode 100644 index 0000000..25b17ff --- /dev/null +++ b/Qwen-encoder-0.5B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92bbb00d8b67b468a36a3b4cc7e4f234c237e3a6eeb0bc5679fe7cdf31396331 +size 420084192 diff --git a/Qwen-encoder-0.5B.Q5_K_S.gguf b/Qwen-encoder-0.5B.Q5_K_S.gguf new file mode 100644 index 0000000..d983724 --- /dev/null +++ b/Qwen-encoder-0.5B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:635a5bf5e507ce066204c68eb46cba22763205bb971afe2ac560a9876af25644 +size 412708320 diff --git a/Qwen-encoder-0.5B.Q6_K.gguf b/Qwen-encoder-0.5B.Q6_K.gguf new file mode 100644 index 0000000..c64aa57 --- /dev/null +++ b/Qwen-encoder-0.5B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26a58967b04eb860bfceed21539533b4bc2ee9f2a9330b5d0cab22231ef58ca7 +size 505734624 diff --git a/Qwen-encoder-0.5B.Q8_0.gguf b/Qwen-encoder-0.5B.Q8_0.gguf new file mode 100644 index 0000000..b908023 --- /dev/null +++ b/Qwen-encoder-0.5B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51d6b8ebcdf1aec7d4663357b2fee83e723128b27c423aa1710cec3db9858642 +size 531066336 diff --git a/Qwen-encoder-0.5B.f16.gguf b/Qwen-encoder-0.5B.f16.gguf new file mode 100644 index 0000000..7fd14f0 --- /dev/null +++ b/Qwen-encoder-0.5B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7c4958445fb3849a8e7afa801573ba7259e88577ea51aa4f82a211dc073ee55 +size 994154976 diff --git a/README.md b/README.md new file mode 100644 index 0000000..620f918 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: knowledgator/Qwen-encoder-0.5B +datasets: +- wikimedia/wikipedia +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- LLM2Vec +- encoder +- LLM +- classification +- NER +- question-answering +--- +## About + + + + + + +static quants of https://huggingface.co/knowledgator/Qwen-encoder-0.5B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen-encoder-0.5B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen-encoder-0.5B-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/Qwen-encoder-0.5B-GGUF/resolve/main/Qwen-encoder-0.5B.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-encoder-0.5B-GGUF/resolve/main/Qwen-encoder-0.5B.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-encoder-0.5B-GGUF/resolve/main/Qwen-encoder-0.5B.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-encoder-0.5B-GGUF/resolve/main/Qwen-encoder-0.5B.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-encoder-0.5B-GGUF/resolve/main/Qwen-encoder-0.5B.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-encoder-0.5B-GGUF/resolve/main/Qwen-encoder-0.5B.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-encoder-0.5B-GGUF/resolve/main/Qwen-encoder-0.5B.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen-encoder-0.5B-GGUF/resolve/main/Qwen-encoder-0.5B.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-encoder-0.5B-GGUF/resolve/main/Qwen-encoder-0.5B.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen-encoder-0.5B-GGUF/resolve/main/Qwen-encoder-0.5B.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-encoder-0.5B-GGUF/resolve/main/Qwen-encoder-0.5B.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen-encoder-0.5B-GGUF/resolve/main/Qwen-encoder-0.5B.f16.gguf) | f16 | 1.1 | 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. + +