commit 1ee789ee8f46a0a77914561ad9923673685fd48a Author: ModelHub XC Date: Thu Apr 16 17:51:56 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/E2Rank-0.6B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d36f26a --- /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 +E2Rank-0.6B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +E2Rank-0.6B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +E2Rank-0.6B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +E2Rank-0.6B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +E2Rank-0.6B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +E2Rank-0.6B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +E2Rank-0.6B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +E2Rank-0.6B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +E2Rank-0.6B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +E2Rank-0.6B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +E2Rank-0.6B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +E2Rank-0.6B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/E2Rank-0.6B.IQ4_XS.gguf b/E2Rank-0.6B.IQ4_XS.gguf new file mode 100644 index 0000000..c13a14b --- /dev/null +++ b/E2Rank-0.6B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bec7af6bd38b344a5bbf10442da490438d812064f1efdcea2c177e8993960b26 +size 369278784 diff --git a/E2Rank-0.6B.Q2_K.gguf b/E2Rank-0.6B.Q2_K.gguf new file mode 100644 index 0000000..ba32804 --- /dev/null +++ b/E2Rank-0.6B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97dee2fac215d1c0bc3fb610af96c1edfe7ad831d740be1c618d492a04533e39 +size 296238912 diff --git a/E2Rank-0.6B.Q3_K_L.gguf b/E2Rank-0.6B.Q3_K_L.gguf new file mode 100644 index 0000000..a5ae2f1 --- /dev/null +++ b/E2Rank-0.6B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:205790d047c452910379755f4679195b0a840b28ebc8285eaa4105a466d4e9d5 +size 368492352 diff --git a/E2Rank-0.6B.Q3_K_M.gguf b/E2Rank-0.6B.Q3_K_M.gguf new file mode 100644 index 0000000..1067212 --- /dev/null +++ b/E2Rank-0.6B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d4810c5a912102ebf918b2ad25295a34b215412466b938e1aa4857cec68ca67 +size 347127616 diff --git a/E2Rank-0.6B.Q3_K_S.gguf b/E2Rank-0.6B.Q3_K_S.gguf new file mode 100644 index 0000000..89a9164 --- /dev/null +++ b/E2Rank-0.6B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d975664c9b1126137577e5003816034e433d2b29806048b1be86a5e7708067a +size 323075904 diff --git a/E2Rank-0.6B.Q4_K_M.gguf b/E2Rank-0.6B.Q4_K_M.gguf new file mode 100644 index 0000000..b6e658c --- /dev/null +++ b/E2Rank-0.6B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8607c7527556895c889e7f69b5d85e1fb069b30c477b371fdb0dda20d432db1 +size 396705600 diff --git a/E2Rank-0.6B.Q4_K_S.gguf b/E2Rank-0.6B.Q4_K_S.gguf new file mode 100644 index 0000000..829e850 --- /dev/null +++ b/E2Rank-0.6B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23e5f235735d86f6147390a51ef49a126a1a58918f11c51cfa233435f68736ac +size 383270720 diff --git a/E2Rank-0.6B.Q5_K_M.gguf b/E2Rank-0.6B.Q5_K_M.gguf new file mode 100644 index 0000000..8b89d19 --- /dev/null +++ b/E2Rank-0.6B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b67a15e66cf67f06d8af58e3b88b982e0d8c531705cd2a05b23f7febd1e79d3 +size 444415808 diff --git a/E2Rank-0.6B.Q5_K_S.gguf b/E2Rank-0.6B.Q5_K_S.gguf new file mode 100644 index 0000000..451f28d --- /dev/null +++ b/E2Rank-0.6B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cebc21a7037ae185e07e61f1ac2901aa7978846988aeb44b448068b14565a65c +size 436617024 diff --git a/E2Rank-0.6B.Q6_K.gguf b/E2Rank-0.6B.Q6_K.gguf new file mode 100644 index 0000000..d3cbb32 --- /dev/null +++ b/E2Rank-0.6B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c741f1e8348a7a988ba24802499db1377326e7043b5b3b9e6832bba7972c92dd +size 495107904 diff --git a/E2Rank-0.6B.Q8_0.gguf b/E2Rank-0.6B.Q8_0.gguf new file mode 100644 index 0000000..4f94a18 --- /dev/null +++ b/E2Rank-0.6B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52a63daf6b314b461b0ec75a392d00feb0ad5958d9035049ab69692fde41e1d4 +size 639447872 diff --git a/E2Rank-0.6B.f16.gguf b/E2Rank-0.6B.f16.gguf new file mode 100644 index 0000000..550ce2c --- /dev/null +++ b/E2Rank-0.6B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b2cae87977c00d431ecce4299e96f46b1f832417379200ae17aea71b5726afb +size 1198183232 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b6f8c4b --- /dev/null +++ b/README.md @@ -0,0 +1,80 @@ +--- +base_model: Alibaba-NLP/E2Rank-0.6B +datasets: +- Alibaba-NLP/E2Rank_ranking_datasets +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- transformers +- sentence-similarity +- feature-extraction +- text-embeddings-inference +- reranking +--- +## About + + + + + + + + + +static quants of https://huggingface.co/Alibaba-NLP/E2Rank-0.6B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#E2Rank-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/E2Rank-0.6B-GGUF/resolve/main/E2Rank-0.6B.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/E2Rank-0.6B-GGUF/resolve/main/E2Rank-0.6B.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/E2Rank-0.6B-GGUF/resolve/main/E2Rank-0.6B.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/E2Rank-0.6B-GGUF/resolve/main/E2Rank-0.6B.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/E2Rank-0.6B-GGUF/resolve/main/E2Rank-0.6B.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/E2Rank-0.6B-GGUF/resolve/main/E2Rank-0.6B.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/E2Rank-0.6B-GGUF/resolve/main/E2Rank-0.6B.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/E2Rank-0.6B-GGUF/resolve/main/E2Rank-0.6B.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/E2Rank-0.6B-GGUF/resolve/main/E2Rank-0.6B.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/E2Rank-0.6B-GGUF/resolve/main/E2Rank-0.6B.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/E2Rank-0.6B-GGUF/resolve/main/E2Rank-0.6B.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/E2Rank-0.6B-GGUF/resolve/main/E2Rank-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. + +