commit 979e89a1302025de2a39438f7ce4784e844ca1a1 Author: ModelHub XC Date: Sat Jun 6 01:06:16 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/RTriever-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0ec1860 --- /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 +RTriever-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +RTriever-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +RTriever-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +RTriever-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RTriever-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RTriever-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RTriever-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RTriever-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +RTriever-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +RTriever-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +RTriever-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RTriever-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8610aac --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: yale-nlp/RTriever-4B +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- sentence-transformers +- text-embedding +- information-retrieval +- reasoning +- retrieval +--- +## About + + + + + + + + + +static quants of https://huggingface.co/yale-nlp/RTriever-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#RTriever-4B-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/RTriever-4B-GGUF/resolve/main/RTriever-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/RTriever-4B-GGUF/resolve/main/RTriever-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/RTriever-4B-GGUF/resolve/main/RTriever-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/RTriever-4B-GGUF/resolve/main/RTriever-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/RTriever-4B-GGUF/resolve/main/RTriever-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/RTriever-4B-GGUF/resolve/main/RTriever-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RTriever-4B-GGUF/resolve/main/RTriever-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/RTriever-4B-GGUF/resolve/main/RTriever-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/RTriever-4B-GGUF/resolve/main/RTriever-4B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/RTriever-4B-GGUF/resolve/main/RTriever-4B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/RTriever-4B-GGUF/resolve/main/RTriever-4B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/RTriever-4B-GGUF/resolve/main/RTriever-4B.f16.gguf) | f16 | 8.1 | 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. + + diff --git a/RTriever-4B.IQ4_XS.gguf b/RTriever-4B.IQ4_XS.gguf new file mode 100644 index 0000000..893adfb --- /dev/null +++ b/RTriever-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba3aa76de7dc7143199410308a4fd0afe9309bb584529379b20f5cb6471c3a5e +size 2285739776 diff --git a/RTriever-4B.Q2_K.gguf b/RTriever-4B.Q2_K.gguf new file mode 100644 index 0000000..77be7f3 --- /dev/null +++ b/RTriever-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:517798ba1017ff28a5051fb0443afe736353ce71d2d16b6441cc51057e3e3181 +size 1668923136 diff --git a/RTriever-4B.Q3_K_L.gguf b/RTriever-4B.Q3_K_L.gguf new file mode 100644 index 0000000..c11c264 --- /dev/null +++ b/RTriever-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10e18184df1a1726e04b4981445f835511a2047861be4dfb562dd4e8c2263370 +size 2239209216 diff --git a/RTriever-4B.Q3_K_M.gguf b/RTriever-4B.Q3_K_M.gguf new file mode 100644 index 0000000..1281f72 --- /dev/null +++ b/RTriever-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:815d748dc212287cd0a541f40aca5a3de5326470735f7a5ca13062a90b78128c +size 2075041536 diff --git a/RTriever-4B.Q3_K_S.gguf b/RTriever-4B.Q3_K_S.gguf new file mode 100644 index 0000000..5ce5218 --- /dev/null +++ b/RTriever-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26c83b2b284630d4041162bb71b60070edf3637c0a766f924d629044f99b3edb +size 1886420736 diff --git a/RTriever-4B.Q4_K_M.gguf b/RTriever-4B.Q4_K_M.gguf new file mode 100644 index 0000000..c4ebe7c --- /dev/null +++ b/RTriever-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62ae5ca40be56b984ac3ffcf9a8220748ae1abedd17578b88a5da0bfad4c4dfb +size 2496704256 diff --git a/RTriever-4B.Q4_K_S.gguf b/RTriever-4B.Q4_K_S.gguf new file mode 100644 index 0000000..f509cf0 --- /dev/null +++ b/RTriever-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97f7b84f2d8cd4de5645d8b81db247194f55dbd2c3d5eb894857bd98e775a20c +size 2382733056 diff --git a/RTriever-4B.Q5_K_M.gguf b/RTriever-4B.Q5_K_M.gguf new file mode 100644 index 0000000..b44d6a7 --- /dev/null +++ b/RTriever-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:908ffca994c82200e74711964a2cb2c30faf1385dcd5a63bd2855498ecbcf08e +size 2888937216 diff --git a/RTriever-4B.Q5_K_S.gguf b/RTriever-4B.Q5_K_S.gguf new file mode 100644 index 0000000..2788884 --- /dev/null +++ b/RTriever-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c755df11d3b5154565510d09d04f38fe47294ec533c59feb3985245e8c197ec8 +size 2823134976 diff --git a/RTriever-4B.Q6_K.gguf b/RTriever-4B.Q6_K.gguf new file mode 100644 index 0000000..04ca494 --- /dev/null +++ b/RTriever-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad7b608d0364b528b6b6ed3423e5f99f6bfaff8d32719997a7c24c3328f8f1f1 +size 3305684736 diff --git a/RTriever-4B.Q8_0.gguf b/RTriever-4B.Q8_0.gguf new file mode 100644 index 0000000..c0f9154 --- /dev/null +++ b/RTriever-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4976423e17f2973ac162eb77fec0f03f3203d834930b10727e322aaca57c1c87 +size 4279660704 diff --git a/RTriever-4B.f16.gguf b/RTriever-4B.f16.gguf new file mode 100644 index 0000000..99067f8 --- /dev/null +++ b/RTriever-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db698d9cf979dd09f170a53116d769230ce16c889a3f5bebba0bcf32b70aaddd +size 8049890304