commit a37d01bba4a57d6f2cc47f6cfeab5d44424ea974 Author: ModelHub XC Date: Sat Jul 4 23:10:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/QueryRefiner-0.5B-v0.1-SFT-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..82290cb --- /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 +QueryRefiner-0.5B-v0.1-SFT.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +QueryRefiner-0.5B-v0.1-SFT.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +QueryRefiner-0.5B-v0.1-SFT.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +QueryRefiner-0.5B-v0.1-SFT.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QueryRefiner-0.5B-v0.1-SFT.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QueryRefiner-0.5B-v0.1-SFT.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QueryRefiner-0.5B-v0.1-SFT.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QueryRefiner-0.5B-v0.1-SFT.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +QueryRefiner-0.5B-v0.1-SFT.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +QueryRefiner-0.5B-v0.1-SFT.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +QueryRefiner-0.5B-v0.1-SFT.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +QueryRefiner-0.5B-v0.1-SFT.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/QueryRefiner-0.5B-v0.1-SFT.IQ4_XS.gguf b/QueryRefiner-0.5B-v0.1-SFT.IQ4_XS.gguf new file mode 100644 index 0000000..d14b962 --- /dev/null +++ b/QueryRefiner-0.5B-v0.1-SFT.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9385ae0b602c03dd110dac396ccc4e464e34d55ed2d24b0b7b095693d2c660b1 +size 351445856 diff --git a/QueryRefiner-0.5B-v0.1-SFT.Q2_K.gguf b/QueryRefiner-0.5B-v0.1-SFT.Q2_K.gguf new file mode 100644 index 0000000..63f179b --- /dev/null +++ b/QueryRefiner-0.5B-v0.1-SFT.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51dbd5ce03c32642ed8d8a3eba5fb95e4fbd5a0b04deef71bb7b0670466b9490 +size 338607968 diff --git a/QueryRefiner-0.5B-v0.1-SFT.Q3_K_L.gguf b/QueryRefiner-0.5B-v0.1-SFT.Q3_K_L.gguf new file mode 100644 index 0000000..a8c60f3 --- /dev/null +++ b/QueryRefiner-0.5B-v0.1-SFT.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a85f554c1535e0fdc77c9bf471b1ff861758854a20377ae6fc8b8a995cb5222 +size 369358688 diff --git a/QueryRefiner-0.5B-v0.1-SFT.Q3_K_M.gguf b/QueryRefiner-0.5B-v0.1-SFT.Q3_K_M.gguf new file mode 100644 index 0000000..dcd58c2 --- /dev/null +++ b/QueryRefiner-0.5B-v0.1-SFT.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41a4ad0a7a330718ae699d80488df89a269f1bc832281286d9198f3144f805d9 +size 355467104 diff --git a/QueryRefiner-0.5B-v0.1-SFT.Q3_K_S.gguf b/QueryRefiner-0.5B-v0.1-SFT.Q3_K_S.gguf new file mode 100644 index 0000000..f579206 --- /dev/null +++ b/QueryRefiner-0.5B-v0.1-SFT.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a5dbcd02d7d96a9a5d1e3a1e665c234c57b782457c0e433a85db967b7e50c90 +size 338263904 diff --git a/QueryRefiner-0.5B-v0.1-SFT.Q4_K_M.gguf b/QueryRefiner-0.5B-v0.1-SFT.Q4_K_M.gguf new file mode 100644 index 0000000..e06d32f --- /dev/null +++ b/QueryRefiner-0.5B-v0.1-SFT.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab823d67b557b23dfcdb7804556d1ba11a1ce3b6385b7bc84867bd2a23421c05 +size 397808480 diff --git a/QueryRefiner-0.5B-v0.1-SFT.Q4_K_S.gguf b/QueryRefiner-0.5B-v0.1-SFT.Q4_K_S.gguf new file mode 100644 index 0000000..c06a048 --- /dev/null +++ b/QueryRefiner-0.5B-v0.1-SFT.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d2a9d67c8a4164e35d4215f82f56e4d3effa3edc61171406e6294e48b8094b4 +size 385472352 diff --git a/QueryRefiner-0.5B-v0.1-SFT.Q5_K_M.gguf b/QueryRefiner-0.5B-v0.1-SFT.Q5_K_M.gguf new file mode 100644 index 0000000..76e0f50 --- /dev/null +++ b/QueryRefiner-0.5B-v0.1-SFT.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f1453dd694e57cb76b2032351e91a78bb2e7f8e4db085e0604c4df2fdf1bfe4 +size 420086624 diff --git a/QueryRefiner-0.5B-v0.1-SFT.Q5_K_S.gguf b/QueryRefiner-0.5B-v0.1-SFT.Q5_K_S.gguf new file mode 100644 index 0000000..a012107 --- /dev/null +++ b/QueryRefiner-0.5B-v0.1-SFT.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c93292b0a136981dedbc2408b8ed9095dfdda3609f72c3aab5a52c870d8a717f +size 412710752 diff --git a/QueryRefiner-0.5B-v0.1-SFT.Q6_K.gguf b/QueryRefiner-0.5B-v0.1-SFT.Q6_K.gguf new file mode 100644 index 0000000..cc0e546 --- /dev/null +++ b/QueryRefiner-0.5B-v0.1-SFT.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1142eb6db133e50728ab2f379cfeb85809e4df0bee6d7384269cf9d4bc8f8deb +size 505737056 diff --git a/QueryRefiner-0.5B-v0.1-SFT.Q8_0.gguf b/QueryRefiner-0.5B-v0.1-SFT.Q8_0.gguf new file mode 100644 index 0000000..9705a98 --- /dev/null +++ b/QueryRefiner-0.5B-v0.1-SFT.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbcddce55f3b955a7d9c3caf114b66de07fdc1142c7d8992bf904d8ec4fd736b +size 531068768 diff --git a/QueryRefiner-0.5B-v0.1-SFT.f16.gguf b/QueryRefiner-0.5B-v0.1-SFT.f16.gguf new file mode 100644 index 0000000..6a94f0d --- /dev/null +++ b/QueryRefiner-0.5B-v0.1-SFT.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:992c2922d2189bfe5bec5387b419ceccfd1fa513ff6a48dd06b2700f040403c0 +size 994157408 diff --git a/README.md b/README.md new file mode 100644 index 0000000..fb46e0c --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: krogoldAI/QueryRefiner-0.5B-v0.1-SFT +datasets: +- krogoldAI/rag-query-analysis +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/krogoldAI/QueryRefiner-0.5B-v0.1-SFT + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#QueryRefiner-0.5B-v0.1-SFT-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/QueryRefiner-0.5B-v0.1-SFT-GGUF/resolve/main/QueryRefiner-0.5B-v0.1-SFT.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/QueryRefiner-0.5B-v0.1-SFT-GGUF/resolve/main/QueryRefiner-0.5B-v0.1-SFT.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/QueryRefiner-0.5B-v0.1-SFT-GGUF/resolve/main/QueryRefiner-0.5B-v0.1-SFT.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QueryRefiner-0.5B-v0.1-SFT-GGUF/resolve/main/QueryRefiner-0.5B-v0.1-SFT.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/QueryRefiner-0.5B-v0.1-SFT-GGUF/resolve/main/QueryRefiner-0.5B-v0.1-SFT.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QueryRefiner-0.5B-v0.1-SFT-GGUF/resolve/main/QueryRefiner-0.5B-v0.1-SFT.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QueryRefiner-0.5B-v0.1-SFT-GGUF/resolve/main/QueryRefiner-0.5B-v0.1-SFT.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/QueryRefiner-0.5B-v0.1-SFT-GGUF/resolve/main/QueryRefiner-0.5B-v0.1-SFT.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QueryRefiner-0.5B-v0.1-SFT-GGUF/resolve/main/QueryRefiner-0.5B-v0.1-SFT.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/QueryRefiner-0.5B-v0.1-SFT-GGUF/resolve/main/QueryRefiner-0.5B-v0.1-SFT.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/QueryRefiner-0.5B-v0.1-SFT-GGUF/resolve/main/QueryRefiner-0.5B-v0.1-SFT.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/QueryRefiner-0.5B-v0.1-SFT-GGUF/resolve/main/QueryRefiner-0.5B-v0.1-SFT.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. + +