commit ed3d500feb117ac8badd682d83d9d63888b17e3b Author: ModelHub XC Date: Fri Aug 14 23:35:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/query-context-pruner-multilingual-Qwen3-1.7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..17a8118 --- /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 +query-context-pruner-multilingual-Qwen3-1.7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +query-context-pruner-multilingual-Qwen3-1.7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +query-context-pruner-multilingual-Qwen3-1.7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +query-context-pruner-multilingual-Qwen3-1.7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +query-context-pruner-multilingual-Qwen3-1.7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +query-context-pruner-multilingual-Qwen3-1.7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +query-context-pruner-multilingual-Qwen3-1.7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +query-context-pruner-multilingual-Qwen3-1.7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +query-context-pruner-multilingual-Qwen3-1.7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +query-context-pruner-multilingual-Qwen3-1.7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +query-context-pruner-multilingual-Qwen3-1.7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +query-context-pruner-multilingual-Qwen3-1.7B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..4c66c57 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: hotchpotch/query-context-pruner-multilingual-Qwen3-1.7B +datasets: +- hotchpotch/qa-context-relevance-multilingual-140k +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/hotchpotch/query-context-pruner-multilingual-Qwen3-1.7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#query-context-pruner-multilingual-Qwen3-1.7B-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/query-context-pruner-multilingual-Qwen3-1.7B-GGUF/resolve/main/query-context-pruner-multilingual-Qwen3-1.7B.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/query-context-pruner-multilingual-Qwen3-1.7B-GGUF/resolve/main/query-context-pruner-multilingual-Qwen3-1.7B.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/query-context-pruner-multilingual-Qwen3-1.7B-GGUF/resolve/main/query-context-pruner-multilingual-Qwen3-1.7B.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/query-context-pruner-multilingual-Qwen3-1.7B-GGUF/resolve/main/query-context-pruner-multilingual-Qwen3-1.7B.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/query-context-pruner-multilingual-Qwen3-1.7B-GGUF/resolve/main/query-context-pruner-multilingual-Qwen3-1.7B.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/query-context-pruner-multilingual-Qwen3-1.7B-GGUF/resolve/main/query-context-pruner-multilingual-Qwen3-1.7B.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/query-context-pruner-multilingual-Qwen3-1.7B-GGUF/resolve/main/query-context-pruner-multilingual-Qwen3-1.7B.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/query-context-pruner-multilingual-Qwen3-1.7B-GGUF/resolve/main/query-context-pruner-multilingual-Qwen3-1.7B.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/query-context-pruner-multilingual-Qwen3-1.7B-GGUF/resolve/main/query-context-pruner-multilingual-Qwen3-1.7B.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/query-context-pruner-multilingual-Qwen3-1.7B-GGUF/resolve/main/query-context-pruner-multilingual-Qwen3-1.7B.Q6_K.gguf) | Q6_K | 1.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/query-context-pruner-multilingual-Qwen3-1.7B-GGUF/resolve/main/query-context-pruner-multilingual-Qwen3-1.7B.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/query-context-pruner-multilingual-Qwen3-1.7B-GGUF/resolve/main/query-context-pruner-multilingual-Qwen3-1.7B.f16.gguf) | f16 | 3.5 | 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/query-context-pruner-multilingual-Qwen3-1.7B.IQ4_XS.gguf b/query-context-pruner-multilingual-Qwen3-1.7B.IQ4_XS.gguf new file mode 100644 index 0000000..43da325 --- /dev/null +++ b/query-context-pruner-multilingual-Qwen3-1.7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80836942c4a204fd289464034b57311070fe708ffa6c47e3ee2bb134366a05d1 +size 1016281888 diff --git a/query-context-pruner-multilingual-Qwen3-1.7B.Q2_K.gguf b/query-context-pruner-multilingual-Qwen3-1.7B.Q2_K.gguf new file mode 100644 index 0000000..752861d --- /dev/null +++ b/query-context-pruner-multilingual-Qwen3-1.7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5834548ad93cbd9c9f3684d992fcc71685b7d30e744b2baa2b26a163830a0964 +size 777796384 diff --git a/query-context-pruner-multilingual-Qwen3-1.7B.Q3_K_L.gguf b/query-context-pruner-multilingual-Qwen3-1.7B.Q3_K_L.gguf new file mode 100644 index 0000000..ae17991 --- /dev/null +++ b/query-context-pruner-multilingual-Qwen3-1.7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07fc1a2ebbac7f6696a4ed829ea3756b55aef48f247f66d946d272c9cad390ed +size 1003502368 diff --git a/query-context-pruner-multilingual-Qwen3-1.7B.Q3_K_M.gguf b/query-context-pruner-multilingual-Qwen3-1.7B.Q3_K_M.gguf new file mode 100644 index 0000000..a96047e --- /dev/null +++ b/query-context-pruner-multilingual-Qwen3-1.7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e803d3e38889c78c6b6bc99deafc095c12914a7096099937d12e475fbd9199db +size 939539232 diff --git a/query-context-pruner-multilingual-Qwen3-1.7B.Q3_K_S.gguf b/query-context-pruner-multilingual-Qwen3-1.7B.Q3_K_S.gguf new file mode 100644 index 0000000..4e7ccb4 --- /dev/null +++ b/query-context-pruner-multilingual-Qwen3-1.7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb05b883c83afc865c371f4e165eba13d7f5879386d3d170b6641b0c0a937ecd +size 867253024 diff --git a/query-context-pruner-multilingual-Qwen3-1.7B.Q4_K_M.gguf b/query-context-pruner-multilingual-Qwen3-1.7B.Q4_K_M.gguf new file mode 100644 index 0000000..f51d25a --- /dev/null +++ b/query-context-pruner-multilingual-Qwen3-1.7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34500e272946aad2246646085e84e2b7efafbda7cc08b56783a75eecdfbe17ef +size 1107409696 diff --git a/query-context-pruner-multilingual-Qwen3-1.7B.Q4_K_S.gguf b/query-context-pruner-multilingual-Qwen3-1.7B.Q4_K_S.gguf new file mode 100644 index 0000000..0075607 --- /dev/null +++ b/query-context-pruner-multilingual-Qwen3-1.7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48865f9bf815d18ef8f89c3cb2ac0cddb57af4f5d9c7eeebf278131aafd2d0c8 +size 1060191008 diff --git a/query-context-pruner-multilingual-Qwen3-1.7B.Q5_K_M.gguf b/query-context-pruner-multilingual-Qwen3-1.7B.Q5_K_M.gguf new file mode 100644 index 0000000..e6520cf --- /dev/null +++ b/query-context-pruner-multilingual-Qwen3-1.7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:756931dfb427f92717b5093c9ab7bafd49b959dcaa55cb86a7808eb3658bbfa1 +size 1257880352 diff --git a/query-context-pruner-multilingual-Qwen3-1.7B.Q5_K_S.gguf b/query-context-pruner-multilingual-Qwen3-1.7B.Q5_K_S.gguf new file mode 100644 index 0000000..36827f9 --- /dev/null +++ b/query-context-pruner-multilingual-Qwen3-1.7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9dd948dd7366c48aa58e338ebc14597c2b4caa3cb4e688a6e596e4b5549d1d6 +size 1230584608 diff --git a/query-context-pruner-multilingual-Qwen3-1.7B.Q6_K.gguf b/query-context-pruner-multilingual-Qwen3-1.7B.Q6_K.gguf new file mode 100644 index 0000000..97abab9 --- /dev/null +++ b/query-context-pruner-multilingual-Qwen3-1.7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b1a50f50b2b8b55f27f020b40fff0989d355b6c2f08537253999e95b085a993 +size 1417755424 diff --git a/query-context-pruner-multilingual-Qwen3-1.7B.Q8_0.gguf b/query-context-pruner-multilingual-Qwen3-1.7B.Q8_0.gguf new file mode 100644 index 0000000..b7a0a56 --- /dev/null +++ b/query-context-pruner-multilingual-Qwen3-1.7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32b47c5977bca00aef6cf69282dbb6ae68fe90f1667c7395e1bdf213b586f2c8 +size 1834427168 diff --git a/query-context-pruner-multilingual-Qwen3-1.7B.f16.gguf b/query-context-pruner-multilingual-Qwen3-1.7B.f16.gguf new file mode 100644 index 0000000..9769ff2 --- /dev/null +++ b/query-context-pruner-multilingual-Qwen3-1.7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b287b04d82d1ce948c6d7fceb10ecd1ba13387bbc5b1cb21ae6924eb7787af17 +size 3447350048