commit e4990151883f3e4f8166aff70ef4cdbd012a0f79 Author: ModelHub XC Date: Sun Jun 14 23:10:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/qwen3-1.7b-gsm8k-sft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0a0ef6e --- /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 +qwen3-1.7b-gsm8k-sft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-1.7b-gsm8k-sft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-1.7b-gsm8k-sft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-1.7b-gsm8k-sft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-1.7b-gsm8k-sft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-1.7b-gsm8k-sft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-1.7b-gsm8k-sft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-1.7b-gsm8k-sft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-1.7b-gsm8k-sft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-1.7b-gsm8k-sft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-1.7b-gsm8k-sft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +qwen3-1.7b-gsm8k-sft.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..604d107 --- /dev/null +++ b/README.md @@ -0,0 +1,82 @@ +--- +base_model: HuggingFaceTB/qwen3-1.7b-gsm8k-sft +datasets: +- openai/gsm8k +- meta-math/MetaMathQA +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- math +- gsm8k +- fine-tuned +- chain-of-thought +- reasoning +- gguf +--- +## About + + + + + + + + + +static quants of https://huggingface.co/HuggingFaceTB/qwen3-1.7b-gsm8k-sft + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#qwen3-1.7b-gsm8k-sft-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/qwen3-1.7b-gsm8k-sft-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/qwen3-1.7b-gsm8k-sft-GGUF/resolve/main/qwen3-1.7b-gsm8k-sft.Q2_K.gguf) | Q2_K | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-1.7b-gsm8k-sft-GGUF/resolve/main/qwen3-1.7b-gsm8k-sft.Q3_K_S.gguf) | Q3_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-1.7b-gsm8k-sft-GGUF/resolve/main/qwen3-1.7b-gsm8k-sft.Q3_K_M.gguf) | Q3_K_M | 1.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-1.7b-gsm8k-sft-GGUF/resolve/main/qwen3-1.7b-gsm8k-sft.Q3_K_L.gguf) | Q3_K_L | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-1.7b-gsm8k-sft-GGUF/resolve/main/qwen3-1.7b-gsm8k-sft.IQ4_XS.gguf) | IQ4_XS | 1.1 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-1.7b-gsm8k-sft-GGUF/resolve/main/qwen3-1.7b-gsm8k-sft.Q4_K_S.gguf) | Q4_K_S | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen3-1.7b-gsm8k-sft-GGUF/resolve/main/qwen3-1.7b-gsm8k-sft.Q4_K_M.gguf) | Q4_K_M | 1.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/qwen3-1.7b-gsm8k-sft-GGUF/resolve/main/qwen3-1.7b-gsm8k-sft.Q5_K_S.gguf) | Q5_K_S | 1.3 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-1.7b-gsm8k-sft-GGUF/resolve/main/qwen3-1.7b-gsm8k-sft.Q5_K_M.gguf) | Q5_K_M | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/qwen3-1.7b-gsm8k-sft-GGUF/resolve/main/qwen3-1.7b-gsm8k-sft.Q6_K.gguf) | Q6_K | 1.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-1.7b-gsm8k-sft-GGUF/resolve/main/qwen3-1.7b-gsm8k-sft.Q8_0.gguf) | Q8_0 | 1.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/qwen3-1.7b-gsm8k-sft-GGUF/resolve/main/qwen3-1.7b-gsm8k-sft.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/qwen3-1.7b-gsm8k-sft.IQ4_XS.gguf b/qwen3-1.7b-gsm8k-sft.IQ4_XS.gguf new file mode 100644 index 0000000..3167d81 --- /dev/null +++ b/qwen3-1.7b-gsm8k-sft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82f6324ebdeb5563ab2acfd89cc4d73e3f9d013c146597347861eefbae1669d2 +size 1016282240 diff --git a/qwen3-1.7b-gsm8k-sft.Q2_K.gguf b/qwen3-1.7b-gsm8k-sft.Q2_K.gguf new file mode 100644 index 0000000..7fdfc92 --- /dev/null +++ b/qwen3-1.7b-gsm8k-sft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e218f921f574acdda214d4913eb2426eb22af879be8e4f37cedc26d2d169e72b +size 777796736 diff --git a/qwen3-1.7b-gsm8k-sft.Q3_K_L.gguf b/qwen3-1.7b-gsm8k-sft.Q3_K_L.gguf new file mode 100644 index 0000000..a037348 --- /dev/null +++ b/qwen3-1.7b-gsm8k-sft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a316af667335e3beb50c1f5282c62015b216ae75c1b1b3b67f3fd128d352a42e +size 1003502720 diff --git a/qwen3-1.7b-gsm8k-sft.Q3_K_M.gguf b/qwen3-1.7b-gsm8k-sft.Q3_K_M.gguf new file mode 100644 index 0000000..66245fa --- /dev/null +++ b/qwen3-1.7b-gsm8k-sft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38c0e875648edaeb93dbb1a0a25cc9609a300dde682ad8854ef98ee03fdd434b +size 939539584 diff --git a/qwen3-1.7b-gsm8k-sft.Q3_K_S.gguf b/qwen3-1.7b-gsm8k-sft.Q3_K_S.gguf new file mode 100644 index 0000000..4c4f5c3 --- /dev/null +++ b/qwen3-1.7b-gsm8k-sft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a56fb353d7500fafd623caea5ae8c423e388fef8629836003e87a51e327207e8 +size 867253376 diff --git a/qwen3-1.7b-gsm8k-sft.Q4_K_M.gguf b/qwen3-1.7b-gsm8k-sft.Q4_K_M.gguf new file mode 100644 index 0000000..8287ce8 --- /dev/null +++ b/qwen3-1.7b-gsm8k-sft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eb3e08de345839716e8b67142208dd6715ada42006bef7ed6ec4e2a6bcb3f52 +size 1107410048 diff --git a/qwen3-1.7b-gsm8k-sft.Q4_K_S.gguf b/qwen3-1.7b-gsm8k-sft.Q4_K_S.gguf new file mode 100644 index 0000000..c512c8b --- /dev/null +++ b/qwen3-1.7b-gsm8k-sft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49d8e2fd785aa0843f61616e353a1f5604da30fe9f5d0279c4a26793d202cf97 +size 1060191360 diff --git a/qwen3-1.7b-gsm8k-sft.Q5_K_M.gguf b/qwen3-1.7b-gsm8k-sft.Q5_K_M.gguf new file mode 100644 index 0000000..a4958ea --- /dev/null +++ b/qwen3-1.7b-gsm8k-sft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b1189083c49146cab3ccfc3df281fd53ce6dd2d884c01f4210bdeac878ba5ea +size 1257880704 diff --git a/qwen3-1.7b-gsm8k-sft.Q5_K_S.gguf b/qwen3-1.7b-gsm8k-sft.Q5_K_S.gguf new file mode 100644 index 0000000..c438aa9 --- /dev/null +++ b/qwen3-1.7b-gsm8k-sft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d60316cd3fab2e8ed160e449e84e71264f56ef0edd8237ff572d3946720ea43 +size 1230584960 diff --git a/qwen3-1.7b-gsm8k-sft.Q6_K.gguf b/qwen3-1.7b-gsm8k-sft.Q6_K.gguf new file mode 100644 index 0000000..7714350 --- /dev/null +++ b/qwen3-1.7b-gsm8k-sft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3a5027803d33a2e19a465e46e537d9cb4d2aed0895f429a9327e25577ce3b61 +size 1417755776 diff --git a/qwen3-1.7b-gsm8k-sft.Q8_0.gguf b/qwen3-1.7b-gsm8k-sft.Q8_0.gguf new file mode 100644 index 0000000..8cb67d1 --- /dev/null +++ b/qwen3-1.7b-gsm8k-sft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b150718a168e010ec01793ac246338ea63f96154ea3dcf48dde37433442b312c +size 1834427520 diff --git a/qwen3-1.7b-gsm8k-sft.f16.gguf b/qwen3-1.7b-gsm8k-sft.f16.gguf new file mode 100644 index 0000000..095876d --- /dev/null +++ b/qwen3-1.7b-gsm8k-sft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c2700b9c7836e3563ec51bae9cf7b004d40f3296fe36f713640cb19938cf7e5 +size 3447350400