commit 3c7d00c362a2401411002b929b51fea25dd23c09 Author: ModelHub XC Date: Tue Oct 13 16:02:25 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen3-4B-tau2-sft-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..76eadbe --- /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 +Qwen3-4B-tau2-sft.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-sft.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-sft.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-sft.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-sft.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-sft.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-sft.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-sft.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-sft.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-sft.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-sft.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen3-4B-tau2-sft.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen3-4B-tau2-sft.IQ4_XS.gguf b/Qwen3-4B-tau2-sft.IQ4_XS.gguf new file mode 100644 index 0000000..5f73b9d --- /dev/null +++ b/Qwen3-4B-tau2-sft.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a9945be294849739b6eb8e5b8fa864ec398fc443bbdb744c2c89583a0b6ae12 +size 2286315072 diff --git a/Qwen3-4B-tau2-sft.Q2_K.gguf b/Qwen3-4B-tau2-sft.Q2_K.gguf new file mode 100644 index 0000000..a5df6e0 --- /dev/null +++ b/Qwen3-4B-tau2-sft.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f963fd53fc427047777533f9b40d27a14098c7e78bce8e36490e8b1ca9f8b008 +size 1669498432 diff --git a/Qwen3-4B-tau2-sft.Q3_K_L.gguf b/Qwen3-4B-tau2-sft.Q3_K_L.gguf new file mode 100644 index 0000000..d64c8ab --- /dev/null +++ b/Qwen3-4B-tau2-sft.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5730240f2642d748191ef538ecdc1556be9eea04186ee190133d634b2885d30a +size 2239784512 diff --git a/Qwen3-4B-tau2-sft.Q3_K_M.gguf b/Qwen3-4B-tau2-sft.Q3_K_M.gguf new file mode 100644 index 0000000..b035bd8 --- /dev/null +++ b/Qwen3-4B-tau2-sft.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97ed4cc99533939d26c65c58839a6ed7df53d75b9d246296ca49d11b8aaf0320 +size 2075616832 diff --git a/Qwen3-4B-tau2-sft.Q3_K_S.gguf b/Qwen3-4B-tau2-sft.Q3_K_S.gguf new file mode 100644 index 0000000..995070d --- /dev/null +++ b/Qwen3-4B-tau2-sft.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67e5e29f41cd684048b4936b9b1ac25393a207637c86b3dc1e9ab292aa855401 +size 1886996032 diff --git a/Qwen3-4B-tau2-sft.Q4_K_M.gguf b/Qwen3-4B-tau2-sft.Q4_K_M.gguf new file mode 100644 index 0000000..6e86f9b --- /dev/null +++ b/Qwen3-4B-tau2-sft.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7477935b9d735a5b4c1f97627c20642309c50af28c0419409ce342930febd430 +size 2497279552 diff --git a/Qwen3-4B-tau2-sft.Q4_K_S.gguf b/Qwen3-4B-tau2-sft.Q4_K_S.gguf new file mode 100644 index 0000000..88533d5 --- /dev/null +++ b/Qwen3-4B-tau2-sft.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15ab5848ea8284c7a360fdd9d459d17d34ee086dedc57692edbfc48dee56d494 +size 2383308352 diff --git a/Qwen3-4B-tau2-sft.Q5_K_M.gguf b/Qwen3-4B-tau2-sft.Q5_K_M.gguf new file mode 100644 index 0000000..98d04c4 --- /dev/null +++ b/Qwen3-4B-tau2-sft.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eff9220546dbc4e4024c10b0aa010bc65be576728948928040a07e84c0084ae +size 2889512512 diff --git a/Qwen3-4B-tau2-sft.Q5_K_S.gguf b/Qwen3-4B-tau2-sft.Q5_K_S.gguf new file mode 100644 index 0000000..64093db --- /dev/null +++ b/Qwen3-4B-tau2-sft.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3134cca8b7d37f96256926b2aab4ad8ab91668420cbf8eabc735ea4abaf98140 +size 2823710272 diff --git a/Qwen3-4B-tau2-sft.Q6_K.gguf b/Qwen3-4B-tau2-sft.Q6_K.gguf new file mode 100644 index 0000000..d5e2616 --- /dev/null +++ b/Qwen3-4B-tau2-sft.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbaac955e2913593e72c22b7ac4b151e07960acd5cda251bebf30aeee3e724f6 +size 3306260032 diff --git a/Qwen3-4B-tau2-sft.Q8_0.gguf b/Qwen3-4B-tau2-sft.Q8_0.gguf new file mode 100644 index 0000000..944c231 --- /dev/null +++ b/Qwen3-4B-tau2-sft.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a686fa9ab0cab13f15b014d98bc040e985a999a69432d61d89e3cfe6bdf19fd +size 4280404032 diff --git a/Qwen3-4B-tau2-sft.f16.gguf b/Qwen3-4B-tau2-sft.f16.gguf new file mode 100644 index 0000000..46dcfaf --- /dev/null +++ b/Qwen3-4B-tau2-sft.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eeff45d2f38e6c52c879343e801cbedd73a6a56b6b8dc2a9a273e1808fccf54 +size 8051284032 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4c76977 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: zjxia/Qwen3-4B-tau2-sft +language: +- en +library_name: transformers +license: apache-2.0 +license_link: https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507/blob/main/LICENSE +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/zjxia/Qwen3-4B-tau2-sft + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen3-4B-tau2-sft-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-4B-tau2-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/Qwen3-4B-tau2-sft-GGUF/resolve/main/Qwen3-4B-tau2-sft.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-sft-GGUF/resolve/main/Qwen3-4B-tau2-sft.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-sft-GGUF/resolve/main/Qwen3-4B-tau2-sft.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-sft-GGUF/resolve/main/Qwen3-4B-tau2-sft.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-sft-GGUF/resolve/main/Qwen3-4B-tau2-sft.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-sft-GGUF/resolve/main/Qwen3-4B-tau2-sft.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-sft-GGUF/resolve/main/Qwen3-4B-tau2-sft.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-sft-GGUF/resolve/main/Qwen3-4B-tau2-sft.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-sft-GGUF/resolve/main/Qwen3-4B-tau2-sft.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-sft-GGUF/resolve/main/Qwen3-4B-tau2-sft.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-sft-GGUF/resolve/main/Qwen3-4B-tau2-sft.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen3-4B-tau2-sft-GGUF/resolve/main/Qwen3-4B-tau2-sft.f16.gguf) | f16 | 8.2 | 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. + +