commit 830c8324f73fc37e941b878040f18106b69a28be Author: ModelHub XC Date: Wed Jun 17 13:34:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/iflow-metadata-qwen3-4b-sft-128k-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4ecd002 --- /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 +iflow-metadata-qwen3-4b-sft-128k.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +iflow-metadata-qwen3-4b-sft-128k.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +iflow-metadata-qwen3-4b-sft-128k.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +iflow-metadata-qwen3-4b-sft-128k.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +iflow-metadata-qwen3-4b-sft-128k.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +iflow-metadata-qwen3-4b-sft-128k.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +iflow-metadata-qwen3-4b-sft-128k.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +iflow-metadata-qwen3-4b-sft-128k.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +iflow-metadata-qwen3-4b-sft-128k.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +iflow-metadata-qwen3-4b-sft-128k.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +iflow-metadata-qwen3-4b-sft-128k.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +iflow-metadata-qwen3-4b-sft-128k.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..fb3e771 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: DheepLearning/iflow-metadata-qwen3-4b-sft-128k +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen3 +--- +## About + + + + + + + + + +static quants of https://huggingface.co/DheepLearning/iflow-metadata-qwen3-4b-sft-128k + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#iflow-metadata-qwen3-4b-sft-128k-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/iflow-metadata-qwen3-4b-sft-128k-GGUF/resolve/main/iflow-metadata-qwen3-4b-sft-128k.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/iflow-metadata-qwen3-4b-sft-128k-GGUF/resolve/main/iflow-metadata-qwen3-4b-sft-128k.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/iflow-metadata-qwen3-4b-sft-128k-GGUF/resolve/main/iflow-metadata-qwen3-4b-sft-128k.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/iflow-metadata-qwen3-4b-sft-128k-GGUF/resolve/main/iflow-metadata-qwen3-4b-sft-128k.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/iflow-metadata-qwen3-4b-sft-128k-GGUF/resolve/main/iflow-metadata-qwen3-4b-sft-128k.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/iflow-metadata-qwen3-4b-sft-128k-GGUF/resolve/main/iflow-metadata-qwen3-4b-sft-128k.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/iflow-metadata-qwen3-4b-sft-128k-GGUF/resolve/main/iflow-metadata-qwen3-4b-sft-128k.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/iflow-metadata-qwen3-4b-sft-128k-GGUF/resolve/main/iflow-metadata-qwen3-4b-sft-128k.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/iflow-metadata-qwen3-4b-sft-128k-GGUF/resolve/main/iflow-metadata-qwen3-4b-sft-128k.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/iflow-metadata-qwen3-4b-sft-128k-GGUF/resolve/main/iflow-metadata-qwen3-4b-sft-128k.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/iflow-metadata-qwen3-4b-sft-128k-GGUF/resolve/main/iflow-metadata-qwen3-4b-sft-128k.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/iflow-metadata-qwen3-4b-sft-128k-GGUF/resolve/main/iflow-metadata-qwen3-4b-sft-128k.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. + + diff --git a/iflow-metadata-qwen3-4b-sft-128k.IQ4_XS.gguf b/iflow-metadata-qwen3-4b-sft-128k.IQ4_XS.gguf new file mode 100644 index 0000000..8c69937 --- /dev/null +++ b/iflow-metadata-qwen3-4b-sft-128k.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1abc38d1a1e7dde0490f36ee22a48403d03da5a1da4eea5df0dcf27d2ca2b30 +size 2286316768 diff --git a/iflow-metadata-qwen3-4b-sft-128k.Q2_K.gguf b/iflow-metadata-qwen3-4b-sft-128k.Q2_K.gguf new file mode 100644 index 0000000..7c381da --- /dev/null +++ b/iflow-metadata-qwen3-4b-sft-128k.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59a19fcefde884c2943abede6d7b07c12b0562168ce6342e04cc5cc6d035d81c +size 1669500128 diff --git a/iflow-metadata-qwen3-4b-sft-128k.Q3_K_L.gguf b/iflow-metadata-qwen3-4b-sft-128k.Q3_K_L.gguf new file mode 100644 index 0000000..2db0c66 --- /dev/null +++ b/iflow-metadata-qwen3-4b-sft-128k.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0f5df31b70e3b7d2a24c77349c30c428d0d2b27ce708f3544923a44739eb91e +size 2239786208 diff --git a/iflow-metadata-qwen3-4b-sft-128k.Q3_K_M.gguf b/iflow-metadata-qwen3-4b-sft-128k.Q3_K_M.gguf new file mode 100644 index 0000000..65620d2 --- /dev/null +++ b/iflow-metadata-qwen3-4b-sft-128k.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2c3bbf6a13b9931fdadeffe2e8a1e2286479ee06fa372624149c41166a1286e +size 2075618528 diff --git a/iflow-metadata-qwen3-4b-sft-128k.Q3_K_S.gguf b/iflow-metadata-qwen3-4b-sft-128k.Q3_K_S.gguf new file mode 100644 index 0000000..2f5514d --- /dev/null +++ b/iflow-metadata-qwen3-4b-sft-128k.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bbf60c88c4b06da2df62e61f15c326234dc62c960821c0cb9a8bb54f980fa26 +size 1886997728 diff --git a/iflow-metadata-qwen3-4b-sft-128k.Q4_K_M.gguf b/iflow-metadata-qwen3-4b-sft-128k.Q4_K_M.gguf new file mode 100644 index 0000000..098dd6d --- /dev/null +++ b/iflow-metadata-qwen3-4b-sft-128k.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e61777687a8704d5f5d880cfef12bf86c6a808ef0a9a18e31aedb3c21ecb8209 +size 2497281248 diff --git a/iflow-metadata-qwen3-4b-sft-128k.Q4_K_S.gguf b/iflow-metadata-qwen3-4b-sft-128k.Q4_K_S.gguf new file mode 100644 index 0000000..a108bb1 --- /dev/null +++ b/iflow-metadata-qwen3-4b-sft-128k.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3836074eb6492fe002aa5acf3512c71e94a6f4f34b8fc21675d83470bda396a +size 2383310048 diff --git a/iflow-metadata-qwen3-4b-sft-128k.Q5_K_M.gguf b/iflow-metadata-qwen3-4b-sft-128k.Q5_K_M.gguf new file mode 100644 index 0000000..0b33e8e --- /dev/null +++ b/iflow-metadata-qwen3-4b-sft-128k.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e7fe87c8857f057b56138d2a230c02ad8893c11f4db832cf7965bfdd02253a3 +size 2889514208 diff --git a/iflow-metadata-qwen3-4b-sft-128k.Q5_K_S.gguf b/iflow-metadata-qwen3-4b-sft-128k.Q5_K_S.gguf new file mode 100644 index 0000000..670a33a --- /dev/null +++ b/iflow-metadata-qwen3-4b-sft-128k.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c77446cd7d3f7596fe6951b4688ea560074e289c4017b8246a6c018a921d3659 +size 2823711968 diff --git a/iflow-metadata-qwen3-4b-sft-128k.Q6_K.gguf b/iflow-metadata-qwen3-4b-sft-128k.Q6_K.gguf new file mode 100644 index 0000000..7ba3d41 --- /dev/null +++ b/iflow-metadata-qwen3-4b-sft-128k.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46fcd85b6d3af6de2be71b1b4e839be3241a5654b19bcb2ec03ca1f3c27e1acc +size 3306261728 diff --git a/iflow-metadata-qwen3-4b-sft-128k.Q8_0.gguf b/iflow-metadata-qwen3-4b-sft-128k.Q8_0.gguf new file mode 100644 index 0000000..9e6c4b1 --- /dev/null +++ b/iflow-metadata-qwen3-4b-sft-128k.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fc6084e926685f7a1699fabaf4f111bc2d243c59bcbb9fc2b141404c74a53e9 +size 4280405728 diff --git a/iflow-metadata-qwen3-4b-sft-128k.f16.gguf b/iflow-metadata-qwen3-4b-sft-128k.f16.gguf new file mode 100644 index 0000000..cbad36d --- /dev/null +++ b/iflow-metadata-qwen3-4b-sft-128k.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b156b03c7547f6dc6b7f3f25a0897c647cd07bc154a193c7ba4b24b03aea84 +size 8051285728