commit 5091dcecda04ba27384b9f98afe283ba41f0c3bd Author: ModelHub XC Date: Wed Jun 10 13:41:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/VietMind-Qwen-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f426089 --- /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 +VietMind-Qwen-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +VietMind-Qwen-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +VietMind-Qwen-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +VietMind-Qwen-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VietMind-Qwen-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VietMind-Qwen-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VietMind-Qwen-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VietMind-Qwen-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VietMind-Qwen-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VietMind-Qwen-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +VietMind-Qwen-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +VietMind-Qwen-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..0e306e9 --- /dev/null +++ b/README.md @@ -0,0 +1,72 @@ +--- +base_model: hiudev/VietMind-Qwen-4B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + + + + +static quants of https://huggingface.co/hiudev/VietMind-Qwen-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#VietMind-Qwen-4B-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/VietMind-Qwen-4B-GGUF/resolve/main/VietMind-Qwen-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/VietMind-Qwen-4B-GGUF/resolve/main/VietMind-Qwen-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/VietMind-Qwen-4B-GGUF/resolve/main/VietMind-Qwen-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/VietMind-Qwen-4B-GGUF/resolve/main/VietMind-Qwen-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/VietMind-Qwen-4B-GGUF/resolve/main/VietMind-Qwen-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/VietMind-Qwen-4B-GGUF/resolve/main/VietMind-Qwen-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/VietMind-Qwen-4B-GGUF/resolve/main/VietMind-Qwen-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/VietMind-Qwen-4B-GGUF/resolve/main/VietMind-Qwen-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/VietMind-Qwen-4B-GGUF/resolve/main/VietMind-Qwen-4B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/VietMind-Qwen-4B-GGUF/resolve/main/VietMind-Qwen-4B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/VietMind-Qwen-4B-GGUF/resolve/main/VietMind-Qwen-4B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/VietMind-Qwen-4B-GGUF/resolve/main/VietMind-Qwen-4B.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/VietMind-Qwen-4B.IQ4_XS.gguf b/VietMind-Qwen-4B.IQ4_XS.gguf new file mode 100644 index 0000000..c5e7426 --- /dev/null +++ b/VietMind-Qwen-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97bac09b9e11f7f301fdb8a6af2761202979db70fb1985ad5f563c8690d043d1 +size 2286314816 diff --git a/VietMind-Qwen-4B.Q2_K.gguf b/VietMind-Qwen-4B.Q2_K.gguf new file mode 100644 index 0000000..f4a2548 --- /dev/null +++ b/VietMind-Qwen-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17b636c7e78d01946d0d37183fe0435259661f09816c4239c7d3069ec23ce4ff +size 1669498176 diff --git a/VietMind-Qwen-4B.Q3_K_L.gguf b/VietMind-Qwen-4B.Q3_K_L.gguf new file mode 100644 index 0000000..e13831f --- /dev/null +++ b/VietMind-Qwen-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c246c304614746712ed2e132962962dbc9bc54e09a85f3d2d995af777e08b0f3 +size 2239784256 diff --git a/VietMind-Qwen-4B.Q3_K_M.gguf b/VietMind-Qwen-4B.Q3_K_M.gguf new file mode 100644 index 0000000..1fbc93a --- /dev/null +++ b/VietMind-Qwen-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:663f9c1d820fbd0eebce4f986cac24c3f416c5c43235a7262ca26f522eba1415 +size 2075616576 diff --git a/VietMind-Qwen-4B.Q3_K_S.gguf b/VietMind-Qwen-4B.Q3_K_S.gguf new file mode 100644 index 0000000..0ea34d0 --- /dev/null +++ b/VietMind-Qwen-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d225629301035baaf6818de104da613df77e3784f67ba5d15a3a5f64d9d710 +size 1886995776 diff --git a/VietMind-Qwen-4B.Q4_K_M.gguf b/VietMind-Qwen-4B.Q4_K_M.gguf new file mode 100644 index 0000000..6cadc8b --- /dev/null +++ b/VietMind-Qwen-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:963d1d9c8009876dd5c1990f35f5d440d8c0820908e72aea3d80baf5fc0eb39d +size 2497279296 diff --git a/VietMind-Qwen-4B.Q4_K_S.gguf b/VietMind-Qwen-4B.Q4_K_S.gguf new file mode 100644 index 0000000..ac8fc62 --- /dev/null +++ b/VietMind-Qwen-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5036dee6288a42337a89c05796bea3cbc1999c6129a8b1399e0898113fc2d287 +size 2383308096 diff --git a/VietMind-Qwen-4B.Q5_K_M.gguf b/VietMind-Qwen-4B.Q5_K_M.gguf new file mode 100644 index 0000000..acc5882 --- /dev/null +++ b/VietMind-Qwen-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d315acfba71f21da0dc7118413af1a36fd3aeef03e15a600e6cb38e7c79e5f3e +size 2889512256 diff --git a/VietMind-Qwen-4B.Q5_K_S.gguf b/VietMind-Qwen-4B.Q5_K_S.gguf new file mode 100644 index 0000000..56dc196 --- /dev/null +++ b/VietMind-Qwen-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8773b7e2d7a121936730e412ec2575a28acbd10742ab2176fd78a96ddb195e9 +size 2823710016 diff --git a/VietMind-Qwen-4B.Q6_K.gguf b/VietMind-Qwen-4B.Q6_K.gguf new file mode 100644 index 0000000..4279dfa --- /dev/null +++ b/VietMind-Qwen-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6b39677d09e254337760c7097ded240febb9795392fa963b85537a1d97a0617 +size 3306259776 diff --git a/VietMind-Qwen-4B.Q8_0.gguf b/VietMind-Qwen-4B.Q8_0.gguf new file mode 100644 index 0000000..4a5a4d8 --- /dev/null +++ b/VietMind-Qwen-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5f114fad720ae044de2daf1547bd2f63837365446ff8b808ac1c97712551da1 +size 4280403776 diff --git a/VietMind-Qwen-4B.f16.gguf b/VietMind-Qwen-4B.f16.gguf new file mode 100644 index 0000000..774a593 --- /dev/null +++ b/VietMind-Qwen-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea33c31db7339912ab610fb41a5352fab5913f061fde8947ea25cff9fdf77b40 +size 8051283776