commit d12774cc763ad314831781810e11b152ebf54fc9 Author: ModelHub XC Date: Fri Jun 19 17:32:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/VLSP-qwen3-4b-NHK-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..17812ef --- /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 +VLSP-qwen3-4b-NHK.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +VLSP-qwen3-4b-NHK.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +VLSP-qwen3-4b-NHK.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +VLSP-qwen3-4b-NHK.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VLSP-qwen3-4b-NHK.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VLSP-qwen3-4b-NHK.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VLSP-qwen3-4b-NHK.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VLSP-qwen3-4b-NHK.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +VLSP-qwen3-4b-NHK.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +VLSP-qwen3-4b-NHK.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +VLSP-qwen3-4b-NHK.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +VLSP-qwen3-4b-NHK.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..d9b6992 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: htNghiaaa/VLSP-qwen3-4b-NHK +language: +- en +- vi +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/htNghiaaa/VLSP-qwen3-4b-NHK + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#VLSP-qwen3-4b-NHK-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/VLSP-qwen3-4b-NHK-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/VLSP-qwen3-4b-NHK-GGUF/resolve/main/VLSP-qwen3-4b-NHK.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/VLSP-qwen3-4b-NHK-GGUF/resolve/main/VLSP-qwen3-4b-NHK.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/VLSP-qwen3-4b-NHK-GGUF/resolve/main/VLSP-qwen3-4b-NHK.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/VLSP-qwen3-4b-NHK-GGUF/resolve/main/VLSP-qwen3-4b-NHK.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/VLSP-qwen3-4b-NHK-GGUF/resolve/main/VLSP-qwen3-4b-NHK.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/VLSP-qwen3-4b-NHK-GGUF/resolve/main/VLSP-qwen3-4b-NHK.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/VLSP-qwen3-4b-NHK-GGUF/resolve/main/VLSP-qwen3-4b-NHK.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/VLSP-qwen3-4b-NHK-GGUF/resolve/main/VLSP-qwen3-4b-NHK.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/VLSP-qwen3-4b-NHK-GGUF/resolve/main/VLSP-qwen3-4b-NHK.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/VLSP-qwen3-4b-NHK-GGUF/resolve/main/VLSP-qwen3-4b-NHK.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/VLSP-qwen3-4b-NHK-GGUF/resolve/main/VLSP-qwen3-4b-NHK.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/VLSP-qwen3-4b-NHK-GGUF/resolve/main/VLSP-qwen3-4b-NHK.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/VLSP-qwen3-4b-NHK.IQ4_XS.gguf b/VLSP-qwen3-4b-NHK.IQ4_XS.gguf new file mode 100644 index 0000000..1ebc2da --- /dev/null +++ b/VLSP-qwen3-4b-NHK.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:629d339c7ae819ec072ce54297f3bf032dac04b34906e0762aa465a9b045d9c9 +size 2286316768 diff --git a/VLSP-qwen3-4b-NHK.Q2_K.gguf b/VLSP-qwen3-4b-NHK.Q2_K.gguf new file mode 100644 index 0000000..97bad0c --- /dev/null +++ b/VLSP-qwen3-4b-NHK.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8b2077e3d6ab9c1d49b656766d73f0266bf641e67972dec1aba8f014dcd714d +size 1669500128 diff --git a/VLSP-qwen3-4b-NHK.Q3_K_L.gguf b/VLSP-qwen3-4b-NHK.Q3_K_L.gguf new file mode 100644 index 0000000..e5d0162 --- /dev/null +++ b/VLSP-qwen3-4b-NHK.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae9ff3b53dcc7ff64e8dae0e27f79bf3c94d8c519b2c18aa34cbbf8cd75a4a4e +size 2239786208 diff --git a/VLSP-qwen3-4b-NHK.Q3_K_M.gguf b/VLSP-qwen3-4b-NHK.Q3_K_M.gguf new file mode 100644 index 0000000..ae3b73f --- /dev/null +++ b/VLSP-qwen3-4b-NHK.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aa826edd879bfbc693303af3b35112b44e678a47bd869da2924a0acf1d3cbab +size 2075618528 diff --git a/VLSP-qwen3-4b-NHK.Q3_K_S.gguf b/VLSP-qwen3-4b-NHK.Q3_K_S.gguf new file mode 100644 index 0000000..a42dcfb --- /dev/null +++ b/VLSP-qwen3-4b-NHK.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46bd79d3df302cd8c7899b7fb53014dc44f276bbecdad096f41719b93b421e25 +size 1886997728 diff --git a/VLSP-qwen3-4b-NHK.Q4_K_M.gguf b/VLSP-qwen3-4b-NHK.Q4_K_M.gguf new file mode 100644 index 0000000..81a3d8c --- /dev/null +++ b/VLSP-qwen3-4b-NHK.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b07a3cb76e59cec942e879679d2ecfec77df31bface24e8c9b3cc7202438bd9 +size 2497281248 diff --git a/VLSP-qwen3-4b-NHK.Q4_K_S.gguf b/VLSP-qwen3-4b-NHK.Q4_K_S.gguf new file mode 100644 index 0000000..070ba07 --- /dev/null +++ b/VLSP-qwen3-4b-NHK.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dbc03d702ef95d51a989568e7b1afc38403532ff264d9dc82b9f2a8043f8d03 +size 2383310048 diff --git a/VLSP-qwen3-4b-NHK.Q5_K_M.gguf b/VLSP-qwen3-4b-NHK.Q5_K_M.gguf new file mode 100644 index 0000000..5f48ad4 --- /dev/null +++ b/VLSP-qwen3-4b-NHK.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:206aea349e76661a28471a8f1bed4a7b744179b8061baf1247e112a317acc24d +size 2889514208 diff --git a/VLSP-qwen3-4b-NHK.Q5_K_S.gguf b/VLSP-qwen3-4b-NHK.Q5_K_S.gguf new file mode 100644 index 0000000..e7393ad --- /dev/null +++ b/VLSP-qwen3-4b-NHK.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c039ff2d2ea59e588c8900e720459476dedd2f5cb8dc44b0d0b14964cdbd14d +size 2823711968 diff --git a/VLSP-qwen3-4b-NHK.Q6_K.gguf b/VLSP-qwen3-4b-NHK.Q6_K.gguf new file mode 100644 index 0000000..0cf4f6d --- /dev/null +++ b/VLSP-qwen3-4b-NHK.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbd008e642199dba674589c55ef22aa4f1314f48b367116c995fc92de6dff13b +size 3306261728 diff --git a/VLSP-qwen3-4b-NHK.Q8_0.gguf b/VLSP-qwen3-4b-NHK.Q8_0.gguf new file mode 100644 index 0000000..d5f6a47 --- /dev/null +++ b/VLSP-qwen3-4b-NHK.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e413a53593d15cbc70336b4f5736543c907def7c8cf0e2cf9fc38353c825222a +size 4280405728 diff --git a/VLSP-qwen3-4b-NHK.f16.gguf b/VLSP-qwen3-4b-NHK.f16.gguf new file mode 100644 index 0000000..a9863c7 --- /dev/null +++ b/VLSP-qwen3-4b-NHK.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e716b5e3edeca92ddb758d8b8056dea59e311ee9437dd8faeb6c9f59134fa600 +size 8051285728