commit e1a382989ffc322edf4ba01115f003dee3ec0723 Author: ModelHub XC Date: Sat Jul 4 14:07:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/DLM-NL2JSON-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f5c66f4 --- /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 +DLM-NL2JSON-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DLM-NL2JSON-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DLM-NL2JSON-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DLM-NL2JSON-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DLM-NL2JSON-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DLM-NL2JSON-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DLM-NL2JSON-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DLM-NL2JSON-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DLM-NL2JSON-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DLM-NL2JSON-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DLM-NL2JSON-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DLM-NL2JSON-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DLM-NL2JSON-4B.IQ4_XS.gguf b/DLM-NL2JSON-4B.IQ4_XS.gguf new file mode 100644 index 0000000..30b3610 --- /dev/null +++ b/DLM-NL2JSON-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2438dcb1f3e596176d33f3e8e9f78e23c40f0605292e796a77e7f54fc1b21b9 +size 2285760640 diff --git a/DLM-NL2JSON-4B.Q2_K.gguf b/DLM-NL2JSON-4B.Q2_K.gguf new file mode 100644 index 0000000..a6945a5 --- /dev/null +++ b/DLM-NL2JSON-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6792c2e73780a475b7f4145414908fd40b0c1f11da51d3a58ca0f1da8060726d +size 1668944000 diff --git a/DLM-NL2JSON-4B.Q3_K_L.gguf b/DLM-NL2JSON-4B.Q3_K_L.gguf new file mode 100644 index 0000000..a2d7321 --- /dev/null +++ b/DLM-NL2JSON-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a4e9e0167bc7e613b3adc232be1117ea3da141689bb455cdcb26a5b4e955765 +size 2239230080 diff --git a/DLM-NL2JSON-4B.Q3_K_M.gguf b/DLM-NL2JSON-4B.Q3_K_M.gguf new file mode 100644 index 0000000..e3119d9 --- /dev/null +++ b/DLM-NL2JSON-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d09e6395659040847785887c53b5d1a09810b293366616ee3d98e19526f804b9 +size 2075062400 diff --git a/DLM-NL2JSON-4B.Q3_K_S.gguf b/DLM-NL2JSON-4B.Q3_K_S.gguf new file mode 100644 index 0000000..e094df2 --- /dev/null +++ b/DLM-NL2JSON-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25eaaabc9d4a67f4ee049242dfba6516e04a1fbda178d45e5ceeab205140266e +size 1886441600 diff --git a/DLM-NL2JSON-4B.Q4_K_M.gguf b/DLM-NL2JSON-4B.Q4_K_M.gguf new file mode 100644 index 0000000..8bc2df4 --- /dev/null +++ b/DLM-NL2JSON-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:853e0d12c474ee6bf484bfd6797fdfebdebdc608a76dc8792d08d7fa823f58ff +size 2496725120 diff --git a/DLM-NL2JSON-4B.Q4_K_S.gguf b/DLM-NL2JSON-4B.Q4_K_S.gguf new file mode 100644 index 0000000..2148f7a --- /dev/null +++ b/DLM-NL2JSON-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86a7baaa180bc0b7a1a08e8aff3761c0b0f274df66a218a73454533902ae6958 +size 2382753920 diff --git a/DLM-NL2JSON-4B.Q5_K_M.gguf b/DLM-NL2JSON-4B.Q5_K_M.gguf new file mode 100644 index 0000000..28fb7d1 --- /dev/null +++ b/DLM-NL2JSON-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33a2f0bdfb3c1b228642f26fd5ee98114c25603ff84efd2a311385a882696e91 +size 2888958080 diff --git a/DLM-NL2JSON-4B.Q5_K_S.gguf b/DLM-NL2JSON-4B.Q5_K_S.gguf new file mode 100644 index 0000000..24601bc --- /dev/null +++ b/DLM-NL2JSON-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5f9a2448fbe82b13a25854f9d2a5234796deaf0c7a5a5d9b4836e08de8d592f +size 2823155840 diff --git a/DLM-NL2JSON-4B.Q6_K.gguf b/DLM-NL2JSON-4B.Q6_K.gguf new file mode 100644 index 0000000..8f998b0 --- /dev/null +++ b/DLM-NL2JSON-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3457cfd67689a616e5d5e83dd29569f34485a08194b8ea0193a47854863cf2f +size 3305705600 diff --git a/DLM-NL2JSON-4B.Q8_0.gguf b/DLM-NL2JSON-4B.Q8_0.gguf new file mode 100644 index 0000000..39098f8 --- /dev/null +++ b/DLM-NL2JSON-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e0ccfffb955ed4369ebdbe8888cbe51fe3b8a8aed183a80f3668a27ca0a2326 +size 4279687136 diff --git a/DLM-NL2JSON-4B.f16.gguf b/DLM-NL2JSON-4B.f16.gguf new file mode 100644 index 0000000..889de65 --- /dev/null +++ b/DLM-NL2JSON-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cc2e519dd068025b81ffdcc72fe24e0f1545e3c0c1a105f4f280a5d6d9002a9 +size 8049938336 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2c3328c --- /dev/null +++ b/README.md @@ -0,0 +1,81 @@ +--- +base_model: dataslab/DLM-NL2JSON-4B +datasets: [] +language: +- ko +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- task-specific +- structured-prediction +- korean +- public-sector +- qwen3 +- domain-specific +- merge +--- +## About + + + + + + + + + +static quants of https://huggingface.co/dataslab/DLM-NL2JSON-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#DLM-NL2JSON-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/DLM-NL2JSON-4B-GGUF/resolve/main/DLM-NL2JSON-4B.Q2_K.gguf) | Q2_K | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/DLM-NL2JSON-4B-GGUF/resolve/main/DLM-NL2JSON-4B.Q3_K_S.gguf) | Q3_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/DLM-NL2JSON-4B-GGUF/resolve/main/DLM-NL2JSON-4B.Q3_K_M.gguf) | Q3_K_M | 2.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DLM-NL2JSON-4B-GGUF/resolve/main/DLM-NL2JSON-4B.Q3_K_L.gguf) | Q3_K_L | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/DLM-NL2JSON-4B-GGUF/resolve/main/DLM-NL2JSON-4B.IQ4_XS.gguf) | IQ4_XS | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/DLM-NL2JSON-4B-GGUF/resolve/main/DLM-NL2JSON-4B.Q4_K_S.gguf) | Q4_K_S | 2.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DLM-NL2JSON-4B-GGUF/resolve/main/DLM-NL2JSON-4B.Q4_K_M.gguf) | Q4_K_M | 2.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DLM-NL2JSON-4B-GGUF/resolve/main/DLM-NL2JSON-4B.Q5_K_S.gguf) | Q5_K_S | 2.9 | | +| [GGUF](https://huggingface.co/mradermacher/DLM-NL2JSON-4B-GGUF/resolve/main/DLM-NL2JSON-4B.Q5_K_M.gguf) | Q5_K_M | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/DLM-NL2JSON-4B-GGUF/resolve/main/DLM-NL2JSON-4B.Q6_K.gguf) | Q6_K | 3.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DLM-NL2JSON-4B-GGUF/resolve/main/DLM-NL2JSON-4B.Q8_0.gguf) | Q8_0 | 4.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DLM-NL2JSON-4B-GGUF/resolve/main/DLM-NL2JSON-4B.f16.gguf) | f16 | 8.1 | 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. + +