commit 9f4c3a1bf3f2fe63b5fa4ff175fe95fc8c5a0c1c Author: ModelHub XC Date: Sun Jun 14 01:14:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-Coder-3B-NEP-new-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2ed2ee4 --- /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 +Qwen2.5-Coder-3B-NEP-new.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-NEP-new.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-NEP-new.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-NEP-new.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-NEP-new.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-NEP-new.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-NEP-new.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-NEP-new.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-NEP-new.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-NEP-new.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-NEP-new.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-Coder-3B-NEP-new.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-Coder-3B-NEP-new.IQ4_XS.gguf b/Qwen2.5-Coder-3B-NEP-new.IQ4_XS.gguf new file mode 100644 index 0000000..a959b9e --- /dev/null +++ b/Qwen2.5-Coder-3B-NEP-new.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50343dedd089c0b2f2b0eed57a6b250df9ee8354426849c8a8efdc029de3d362 +size 1917746752 diff --git a/Qwen2.5-Coder-3B-NEP-new.Q2_K.gguf b/Qwen2.5-Coder-3B-NEP-new.Q2_K.gguf new file mode 100644 index 0000000..761e188 --- /dev/null +++ b/Qwen2.5-Coder-3B-NEP-new.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:550d06605d0bd0cce339bb34c0f409c7e82757ca2232f8eefa99bed567bb6315 +size 1376223264 diff --git a/Qwen2.5-Coder-3B-NEP-new.Q3_K_L.gguf b/Qwen2.5-Coder-3B-NEP-new.Q3_K_L.gguf new file mode 100644 index 0000000..a2d59ea --- /dev/null +++ b/Qwen2.5-Coder-3B-NEP-new.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b27bb92f620e4923a9bab5603fc318425013053847f29e85f68d8a2274a6a06 +size 1840406336 diff --git a/Qwen2.5-Coder-3B-NEP-new.Q3_K_M.gguf b/Qwen2.5-Coder-3B-NEP-new.Q3_K_M.gguf new file mode 100644 index 0000000..758ce9e --- /dev/null +++ b/Qwen2.5-Coder-3B-NEP-new.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cf109946294c98a54b26e1ad983c2b213fca1abcb41e63528fd47ae9913c2e2 +size 1723490112 diff --git a/Qwen2.5-Coder-3B-NEP-new.Q3_K_S.gguf b/Qwen2.5-Coder-3B-NEP-new.Q3_K_S.gguf new file mode 100644 index 0000000..53448eb --- /dev/null +++ b/Qwen2.5-Coder-3B-NEP-new.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a8aaf22ecaf940d8a04f6fa35be22c77fad27233c4cdc9fb6bce73b60550e38 +size 1587371840 diff --git a/Qwen2.5-Coder-3B-NEP-new.Q4_K_M.gguf b/Qwen2.5-Coder-3B-NEP-new.Q4_K_M.gguf new file mode 100644 index 0000000..3df79b6 --- /dev/null +++ b/Qwen2.5-Coder-3B-NEP-new.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35a4130d7affae8e4b527f6840451e8910f750c8482e53ce1ad8496f51a97e45 +size 2104171392 diff --git a/Qwen2.5-Coder-3B-NEP-new.Q4_K_S.gguf b/Qwen2.5-Coder-3B-NEP-new.Q4_K_S.gguf new file mode 100644 index 0000000..738ce35 --- /dev/null +++ b/Qwen2.5-Coder-3B-NEP-new.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bd5aad9fdeb577113ff9fdc06e8739d65c4b3d0d40cdea6d72392ccdad187ab +size 2008652672 diff --git a/Qwen2.5-Coder-3B-NEP-new.Q5_K_M.gguf b/Qwen2.5-Coder-3B-NEP-new.Q5_K_M.gguf new file mode 100644 index 0000000..196f674 --- /dev/null +++ b/Qwen2.5-Coder-3B-NEP-new.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f3fc3f831b5ad119b307aa828c1d08573f7ef4167e29a6675905a58ba4a2d74 +size 2437910656 diff --git a/Qwen2.5-Coder-3B-NEP-new.Q5_K_S.gguf b/Qwen2.5-Coder-3B-NEP-new.Q5_K_S.gguf new file mode 100644 index 0000000..6d4ead0 --- /dev/null +++ b/Qwen2.5-Coder-3B-NEP-new.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a8d0e03e87ffdbb4f6f1ce6d1907c0cd7a7d5db5a172176c7ebdc1359ca68f4 +size 2382762112 diff --git a/Qwen2.5-Coder-3B-NEP-new.Q6_K.gguf b/Qwen2.5-Coder-3B-NEP-new.Q6_K.gguf new file mode 100644 index 0000000..825e258 --- /dev/null +++ b/Qwen2.5-Coder-3B-NEP-new.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a13986d6b56d4e9096292a376d3c507c6bba26f32b90096045fe7d5b32d136a6 +size 2792508640 diff --git a/Qwen2.5-Coder-3B-NEP-new.Q8_0.gguf b/Qwen2.5-Coder-3B-NEP-new.Q8_0.gguf new file mode 100644 index 0000000..80b0679 --- /dev/null +++ b/Qwen2.5-Coder-3B-NEP-new.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:182bb79a0710db41b5296ad1767ee7fb2bafdf4c8e0c7b64e8ff347a89e00afc +size 3614921248 diff --git a/Qwen2.5-Coder-3B-NEP-new.f16.gguf b/Qwen2.5-Coder-3B-NEP-new.f16.gguf new file mode 100644 index 0000000..746fe96 --- /dev/null +++ b/Qwen2.5-Coder-3B-NEP-new.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73c1a7de7d82be401f24fea30908e127fea96b2fc43a5812859fdbe9930d7780 +size 6798454048 diff --git a/README.md b/README.md new file mode 100644 index 0000000..942102a --- /dev/null +++ b/README.md @@ -0,0 +1,79 @@ +--- +base_model: lurf21/Qwen2.5-Coder-3B-NEP +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/lurf21/Qwen2.5-Coder-3B-NEP + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-Coder-3B-NEP-new-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/Qwen2.5-Coder-3B-NEP-new-GGUF/resolve/main/Qwen2.5-Coder-3B-NEP-new.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-NEP-new-GGUF/resolve/main/Qwen2.5-Coder-3B-NEP-new.Q3_K_S.gguf) | Q3_K_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-NEP-new-GGUF/resolve/main/Qwen2.5-Coder-3B-NEP-new.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-NEP-new-GGUF/resolve/main/Qwen2.5-Coder-3B-NEP-new.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-NEP-new-GGUF/resolve/main/Qwen2.5-Coder-3B-NEP-new.IQ4_XS.gguf) | IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-NEP-new-GGUF/resolve/main/Qwen2.5-Coder-3B-NEP-new.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-NEP-new-GGUF/resolve/main/Qwen2.5-Coder-3B-NEP-new.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-NEP-new-GGUF/resolve/main/Qwen2.5-Coder-3B-NEP-new.Q5_K_S.gguf) | Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-NEP-new-GGUF/resolve/main/Qwen2.5-Coder-3B-NEP-new.Q5_K_M.gguf) | Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-NEP-new-GGUF/resolve/main/Qwen2.5-Coder-3B-NEP-new.Q6_K.gguf) | Q6_K | 2.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-NEP-new-GGUF/resolve/main/Qwen2.5-Coder-3B-NEP-new.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-Coder-3B-NEP-new-GGUF/resolve/main/Qwen2.5-Coder-3B-NEP-new.f16.gguf) | f16 | 6.9 | 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. + +