commit dbf720fd11298f4ea6998d7770ce9a66f4d07b7b Author: ModelHub XC Date: Sun Apr 12 03:46:58 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Forge-Qwen2.5-0.5B-s1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..4c69492 --- /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 +Forge-Qwen2.5-0.5B-s1.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Forge-Qwen2.5-0.5B-s1.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Forge-Qwen2.5-0.5B-s1.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Forge-Qwen2.5-0.5B-s1.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Forge-Qwen2.5-0.5B-s1.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Forge-Qwen2.5-0.5B-s1.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Forge-Qwen2.5-0.5B-s1.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Forge-Qwen2.5-0.5B-s1.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Forge-Qwen2.5-0.5B-s1.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Forge-Qwen2.5-0.5B-s1.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Forge-Qwen2.5-0.5B-s1.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Forge-Qwen2.5-0.5B-s1.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Forge-Qwen2.5-0.5B-s1.IQ4_XS.gguf b/Forge-Qwen2.5-0.5B-s1.IQ4_XS.gguf new file mode 100644 index 0000000..f4cdeed --- /dev/null +++ b/Forge-Qwen2.5-0.5B-s1.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:079ab03ba9ab9a36c797a19664626ecb02638fdd2a52f21b4cd991f5c2731bef +size 414755040 diff --git a/Forge-Qwen2.5-0.5B-s1.Q2_K.gguf b/Forge-Qwen2.5-0.5B-s1.Q2_K.gguf new file mode 100644 index 0000000..a3bb921 --- /dev/null +++ b/Forge-Qwen2.5-0.5B-s1.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7cda9b440ef6fb9cb8508903feccea37ef7561e103c0cac83c184f6e43d844e +size 401917152 diff --git a/Forge-Qwen2.5-0.5B-s1.Q3_K_L.gguf b/Forge-Qwen2.5-0.5B-s1.Q3_K_L.gguf new file mode 100644 index 0000000..14d6149 --- /dev/null +++ b/Forge-Qwen2.5-0.5B-s1.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3471899a00e72c3a584130ba8c8c389f41b62e08fbd6d81a6a0915b2b3fce639 +size 432667872 diff --git a/Forge-Qwen2.5-0.5B-s1.Q3_K_M.gguf b/Forge-Qwen2.5-0.5B-s1.Q3_K_M.gguf new file mode 100644 index 0000000..6035361 --- /dev/null +++ b/Forge-Qwen2.5-0.5B-s1.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be0c51a2162f81286d69f054a63d2b2a9724f9ef4f57b0ecea5adb6a8f3be0e2 +size 418776288 diff --git a/Forge-Qwen2.5-0.5B-s1.Q3_K_S.gguf b/Forge-Qwen2.5-0.5B-s1.Q3_K_S.gguf new file mode 100644 index 0000000..7ddf23b --- /dev/null +++ b/Forge-Qwen2.5-0.5B-s1.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37a6c3a7e95a8ba62f2cfdf767c9b537018a08cf3002fef7ae1e9921e0f631d6 +size 401573088 diff --git a/Forge-Qwen2.5-0.5B-s1.Q4_K_M.gguf b/Forge-Qwen2.5-0.5B-s1.Q4_K_M.gguf new file mode 100644 index 0000000..93b2b78 --- /dev/null +++ b/Forge-Qwen2.5-0.5B-s1.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa58c8ca81ac7df4059afe6af0e6269fbc991d4bbd6031f2da2e1e0db1008097 +size 461117664 diff --git a/Forge-Qwen2.5-0.5B-s1.Q4_K_S.gguf b/Forge-Qwen2.5-0.5B-s1.Q4_K_S.gguf new file mode 100644 index 0000000..09cf80e --- /dev/null +++ b/Forge-Qwen2.5-0.5B-s1.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00beb05a6ea5b696f6dcd9b137a706dd793e61cc0d33319a483ce09ef562d3c3 +size 448781536 diff --git a/Forge-Qwen2.5-0.5B-s1.Q5_K_M.gguf b/Forge-Qwen2.5-0.5B-s1.Q5_K_M.gguf new file mode 100644 index 0000000..322c56e --- /dev/null +++ b/Forge-Qwen2.5-0.5B-s1.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e30ea810a17ad373fd0ed67c8ec6041b93dcb81b7d9897b50c94ee830b5d2727 +size 483395808 diff --git a/Forge-Qwen2.5-0.5B-s1.Q5_K_S.gguf b/Forge-Qwen2.5-0.5B-s1.Q5_K_S.gguf new file mode 100644 index 0000000..1decf19 --- /dev/null +++ b/Forge-Qwen2.5-0.5B-s1.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:024f5f0df7a5ebef3bfd4bc0cf7094a66e714a44098b7ff18dff6bc103fa0bb0 +size 476019936 diff --git a/Forge-Qwen2.5-0.5B-s1.Q6_K.gguf b/Forge-Qwen2.5-0.5B-s1.Q6_K.gguf new file mode 100644 index 0000000..2a55591 --- /dev/null +++ b/Forge-Qwen2.5-0.5B-s1.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2da125a09828a7e7c91c80492aeb60f2513bc1c9c50afe5041659039677a28fa +size 569046240 diff --git a/Forge-Qwen2.5-0.5B-s1.Q8_0.gguf b/Forge-Qwen2.5-0.5B-s1.Q8_0.gguf new file mode 100644 index 0000000..bfea55e --- /dev/null +++ b/Forge-Qwen2.5-0.5B-s1.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eae363dbc4825832f7349b2310edd326070a21f5be9f164decd41d9541579957 +size 594377952 diff --git a/Forge-Qwen2.5-0.5B-s1.f16.gguf b/Forge-Qwen2.5-0.5B-s1.f16.gguf new file mode 100644 index 0000000..35df8d2 --- /dev/null +++ b/Forge-Qwen2.5-0.5B-s1.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6ae8302898c93f2b951128a8a5a4e7bb94368de0e99f463fe6330336a8b5daf +size 1112301792 diff --git a/README.md b/README.md new file mode 100644 index 0000000..93894f9 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: AL-GR/Forge-Qwen2.5-0.5B-s1 +datasets: +- AL-GR/AL-GR-v1 +language: +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/AL-GR/Forge-Qwen2.5-0.5B-s1 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Forge-Qwen2.5-0.5B-s1-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/Forge-Qwen2.5-0.5B-s1-GGUF/resolve/main/Forge-Qwen2.5-0.5B-s1.Q3_K_S.gguf) | Q3_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Forge-Qwen2.5-0.5B-s1-GGUF/resolve/main/Forge-Qwen2.5-0.5B-s1.Q2_K.gguf) | Q2_K | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Forge-Qwen2.5-0.5B-s1-GGUF/resolve/main/Forge-Qwen2.5-0.5B-s1.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Forge-Qwen2.5-0.5B-s1-GGUF/resolve/main/Forge-Qwen2.5-0.5B-s1.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Forge-Qwen2.5-0.5B-s1-GGUF/resolve/main/Forge-Qwen2.5-0.5B-s1.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Forge-Qwen2.5-0.5B-s1-GGUF/resolve/main/Forge-Qwen2.5-0.5B-s1.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Forge-Qwen2.5-0.5B-s1-GGUF/resolve/main/Forge-Qwen2.5-0.5B-s1.Q4_K_M.gguf) | Q4_K_M | 0.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Forge-Qwen2.5-0.5B-s1-GGUF/resolve/main/Forge-Qwen2.5-0.5B-s1.Q5_K_S.gguf) | Q5_K_S | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Forge-Qwen2.5-0.5B-s1-GGUF/resolve/main/Forge-Qwen2.5-0.5B-s1.Q5_K_M.gguf) | Q5_K_M | 0.6 | | +| [GGUF](https://huggingface.co/mradermacher/Forge-Qwen2.5-0.5B-s1-GGUF/resolve/main/Forge-Qwen2.5-0.5B-s1.Q6_K.gguf) | Q6_K | 0.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Forge-Qwen2.5-0.5B-s1-GGUF/resolve/main/Forge-Qwen2.5-0.5B-s1.Q8_0.gguf) | Q8_0 | 0.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Forge-Qwen2.5-0.5B-s1-GGUF/resolve/main/Forge-Qwen2.5-0.5B-s1.f16.gguf) | f16 | 1.2 | 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. + +