commit e4003ff6311660b066d0c919735b459b5fcbee62 Author: ModelHub XC Date: Mon Apr 13 17:49:03 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Dumpling-Qwen2.5-1.5B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..2a133f0 --- /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 +Dumpling-Qwen2.5-1.5B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Dumpling-Qwen2.5-1.5B.IQ4_XS.gguf b/Dumpling-Qwen2.5-1.5B.IQ4_XS.gguf new file mode 100644 index 0000000..a43921c --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc565466b70d2359a1b26e8ec3b67f577a50018553ad7c35ee0b1050fb674e28 +size 902185824 diff --git a/Dumpling-Qwen2.5-1.5B.Q2_K.gguf b/Dumpling-Qwen2.5-1.5B.Q2_K.gguf new file mode 100644 index 0000000..ada9e2d --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4aeaf03d3603c8a06eed7d97d9f17c4a26db9ac1bdf8b6f4a48aabf5399aacb +size 676307808 diff --git a/Dumpling-Qwen2.5-1.5B.Q3_K_L.gguf b/Dumpling-Qwen2.5-1.5B.Q3_K_L.gguf new file mode 100644 index 0000000..87c3dc8 --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61367b1911953444bcffb11eeccc79919b753f3f085040d5ca125297cc784043 +size 880165728 diff --git a/Dumpling-Qwen2.5-1.5B.Q3_K_M.gguf b/Dumpling-Qwen2.5-1.5B.Q3_K_M.gguf new file mode 100644 index 0000000..5a92927 --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30ddcf26529134f9d96f5f5d85cee6816df0b3f5254ca788fa0fd19fd9aefbc1 +size 824181600 diff --git a/Dumpling-Qwen2.5-1.5B.Q3_K_S.gguf b/Dumpling-Qwen2.5-1.5B.Q3_K_S.gguf new file mode 100644 index 0000000..e1619ab --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46ae002cc120380acb4041bba018d635d312b009c50734b8a27899938b86a903 +size 760947552 diff --git a/Dumpling-Qwen2.5-1.5B.Q4_K_M.gguf b/Dumpling-Qwen2.5-1.5B.Q4_K_M.gguf new file mode 100644 index 0000000..9297db3 --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:409c919bf572ad52cd1c8d7a85a481c0b78033f0ad2e303cc8c7ade98c94d734 +size 986051424 diff --git a/Dumpling-Qwen2.5-1.5B.Q4_K_S.gguf b/Dumpling-Qwen2.5-1.5B.Q4_K_S.gguf new file mode 100644 index 0000000..82649f8 --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7599defca565476f4a650e2a3fce31621a7e7754ea0d3b362587b8022d42667 +size 940315488 diff --git a/Dumpling-Qwen2.5-1.5B.Q5_K_M.gguf b/Dumpling-Qwen2.5-1.5B.Q5_K_M.gguf new file mode 100644 index 0000000..5bb1a22 --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c88ed703038593b7b42e75bd4d9c5aff468b4de909b869cd8be61a226947e267 +size 1125053280 diff --git a/Dumpling-Qwen2.5-1.5B.Q5_K_S.gguf b/Dumpling-Qwen2.5-1.5B.Q5_K_S.gguf new file mode 100644 index 0000000..b3f07f0 --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b33bd2ccbc49720f41d9ff1613f929b0664f55a1520bf34a49aec7bd22f3ff8 +size 1098732384 diff --git a/Dumpling-Qwen2.5-1.5B.Q6_K.gguf b/Dumpling-Qwen2.5-1.5B.Q6_K.gguf new file mode 100644 index 0000000..c5066b5 --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5868f760969b160ae80866c10731356dc3ddcc8038b45a15ee8551830afaacd7 +size 1272742752 diff --git a/Dumpling-Qwen2.5-1.5B.Q8_0.gguf b/Dumpling-Qwen2.5-1.5B.Q8_0.gguf new file mode 100644 index 0000000..f783a3d --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d786827cd86b789d39fe67c50138c6fe334cc1d1d1b7bfa4476d7e02c7ea3c5e +size 1646575968 diff --git a/Dumpling-Qwen2.5-1.5B.f16.gguf b/Dumpling-Qwen2.5-1.5B.f16.gguf new file mode 100644 index 0000000..771e000 --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9109c0ec91f60bdcb96829d29315a5437ec52d66f252dd021ce88c1cef212fe4 +size 3093672288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4461be7 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: nbeerbower/Dumpling-Qwen2.5-1.5B +datasets: +- nbeerbower/GreatFirewall-DPO +- nbeerbower/Schule-DPO +- nbeerbower/Purpura-DPO +- nbeerbower/Arkhaios-DPO +- jondurbin/truthy-dpo-v0.1 +- antiven0m/physical-reasoning-dpo +- flammenai/Date-DPO-NoAsterisks +- flammenai/Prude-Phi3-DPO +- Atsunori/HelpSteer2-DPO +- jondurbin/gutenberg-dpo-v0.1 +- nbeerbower/gutenberg2-dpo +- nbeerbower/gutenberg-moderne-dpo +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/nbeerbower/Dumpling-Qwen2.5-1.5B + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-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/Dumpling-Qwen2.5-1.5B-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B.f16.gguf) | f16 | 3.2 | 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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +