commit ae8e318db06b73c267395c33f47e14c77b25cfc6 Author: ModelHub XC Date: Tue Apr 21 01:25:34 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Dumpling-Qwen2.5-1.5B-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..0945759 --- /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-v2.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-1.5B-v2.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Dumpling-Qwen2.5-1.5B-v2.IQ4_XS.gguf b/Dumpling-Qwen2.5-1.5B-v2.IQ4_XS.gguf new file mode 100644 index 0000000..28fb376 --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B-v2.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bc81f98cc000f1201a6044def9566df989680ac53d987b39a453f1803930874 +size 902185856 diff --git a/Dumpling-Qwen2.5-1.5B-v2.Q2_K.gguf b/Dumpling-Qwen2.5-1.5B-v2.Q2_K.gguf new file mode 100644 index 0000000..423907b --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c4f008d1483d1504c99055727e1de7080dc845eee6b21dc67357f654d7006d8 +size 676307840 diff --git a/Dumpling-Qwen2.5-1.5B-v2.Q3_K_L.gguf b/Dumpling-Qwen2.5-1.5B-v2.Q3_K_L.gguf new file mode 100644 index 0000000..e355da9 --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:800d7ee14f8e106bf6e243adf438f2ec4646511943796c6531796d8a67dec13d +size 880165760 diff --git a/Dumpling-Qwen2.5-1.5B-v2.Q3_K_M.gguf b/Dumpling-Qwen2.5-1.5B-v2.Q3_K_M.gguf new file mode 100644 index 0000000..d4430a7 --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd108ca7602793fd0f568a8bcb6dafe43111c2b1cd04d681daca2e4bd8a5b1f8 +size 824181632 diff --git a/Dumpling-Qwen2.5-1.5B-v2.Q3_K_S.gguf b/Dumpling-Qwen2.5-1.5B-v2.Q3_K_S.gguf new file mode 100644 index 0000000..106bcbd --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c0e24c40611737d438494dba21d6c886d7678e024023310932e330b567109e3 +size 760947584 diff --git a/Dumpling-Qwen2.5-1.5B-v2.Q4_K_M.gguf b/Dumpling-Qwen2.5-1.5B-v2.Q4_K_M.gguf new file mode 100644 index 0000000..529ad86 --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ac2652871707d0c24a6ad9e6f0c4121d67a1dca4aa07438b4bca267c694570e +size 986051456 diff --git a/Dumpling-Qwen2.5-1.5B-v2.Q4_K_S.gguf b/Dumpling-Qwen2.5-1.5B-v2.Q4_K_S.gguf new file mode 100644 index 0000000..eb2ba56 --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97aacfaff78299aefdd28ed6a0880ea26e283be6f2e628158557c36003445f3f +size 940315520 diff --git a/Dumpling-Qwen2.5-1.5B-v2.Q5_K_M.gguf b/Dumpling-Qwen2.5-1.5B-v2.Q5_K_M.gguf new file mode 100644 index 0000000..9f039f2 --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d077f40a311ae74044492ca55d612ec2fbb386a27a6997ee8c97e340b6b2b8ad +size 1125053312 diff --git a/Dumpling-Qwen2.5-1.5B-v2.Q5_K_S.gguf b/Dumpling-Qwen2.5-1.5B-v2.Q5_K_S.gguf new file mode 100644 index 0000000..35d0067 --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecb6531780b0aaaed84aac217f4f04bc084b34d98022eefe03abdcc0a0dc093c +size 1098732416 diff --git a/Dumpling-Qwen2.5-1.5B-v2.Q6_K.gguf b/Dumpling-Qwen2.5-1.5B-v2.Q6_K.gguf new file mode 100644 index 0000000..c231392 --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eabb9cd6a3b29108f0c88089a8fe1b8cf7407c09bb6c54cf6b292bb3341c595c +size 1272742784 diff --git a/Dumpling-Qwen2.5-1.5B-v2.Q8_0.gguf b/Dumpling-Qwen2.5-1.5B-v2.Q8_0.gguf new file mode 100644 index 0000000..71c0fec --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f33699328ab37924e7a904279b3a77696e5c5f01dad4d73455d25b68384cb7ae +size 1646576000 diff --git a/Dumpling-Qwen2.5-1.5B-v2.f16.gguf b/Dumpling-Qwen2.5-1.5B-v2.f16.gguf new file mode 100644 index 0000000..53862e5 --- /dev/null +++ b/Dumpling-Qwen2.5-1.5B-v2.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03b9f15834563821b049dbf32b30c28f33504e1de8f2bc09c1eed87c390c9598 +size 3093672320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..4f63ccf --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: nbeerbower/Dumpling-Qwen2.5-1.5B-v2 +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-v2 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-v2-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-v2-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B-v2.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-v2-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B-v2.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-v2-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B-v2.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-v2-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B-v2.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-v2-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B-v2.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-v2-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B-v2.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-v2-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B-v2.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-v2-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B-v2.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-v2-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B-v2.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-v2-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B-v2.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-v2-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B-v2.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-1.5B-v2-GGUF/resolve/main/Dumpling-Qwen2.5-1.5B-v2.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. + +