commit 81c9810b148cd8359d35e5d7cbca59e6ef6dcee0 Author: ModelHub XC Date: Wed May 6 19:38:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Dumpling-Qwen2.5-7B-1k-r256-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b758d31 --- /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-Qwen2.5-7B-1k-r256.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-7B-1k-r256.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-7B-1k-r256.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-7B-1k-r256.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-7B-1k-r256.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-7B-1k-r256.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-7B-1k-r256.f16.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-7B-1k-r256.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-7B-1k-r256.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-7B-1k-r256.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-7B-1k-r256.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Dumpling-Qwen2.5-7B-1k-r256.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Dumpling-Qwen2.5-7B-1k-r256.IQ4_XS.gguf b/Dumpling-Qwen2.5-7B-1k-r256.IQ4_XS.gguf new file mode 100644 index 0000000..0cca135 --- /dev/null +++ b/Dumpling-Qwen2.5-7B-1k-r256.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98ce5700cd756acc54bc6f215bb07fe42c22954549105f5d8e5d358167410b7d +size 4250301696 diff --git a/Dumpling-Qwen2.5-7B-1k-r256.Q2_K.gguf b/Dumpling-Qwen2.5-7B-1k-r256.Q2_K.gguf new file mode 100644 index 0000000..ab59a0e --- /dev/null +++ b/Dumpling-Qwen2.5-7B-1k-r256.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4fdcd160f09d5f5a09bbcd64c59127d71b353b97d97b29687366fb9d79c92ba +size 3015943424 diff --git a/Dumpling-Qwen2.5-7B-1k-r256.Q3_K_L.gguf b/Dumpling-Qwen2.5-7B-1k-r256.Q3_K_L.gguf new file mode 100644 index 0000000..88016e6 --- /dev/null +++ b/Dumpling-Qwen2.5-7B-1k-r256.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c254adabf927eeddb687a56850a34fc5b9cf240240e49da778a143df3adaf7ce +size 4088462592 diff --git a/Dumpling-Qwen2.5-7B-1k-r256.Q3_K_M.gguf b/Dumpling-Qwen2.5-7B-1k-r256.Q3_K_M.gguf new file mode 100644 index 0000000..1caa90a --- /dev/null +++ b/Dumpling-Qwen2.5-7B-1k-r256.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1727d1a9929b85573a885802f9488958ed0555c98ce0af03b5267dd309494776 +size 3808394496 diff --git a/Dumpling-Qwen2.5-7B-1k-r256.Q3_K_S.gguf b/Dumpling-Qwen2.5-7B-1k-r256.Q3_K_S.gguf new file mode 100644 index 0000000..260c394 --- /dev/null +++ b/Dumpling-Qwen2.5-7B-1k-r256.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50d598d217254397c95096a9d1da9cf6e37507d591010547982d2ad7c6cbcb54 +size 3492371712 diff --git a/Dumpling-Qwen2.5-7B-1k-r256.Q4_K_M.gguf b/Dumpling-Qwen2.5-7B-1k-r256.Q4_K_M.gguf new file mode 100644 index 0000000..9b21c3f --- /dev/null +++ b/Dumpling-Qwen2.5-7B-1k-r256.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b01d456977fa2bd967829cd54a8e2547e4def9ce1745acd09cac22c17792ebdf +size 4683076864 diff --git a/Dumpling-Qwen2.5-7B-1k-r256.Q4_K_S.gguf b/Dumpling-Qwen2.5-7B-1k-r256.Q4_K_S.gguf new file mode 100644 index 0000000..3d34dab --- /dev/null +++ b/Dumpling-Qwen2.5-7B-1k-r256.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12a2c66879fc1c9a29d7a4d118526e73d8c810d36f21c126c3282a7ad9af1599 +size 4457772288 diff --git a/Dumpling-Qwen2.5-7B-1k-r256.Q5_K_M.gguf b/Dumpling-Qwen2.5-7B-1k-r256.Q5_K_M.gguf new file mode 100644 index 0000000..f49fad7 --- /dev/null +++ b/Dumpling-Qwen2.5-7B-1k-r256.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d34e8e8213703745911401f62ce5dbc7e52c6a553485160201b28cd6ab5fe28 +size 5444834560 diff --git a/Dumpling-Qwen2.5-7B-1k-r256.Q5_K_S.gguf b/Dumpling-Qwen2.5-7B-1k-r256.Q5_K_S.gguf new file mode 100644 index 0000000..31981f2 --- /dev/null +++ b/Dumpling-Qwen2.5-7B-1k-r256.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b910170e0ac309c17708cac0f26f6eb7b6666d5b33f54f56e551c53663d7a45c +size 5315179776 diff --git a/Dumpling-Qwen2.5-7B-1k-r256.Q6_K.gguf b/Dumpling-Qwen2.5-7B-1k-r256.Q6_K.gguf new file mode 100644 index 0000000..f55f423 --- /dev/null +++ b/Dumpling-Qwen2.5-7B-1k-r256.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08afb7f93cf7f5c8ff8712dc65305b0d1b098c5160d4e1921f2810d531c8e0ba +size 6254202112 diff --git a/Dumpling-Qwen2.5-7B-1k-r256.Q8_0.gguf b/Dumpling-Qwen2.5-7B-1k-r256.Q8_0.gguf new file mode 100644 index 0000000..a9787f8 --- /dev/null +++ b/Dumpling-Qwen2.5-7B-1k-r256.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd22af2af6e12ce982d973ba5811a0adcbc8e2bf435a5d20638130429ebd7015 +size 8098528512 diff --git a/Dumpling-Qwen2.5-7B-1k-r256.f16.gguf b/Dumpling-Qwen2.5-7B-1k-r256.f16.gguf new file mode 100644 index 0000000..080a2e2 --- /dev/null +++ b/Dumpling-Qwen2.5-7B-1k-r256.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1500855672722ff576cd45e65536a154a9c55bf0b24c9329ada2df5ae971497e +size 15237856512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..02d88ec --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: nbeerbower/Dumpling-Qwen2.5-7B-1k-r256 +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-Qwen2.5-7B-1k-r256 + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Dumpling-Qwen2.5-7B-1k-r256-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-Qwen2.5-7B-1k-r256-GGUF/resolve/main/Dumpling-Qwen2.5-7B-1k-r256.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-7B-1k-r256-GGUF/resolve/main/Dumpling-Qwen2.5-7B-1k-r256.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-7B-1k-r256-GGUF/resolve/main/Dumpling-Qwen2.5-7B-1k-r256.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-7B-1k-r256-GGUF/resolve/main/Dumpling-Qwen2.5-7B-1k-r256.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-7B-1k-r256-GGUF/resolve/main/Dumpling-Qwen2.5-7B-1k-r256.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-7B-1k-r256-GGUF/resolve/main/Dumpling-Qwen2.5-7B-1k-r256.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-7B-1k-r256-GGUF/resolve/main/Dumpling-Qwen2.5-7B-1k-r256.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-7B-1k-r256-GGUF/resolve/main/Dumpling-Qwen2.5-7B-1k-r256.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-7B-1k-r256-GGUF/resolve/main/Dumpling-Qwen2.5-7B-1k-r256.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-7B-1k-r256-GGUF/resolve/main/Dumpling-Qwen2.5-7B-1k-r256.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-7B-1k-r256-GGUF/resolve/main/Dumpling-Qwen2.5-7B-1k-r256.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Dumpling-Qwen2.5-7B-1k-r256-GGUF/resolve/main/Dumpling-Qwen2.5-7B-1k-r256.f16.gguf) | f16 | 15.3 | 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. + +