commit 87a0711579066a44377c89a8b9f6d540615ed83e Author: ModelHub XC Date: Wed May 6 05:31:37 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-LongPO-128K-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..5f7d474 --- /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 +Qwen2.5-7B-LongPO-128K.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-LongPO-128K.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-LongPO-128K.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-LongPO-128K.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-LongPO-128K.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-LongPO-128K.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-LongPO-128K.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-LongPO-128K.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-LongPO-128K.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-LongPO-128K.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-LongPO-128K.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-LongPO-128K.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-LongPO-128K.IQ4_XS.gguf b/Qwen2.5-7B-LongPO-128K.IQ4_XS.gguf new file mode 100644 index 0000000..b45f544 --- /dev/null +++ b/Qwen2.5-7B-LongPO-128K.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2965bf00c37bf50f5a17e410aa0f9914300ce1eceb783ee9942b87671d71f577 +size 4250298752 diff --git a/Qwen2.5-7B-LongPO-128K.Q2_K.gguf b/Qwen2.5-7B-LongPO-128K.Q2_K.gguf new file mode 100644 index 0000000..08aaef1 --- /dev/null +++ b/Qwen2.5-7B-LongPO-128K.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eb409090a6ceb0dfb9564683ad924afc535650e48824aacda02001fdf17f63d +size 3015940480 diff --git a/Qwen2.5-7B-LongPO-128K.Q3_K_L.gguf b/Qwen2.5-7B-LongPO-128K.Q3_K_L.gguf new file mode 100644 index 0000000..0b72718 --- /dev/null +++ b/Qwen2.5-7B-LongPO-128K.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11169e490bb8ce9766ca9a4c21f8073751d7810790288fcbb63f0d4300b65c06 +size 4088459648 diff --git a/Qwen2.5-7B-LongPO-128K.Q3_K_M.gguf b/Qwen2.5-7B-LongPO-128K.Q3_K_M.gguf new file mode 100644 index 0000000..28aaaeb --- /dev/null +++ b/Qwen2.5-7B-LongPO-128K.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c8fc6c2d589ef74c4d44247ebc0b224f589ea00306e3fa7b1b632eff9e5da1b +size 3808391552 diff --git a/Qwen2.5-7B-LongPO-128K.Q3_K_S.gguf b/Qwen2.5-7B-LongPO-128K.Q3_K_S.gguf new file mode 100644 index 0000000..6b9bac2 --- /dev/null +++ b/Qwen2.5-7B-LongPO-128K.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4f18862cc26e9e494a4b00a3ca26ec5c243347a8e7d6eb05c6d3eaaf90b0c6e +size 3492368768 diff --git a/Qwen2.5-7B-LongPO-128K.Q4_K_M.gguf b/Qwen2.5-7B-LongPO-128K.Q4_K_M.gguf new file mode 100644 index 0000000..865643f --- /dev/null +++ b/Qwen2.5-7B-LongPO-128K.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c916af7856fdaa9cab8b2d9e9d29d3595662ea2b63896dcd29c8daad54ca7fa5 +size 4683073920 diff --git a/Qwen2.5-7B-LongPO-128K.Q4_K_S.gguf b/Qwen2.5-7B-LongPO-128K.Q4_K_S.gguf new file mode 100644 index 0000000..85ea488 --- /dev/null +++ b/Qwen2.5-7B-LongPO-128K.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a584161e9cab6edc9234825a98133d66154663f53412d7440950b1e90ecf3152 +size 4457769344 diff --git a/Qwen2.5-7B-LongPO-128K.Q5_K_M.gguf b/Qwen2.5-7B-LongPO-128K.Q5_K_M.gguf new file mode 100644 index 0000000..ffd9d62 --- /dev/null +++ b/Qwen2.5-7B-LongPO-128K.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ba90a05d7a1a47322b1239598f537a914d59581a5072bb5e7051addbae10ffb +size 5444831616 diff --git a/Qwen2.5-7B-LongPO-128K.Q5_K_S.gguf b/Qwen2.5-7B-LongPO-128K.Q5_K_S.gguf new file mode 100644 index 0000000..f3e6334 --- /dev/null +++ b/Qwen2.5-7B-LongPO-128K.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaa150bfe541105fabed804d0f05c8abd7dd2adc1763c6a7cd0483966d3d14a4 +size 5315176832 diff --git a/Qwen2.5-7B-LongPO-128K.Q6_K.gguf b/Qwen2.5-7B-LongPO-128K.Q6_K.gguf new file mode 100644 index 0000000..2090c57 --- /dev/null +++ b/Qwen2.5-7B-LongPO-128K.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4263e3a71428618c7462e75e9180507f1b188d942a21f525c96fb38320151b4c +size 6254199168 diff --git a/Qwen2.5-7B-LongPO-128K.Q8_0.gguf b/Qwen2.5-7B-LongPO-128K.Q8_0.gguf new file mode 100644 index 0000000..c07dd59 --- /dev/null +++ b/Qwen2.5-7B-LongPO-128K.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ceeb29faaae2fb74cb9e7031e00102036916b2b120ae252751c226faeb550102 +size 8098525568 diff --git a/Qwen2.5-7B-LongPO-128K.f16.gguf b/Qwen2.5-7B-LongPO-128K.f16.gguf new file mode 100644 index 0000000..5cd5dec --- /dev/null +++ b/Qwen2.5-7B-LongPO-128K.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ccb61fd300e6aef3536fcf3ea7b0585dc6c622e69a9b33e5f32457c5f3bf9af +size 15237853568 diff --git a/README.md b/README.md new file mode 100644 index 0000000..173df9b --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: DAMO-NLP-SG/Qwen2.5-7B-LongPO-128K +datasets: +- DAMO-NLP-SG/Qwen2.5-7B-LongPO-128K-tokenized +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/DAMO-NLP-SG/Qwen2.5-7B-LongPO-128K + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-7B-LongPO-128K-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/Qwen2.5-7B-LongPO-128K-GGUF/resolve/main/Qwen2.5-7B-LongPO-128K.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-LongPO-128K-GGUF/resolve/main/Qwen2.5-7B-LongPO-128K.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-LongPO-128K-GGUF/resolve/main/Qwen2.5-7B-LongPO-128K.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-LongPO-128K-GGUF/resolve/main/Qwen2.5-7B-LongPO-128K.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-LongPO-128K-GGUF/resolve/main/Qwen2.5-7B-LongPO-128K.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-LongPO-128K-GGUF/resolve/main/Qwen2.5-7B-LongPO-128K.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-LongPO-128K-GGUF/resolve/main/Qwen2.5-7B-LongPO-128K.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-LongPO-128K-GGUF/resolve/main/Qwen2.5-7B-LongPO-128K.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-LongPO-128K-GGUF/resolve/main/Qwen2.5-7B-LongPO-128K.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-LongPO-128K-GGUF/resolve/main/Qwen2.5-7B-LongPO-128K.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-LongPO-128K-GGUF/resolve/main/Qwen2.5-7B-LongPO-128K.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-LongPO-128K-GGUF/resolve/main/Qwen2.5-7B-LongPO-128K.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. + +