commit 22e6687a2c347fb33c39938ed24b2d2afca2b4c6 Author: ModelHub XC Date: Fri May 8 20:02:22 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-IPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..ba7c0ff --- /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-sft-gen-dpo-10k-IPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-IPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-IPO.IQ4_XS.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.IQ4_XS.gguf new file mode 100644 index 0000000..1a31dbf --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:525e29c3ae238b433c8e72128bd9f692ce0983ca33447902540eb4b582ad7f35 +size 4250297120 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q2_K.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q2_K.gguf new file mode 100644 index 0000000..2fbbc06 --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac4911a9aa32ecd1ec856c7f131b69f4766f4e886c46786a58b4f3fea0a60202 +size 3015938848 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q3_K_L.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q3_K_L.gguf new file mode 100644 index 0000000..cdae9b1 --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:296c98736bddd72941e0c84dc003d533287ec0f0037c902c16420ebe153b11ff +size 4088458016 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q3_K_M.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q3_K_M.gguf new file mode 100644 index 0000000..b3ade83 --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7abc05b8ad9eb3f4d1b33a9ab9a081e4f0d25df2a8eb48dc2a90b1bbb882289a +size 3808389920 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q3_K_S.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q3_K_S.gguf new file mode 100644 index 0000000..c4df949 --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7217fdad590d8a94ad7d6d3896573a2cc024f54419ea6f233c6bb8b230de1c44 +size 3492367136 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q4_K_M.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q4_K_M.gguf new file mode 100644 index 0000000..1c022f4 --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b865622ad99c371f0d1af3e8b5b3b4516f432dff58073d73decfac9f53fce8bf +size 4683072288 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q4_K_S.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q4_K_S.gguf new file mode 100644 index 0000000..33f3af2 --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6cdc6ed755376c42f347405d364433d916c73f4b08eaa2920dc565123ad1f7e +size 4457767712 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q5_K_M.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q5_K_M.gguf new file mode 100644 index 0000000..2c31153 --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95239d57bea80abb7003c5ffe4ffb30b43090a4edf5508fd79188f2d4b97553f +size 5444829984 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q5_K_S.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q5_K_S.gguf new file mode 100644 index 0000000..a1f1f4d --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5da5043724b75bc0aa57601fb222a1846d84934281958d62b50aaa2b70d20bde +size 5315175200 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q6_K.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q6_K.gguf new file mode 100644 index 0000000..4896b9a --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3006e6644b3538712bdb4a331af1214e6f3ee64b9e25d1cc3cbf36c0d140b716 +size 6254197536 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q8_0.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q8_0.gguf new file mode 100644 index 0000000..eb6afbb --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a14df32204031c46dcf4f30bd62b1fd744c847b36b609a21aa31911cc0081001 +size 8098523936 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-IPO.f16.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.f16.gguf new file mode 100644 index 0000000..873be7f --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-IPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a81606715cab39f43ac94d463196502858f18df2f7b4eb378140c0b1a41cb54 +size 15237851936 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dadb380 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: AmberYifan/Qwen2.5-7B-sft-gen-dpo-10k-IPO +language: +- en +library_name: transformers +model_name: Qwen2.5-7B-sft-gen-dpo-10k-IPO +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Qwen2.5-7B-sft-gen-dpo-10k-IPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-7B-sft-gen-dpo-10k-IPO-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/Qwen2.5-7B-sft-gen-dpo-10k-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-IPO.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-IPO.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-IPO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-IPO.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. + +