commit 2a8ebf7a2a58b758f66c4d8f4c83b984098ab494 Author: ModelHub XC Date: Wed May 20 15:15:44 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-sft-dpo-10k-KTO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..559efb9 --- /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-dpo-10k-KTO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-dpo-10k-KTO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-dpo-10k-KTO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-dpo-10k-KTO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-dpo-10k-KTO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-dpo-10k-KTO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-dpo-10k-KTO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-dpo-10k-KTO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-dpo-10k-KTO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-dpo-10k-KTO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-dpo-10k-KTO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-dpo-10k-KTO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-sft-dpo-10k-KTO.IQ4_XS.gguf b/Qwen2.5-7B-sft-dpo-10k-KTO.IQ4_XS.gguf new file mode 100644 index 0000000..d0b3443 --- /dev/null +++ b/Qwen2.5-7B-sft-dpo-10k-KTO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48d769195db6fcdc01c4501c7d133df8ed756e8c34a33982951d70845ff11f08 +size 4250297088 diff --git a/Qwen2.5-7B-sft-dpo-10k-KTO.Q2_K.gguf b/Qwen2.5-7B-sft-dpo-10k-KTO.Q2_K.gguf new file mode 100644 index 0000000..891e954 --- /dev/null +++ b/Qwen2.5-7B-sft-dpo-10k-KTO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dc178d45221f151322a427b02f8b2aca955bb3cdadfb032b3ab194e950b7d3e +size 3015938816 diff --git a/Qwen2.5-7B-sft-dpo-10k-KTO.Q3_K_L.gguf b/Qwen2.5-7B-sft-dpo-10k-KTO.Q3_K_L.gguf new file mode 100644 index 0000000..9839d47 --- /dev/null +++ b/Qwen2.5-7B-sft-dpo-10k-KTO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:241221e91ce164d1bf0bca975881336ecd29d7591eefa536bfd688577d5c1fc9 +size 4088457984 diff --git a/Qwen2.5-7B-sft-dpo-10k-KTO.Q3_K_M.gguf b/Qwen2.5-7B-sft-dpo-10k-KTO.Q3_K_M.gguf new file mode 100644 index 0000000..73733e1 --- /dev/null +++ b/Qwen2.5-7B-sft-dpo-10k-KTO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c6edb23667e0bd92fbbc8b34050bd5a2dc84b7f2217e4d49ce17b1ed02a4574 +size 3808389888 diff --git a/Qwen2.5-7B-sft-dpo-10k-KTO.Q3_K_S.gguf b/Qwen2.5-7B-sft-dpo-10k-KTO.Q3_K_S.gguf new file mode 100644 index 0000000..d110987 --- /dev/null +++ b/Qwen2.5-7B-sft-dpo-10k-KTO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4a344077c5a457da90cb52c183cd681bd32168b57b4425933b6fe73cc72886c +size 3492367104 diff --git a/Qwen2.5-7B-sft-dpo-10k-KTO.Q4_K_M.gguf b/Qwen2.5-7B-sft-dpo-10k-KTO.Q4_K_M.gguf new file mode 100644 index 0000000..03635cc --- /dev/null +++ b/Qwen2.5-7B-sft-dpo-10k-KTO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd0204f6d0f93f27fc481e734980fb036ee8b2a5a52130869a55be714e6e7804 +size 4683072256 diff --git a/Qwen2.5-7B-sft-dpo-10k-KTO.Q4_K_S.gguf b/Qwen2.5-7B-sft-dpo-10k-KTO.Q4_K_S.gguf new file mode 100644 index 0000000..34b2215 --- /dev/null +++ b/Qwen2.5-7B-sft-dpo-10k-KTO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd99e732919981f65020e053f55b961eab198cdfd0593dc79853c7afdfd4aa87 +size 4457767680 diff --git a/Qwen2.5-7B-sft-dpo-10k-KTO.Q5_K_M.gguf b/Qwen2.5-7B-sft-dpo-10k-KTO.Q5_K_M.gguf new file mode 100644 index 0000000..27c5ad1 --- /dev/null +++ b/Qwen2.5-7B-sft-dpo-10k-KTO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7378dad74c20fd039a194b9167d5cf86e935ea0921820245489700d829aa4653 +size 5444829952 diff --git a/Qwen2.5-7B-sft-dpo-10k-KTO.Q5_K_S.gguf b/Qwen2.5-7B-sft-dpo-10k-KTO.Q5_K_S.gguf new file mode 100644 index 0000000..7be5ba0 --- /dev/null +++ b/Qwen2.5-7B-sft-dpo-10k-KTO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbbecd7e83e9c06c43065fd426bdae28e62bfb7dfd9fe19339a6ade3d230da0d +size 5315175168 diff --git a/Qwen2.5-7B-sft-dpo-10k-KTO.Q6_K.gguf b/Qwen2.5-7B-sft-dpo-10k-KTO.Q6_K.gguf new file mode 100644 index 0000000..16f41fd --- /dev/null +++ b/Qwen2.5-7B-sft-dpo-10k-KTO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31e36bfa830bbd373897fdb78824af19873a6e7409c4b8d12464768275fb3173 +size 6254197504 diff --git a/Qwen2.5-7B-sft-dpo-10k-KTO.Q8_0.gguf b/Qwen2.5-7B-sft-dpo-10k-KTO.Q8_0.gguf new file mode 100644 index 0000000..a321bc0 --- /dev/null +++ b/Qwen2.5-7B-sft-dpo-10k-KTO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c964d58e14667e3d7da2c963a608c9aeee6ab0d837624dac6ce26ce4e24db596 +size 8098523904 diff --git a/Qwen2.5-7B-sft-dpo-10k-KTO.f16.gguf b/Qwen2.5-7B-sft-dpo-10k-KTO.f16.gguf new file mode 100644 index 0000000..121fac2 --- /dev/null +++ b/Qwen2.5-7B-sft-dpo-10k-KTO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:261a7a67ceb5b22614d86d0c07ab75cff2aa5b49336e6780886ae8a4a96b2536 +size 15237851904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1edf859 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: AmberYifan/Qwen2.5-7B-sft-dpo-10k-KTO +language: +- en +library_name: transformers +model_name: Qwen2.5-7B-sft-dpo-10k-KTO +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- kto +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Qwen2.5-7B-sft-dpo-10k-KTO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-7B-sft-dpo-10k-KTO-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-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-dpo-10k-KTO.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-dpo-10k-KTO.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-dpo-10k-KTO.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-dpo-10k-KTO.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-dpo-10k-KTO.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-dpo-10k-KTO.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-dpo-10k-KTO.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-dpo-10k-KTO.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-dpo-10k-KTO.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-dpo-10k-KTO.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-dpo-10k-KTO.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-dpo-10k-KTO.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. + +