commit b9822495b1d1bffdf31aaba6c3aa8903b162228f Author: ModelHub XC Date: Wed May 20 15:11:43 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-KTO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1878db6 --- /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-KTO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-gen-dpo-10k-KTO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-KTO.IQ4_XS.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.IQ4_XS.gguf new file mode 100644 index 0000000..7282725 --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65400342e40c2e888138d35abf05b8c9157c052251ce98742b7832381394acb3 +size 4250297120 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q2_K.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q2_K.gguf new file mode 100644 index 0000000..cf031a8 --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5139eadadb9ea69104e29253b7f5deee9f765d1f35b759f25f760afe9097d405 +size 3015938848 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q3_K_L.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q3_K_L.gguf new file mode 100644 index 0000000..51b4f86 --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cd0101e7ccf6795ad39321fbbe99068b9885be86b1e56dbfd1a798aea6d1aad +size 4088458016 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q3_K_M.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q3_K_M.gguf new file mode 100644 index 0000000..f16598b --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:656302a57bce60301344b4589aa3cffe92f38176697b2223d142c5d263cede12 +size 3808389920 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q3_K_S.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q3_K_S.gguf new file mode 100644 index 0000000..c6db0ea --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e686cc325fc9748367b346c3ad5759437fc0d8249245928d1831ad692ef6c3ae +size 3492367136 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q4_K_M.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q4_K_M.gguf new file mode 100644 index 0000000..fc36131 --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:138fd9be772028d4cadc7d2f123d4d5411c3d92434f69b68db1a0ffad1e9e7d3 +size 4683072288 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q4_K_S.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q4_K_S.gguf new file mode 100644 index 0000000..e4981b8 --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d2231bf45cac3062baee05bf83dcfc3ce62d2d3ef2bb837a53e3e5dbef257f2 +size 4457767712 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q5_K_M.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q5_K_M.gguf new file mode 100644 index 0000000..e1f3d48 --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99cd63583ca877dcb2a7c5012c9ff0f533fee8d294abc8da574e48d1eab3f59c +size 5444829984 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q5_K_S.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q5_K_S.gguf new file mode 100644 index 0000000..99e66c9 --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6161c29979150fe1540e64d82b8508815c00359f0fcf49597eafec7852ecb173 +size 5315175200 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q6_K.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q6_K.gguf new file mode 100644 index 0000000..d56300a --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa92e6cf058b1bf3bb74aeb96c5bf4a355570167135ff98c0338affa4f31961d +size 6254197536 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q8_0.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q8_0.gguf new file mode 100644 index 0000000..72cc882 --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b115cf4da36e448370dc73f40f764695ff31b6ca8bde655c681395c026d349e +size 8098523936 diff --git a/Qwen2.5-7B-sft-gen-dpo-10k-KTO.f16.gguf b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.f16.gguf new file mode 100644 index 0000000..9be22a0 --- /dev/null +++ b/Qwen2.5-7B-sft-gen-dpo-10k-KTO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d48bc2df4c8773f872f921de22051e5c36aac8bba00cf83bb3100ef5903c319 +size 15237851936 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ec76fec --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: AmberYifan/Qwen2.5-7B-sft-gen-dpo-10k-KTO +language: +- en +library_name: transformers +model_name: Qwen2.5-7B-sft-gen-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-gen-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-gen-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-gen-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-KTO.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-dpo-10k-KTO.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-gen-dpo-10k-KTO-GGUF/resolve/main/Qwen2.5-7B-sft-gen-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. + +