commit 4e9b5a5ad1fc57881a32e6876fbc2e96026d4f56 Author: ModelHub XC Date: Sat Jul 11 11:40:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-sft-hhrlhf-dpo-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9059c7e --- /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-hhrlhf-dpo.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-hhrlhf-dpo.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-hhrlhf-dpo.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-hhrlhf-dpo.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-hhrlhf-dpo.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-hhrlhf-dpo.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-hhrlhf-dpo.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-hhrlhf-dpo.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-hhrlhf-dpo.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-hhrlhf-dpo.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-hhrlhf-dpo.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-sft-hhrlhf-dpo.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-sft-hhrlhf-dpo.IQ4_XS.gguf b/Qwen2.5-7B-sft-hhrlhf-dpo.IQ4_XS.gguf new file mode 100644 index 0000000..4928e22 --- /dev/null +++ b/Qwen2.5-7B-sft-hhrlhf-dpo.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70cf2acde11fd45cdcc7a3bc4714da72fac6249b028bbd21395d0d94f12a0f53 +size 4250297088 diff --git a/Qwen2.5-7B-sft-hhrlhf-dpo.Q2_K.gguf b/Qwen2.5-7B-sft-hhrlhf-dpo.Q2_K.gguf new file mode 100644 index 0000000..00da5c6 --- /dev/null +++ b/Qwen2.5-7B-sft-hhrlhf-dpo.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a39d6f181936268593a532917ad8a82c4d4c85d07f628f346b148c0a4539932 +size 3015938816 diff --git a/Qwen2.5-7B-sft-hhrlhf-dpo.Q3_K_L.gguf b/Qwen2.5-7B-sft-hhrlhf-dpo.Q3_K_L.gguf new file mode 100644 index 0000000..f0476cf --- /dev/null +++ b/Qwen2.5-7B-sft-hhrlhf-dpo.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92620bd79d2d7209b0cff3f2bdeccaf58e67d2128e67f065bd31669d0ea74046 +size 4088457984 diff --git a/Qwen2.5-7B-sft-hhrlhf-dpo.Q3_K_M.gguf b/Qwen2.5-7B-sft-hhrlhf-dpo.Q3_K_M.gguf new file mode 100644 index 0000000..1e26a6a --- /dev/null +++ b/Qwen2.5-7B-sft-hhrlhf-dpo.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:453b8fc7c47c31bd91ad31952d38878c21565a5c7e1b4092d379e352afaaa45c +size 3808389888 diff --git a/Qwen2.5-7B-sft-hhrlhf-dpo.Q3_K_S.gguf b/Qwen2.5-7B-sft-hhrlhf-dpo.Q3_K_S.gguf new file mode 100644 index 0000000..f564da7 --- /dev/null +++ b/Qwen2.5-7B-sft-hhrlhf-dpo.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48c1b6ea33355d8b5ec79bfb51435c6c70ad7b9aa388502438d70dae2b2dbaf4 +size 3492367104 diff --git a/Qwen2.5-7B-sft-hhrlhf-dpo.Q4_K_M.gguf b/Qwen2.5-7B-sft-hhrlhf-dpo.Q4_K_M.gguf new file mode 100644 index 0000000..7916beb --- /dev/null +++ b/Qwen2.5-7B-sft-hhrlhf-dpo.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee6eb32254d037476e71d68d026b7ddde7f3abc7dd33814edf9c69df6200f33e +size 4683072256 diff --git a/Qwen2.5-7B-sft-hhrlhf-dpo.Q4_K_S.gguf b/Qwen2.5-7B-sft-hhrlhf-dpo.Q4_K_S.gguf new file mode 100644 index 0000000..5261247 --- /dev/null +++ b/Qwen2.5-7B-sft-hhrlhf-dpo.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a35b1664b831f1965227aa0b7d507a5a58d8ad3f118a37834596cc84e7a74b9f +size 4457767680 diff --git a/Qwen2.5-7B-sft-hhrlhf-dpo.Q5_K_M.gguf b/Qwen2.5-7B-sft-hhrlhf-dpo.Q5_K_M.gguf new file mode 100644 index 0000000..022d0b5 --- /dev/null +++ b/Qwen2.5-7B-sft-hhrlhf-dpo.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f91f199f79be6b18d6026716eed6d659954bd5e68fd67a245dd78e9662f1818 +size 5444829952 diff --git a/Qwen2.5-7B-sft-hhrlhf-dpo.Q5_K_S.gguf b/Qwen2.5-7B-sft-hhrlhf-dpo.Q5_K_S.gguf new file mode 100644 index 0000000..94360eb --- /dev/null +++ b/Qwen2.5-7B-sft-hhrlhf-dpo.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea4b7cf5de6a3ea1ffd682d5000d6cac8f62f5e69f9d2f964591e400bd59621b +size 5315175168 diff --git a/Qwen2.5-7B-sft-hhrlhf-dpo.Q6_K.gguf b/Qwen2.5-7B-sft-hhrlhf-dpo.Q6_K.gguf new file mode 100644 index 0000000..a259784 --- /dev/null +++ b/Qwen2.5-7B-sft-hhrlhf-dpo.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e40205d26e55677d0415751d153fbb6478dd2af80897100180f88e704d2538e +size 6254197504 diff --git a/Qwen2.5-7B-sft-hhrlhf-dpo.Q8_0.gguf b/Qwen2.5-7B-sft-hhrlhf-dpo.Q8_0.gguf new file mode 100644 index 0000000..a2d0305 --- /dev/null +++ b/Qwen2.5-7B-sft-hhrlhf-dpo.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22e9345fc42eb9a04ef5202f38ec9a8249e5a545a494b1052a933c35b7c07a15 +size 8098523904 diff --git a/Qwen2.5-7B-sft-hhrlhf-dpo.f16.gguf b/Qwen2.5-7B-sft-hhrlhf-dpo.f16.gguf new file mode 100644 index 0000000..d561308 --- /dev/null +++ b/Qwen2.5-7B-sft-hhrlhf-dpo.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:893ea42b69f1458d505762e76ca5d140fe1659c3fe4f28674f3afacae4436558 +size 15237851904 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e6f57dd --- /dev/null +++ b/README.md @@ -0,0 +1,68 @@ +--- +base_model: AmberYifan/Qwen2.5-7B-sft-hhrlhf-dpo +language: +- en +library_name: transformers +model_name: Qwen2.5-7B-sft-hhrlhf-dpo +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/AmberYifan/Qwen2.5-7B-sft-hhrlhf-dpo + + +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-hhrlhf-dpo-GGUF/resolve/main/Qwen2.5-7B-sft-hhrlhf-dpo.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-hhrlhf-dpo-GGUF/resolve/main/Qwen2.5-7B-sft-hhrlhf-dpo.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-hhrlhf-dpo-GGUF/resolve/main/Qwen2.5-7B-sft-hhrlhf-dpo.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-hhrlhf-dpo-GGUF/resolve/main/Qwen2.5-7B-sft-hhrlhf-dpo.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-hhrlhf-dpo-GGUF/resolve/main/Qwen2.5-7B-sft-hhrlhf-dpo.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-hhrlhf-dpo-GGUF/resolve/main/Qwen2.5-7B-sft-hhrlhf-dpo.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-hhrlhf-dpo-GGUF/resolve/main/Qwen2.5-7B-sft-hhrlhf-dpo.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-hhrlhf-dpo-GGUF/resolve/main/Qwen2.5-7B-sft-hhrlhf-dpo.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-hhrlhf-dpo-GGUF/resolve/main/Qwen2.5-7B-sft-hhrlhf-dpo.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-hhrlhf-dpo-GGUF/resolve/main/Qwen2.5-7B-sft-hhrlhf-dpo.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-hhrlhf-dpo-GGUF/resolve/main/Qwen2.5-7B-sft-hhrlhf-dpo.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-sft-hhrlhf-dpo-GGUF/resolve/main/Qwen2.5-7B-sft-hhrlhf-dpo.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. + +