commit cd0764ef85e718e7c172efc6cfb8bd9181b66bdc Author: ModelHub XC Date: Fri Oct 9 18:53:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8c63f7c --- /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-Instruct-wildfeedback-DRIFT-iter2-RPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.IQ4_XS.gguf b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.IQ4_XS.gguf new file mode 100644 index 0000000..ee495d5 --- /dev/null +++ b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae295d04bc35754bb62fddb510c92a9018ce16d97972b3c4afff02e78d7d890c +size 4250299328 diff --git a/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q2_K.gguf b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q2_K.gguf new file mode 100644 index 0000000..04a8a90 --- /dev/null +++ b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12ab167c9c41cdf9d5c25205d072008eb751bbaf9d6ca482913cbe8e15545533 +size 3015941056 diff --git a/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q3_K_L.gguf b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q3_K_L.gguf new file mode 100644 index 0000000..8b27293 --- /dev/null +++ b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a28f089bfaea8b0b4924087d373fc49d0ceb4d34b4f012ef3a4587c8c5500044 +size 4088460224 diff --git a/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q3_K_M.gguf b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q3_K_M.gguf new file mode 100644 index 0000000..650049a --- /dev/null +++ b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fd07b1935bca8f22af3b9f23190b215061d9a1808da6648161c6f13bec08d86 +size 3808392128 diff --git a/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q3_K_S.gguf b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q3_K_S.gguf new file mode 100644 index 0000000..ff0c742 --- /dev/null +++ b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbd0f2d2cb0d7823c24ea3db81079ebc3db40d7f3b580f45d2a9cc36cd86e69c +size 3492369344 diff --git a/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q4_K_M.gguf b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q4_K_M.gguf new file mode 100644 index 0000000..9bb3133 --- /dev/null +++ b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f15bc4489b0d8f8816ee0b9dc9c7a47b2029943cb867763770dfddb5d6881e11 +size 4683074496 diff --git a/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q4_K_S.gguf b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q4_K_S.gguf new file mode 100644 index 0000000..13fb09a --- /dev/null +++ b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94da1c92699db824bdbdf5cb29911f19d252903f5fba20b6b3389e64958b9de5 +size 4457769920 diff --git a/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q5_K_M.gguf b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q5_K_M.gguf new file mode 100644 index 0000000..8ecf903 --- /dev/null +++ b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e577c551bab56842ee26a5f599f3bc64d7c7b33b34336ae66ccb295fbe4543e8 +size 5444832192 diff --git a/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q5_K_S.gguf b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q5_K_S.gguf new file mode 100644 index 0000000..da1d1a4 --- /dev/null +++ b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f0928a0125cfe940fe03a170d2fd115053296395d0420f0a1f7637d24a06b2f +size 5315177408 diff --git a/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q6_K.gguf b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q6_K.gguf new file mode 100644 index 0000000..b245418 --- /dev/null +++ b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12ed942b1b09d883add18e8afa34863171f9295c4d77ad61af7bc300fa468051 +size 6254199744 diff --git a/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q8_0.gguf b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q8_0.gguf new file mode 100644 index 0000000..3419f8d --- /dev/null +++ b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73e914639e6d476d7a6f0446103ad23f4e453ef87e4e73d7d328bfa95f68082b +size 8098526144 diff --git a/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.f16.gguf b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.f16.gguf new file mode 100644 index 0000000..1c78f58 --- /dev/null +++ b/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02e14260dd40808f74d905200d8e03a6f4ff4f0f48c920376fb9240dbca899b7 +size 15237854144 diff --git a/README.md b/README.md new file mode 100644 index 0000000..32ac6fb --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: AmberYifan/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO +language: +- en +library_name: transformers +model_name: Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + + + + +static quants of https://huggingface.co/AmberYifan/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO-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-Instruct-wildfeedback-DRIFT-iter2-RPO-GGUF/resolve/main/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO-GGUF/resolve/main/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q3_K_S.gguf) | Q3_K_S | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO-GGUF/resolve/main/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO-GGUF/resolve/main/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q3_K_L.gguf) | Q3_K_L | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO-GGUF/resolve/main/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO-GGUF/resolve/main/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO-GGUF/resolve/main/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO-GGUF/resolve/main/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q5_K_S.gguf) | Q5_K_S | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO-GGUF/resolve/main/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q5_K_M.gguf) | Q5_K_M | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO-GGUF/resolve/main/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q6_K.gguf) | Q6_K | 6.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO-GGUF/resolve/main/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO-GGUF/resolve/main/Qwen2.5-7B-Instruct-wildfeedback-DRIFT-iter2-RPO.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. + +