commit 2b60181fd72d0ada67ea7fcfbb4af035bf6fcded Author: ModelHub XC Date: Sat Apr 11 17:08:02 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2-0.5B-ORPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..90b4367 --- /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 +Qwen2-0.5B-ORPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-ORPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-ORPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-ORPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-ORPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-ORPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-ORPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-ORPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-ORPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-ORPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-ORPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2-0.5B-ORPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2-0.5B-ORPO.IQ4_XS.gguf b/Qwen2-0.5B-ORPO.IQ4_XS.gguf new file mode 100644 index 0000000..2b285c4 --- /dev/null +++ b/Qwen2-0.5B-ORPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0e2a33246a26a151338a9a71dcefd1b4cac8d60def102f46c02844451fddcdd +size 351443584 diff --git a/Qwen2-0.5B-ORPO.Q2_K.gguf b/Qwen2-0.5B-ORPO.Q2_K.gguf new file mode 100644 index 0000000..8bd1ae4 --- /dev/null +++ b/Qwen2-0.5B-ORPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2538cca136b266b1eec790c4fe2a414f78ce93fc6473a7783677599593781d3d +size 338605696 diff --git a/Qwen2-0.5B-ORPO.Q3_K_L.gguf b/Qwen2-0.5B-ORPO.Q3_K_L.gguf new file mode 100644 index 0000000..80b88be --- /dev/null +++ b/Qwen2-0.5B-ORPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20ab6d47180ca61623e72d6fbcb3b680ef7329c5fe6a3975256ef27ec8d3cd19 +size 369356416 diff --git a/Qwen2-0.5B-ORPO.Q3_K_M.gguf b/Qwen2-0.5B-ORPO.Q3_K_M.gguf new file mode 100644 index 0000000..6c81452 --- /dev/null +++ b/Qwen2-0.5B-ORPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:653b01a9f864cb6c4bbac4d36b54468cd647aabffd0da7503f5861d02d357b29 +size 355464832 diff --git a/Qwen2-0.5B-ORPO.Q3_K_S.gguf b/Qwen2-0.5B-ORPO.Q3_K_S.gguf new file mode 100644 index 0000000..e6006f7 --- /dev/null +++ b/Qwen2-0.5B-ORPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c666579a648d0d5c2ab6fb32d419c90bf80cd3e4be52dcfc0243ae23f285e187 +size 338261632 diff --git a/Qwen2-0.5B-ORPO.Q4_K_M.gguf b/Qwen2-0.5B-ORPO.Q4_K_M.gguf new file mode 100644 index 0000000..90f5168 --- /dev/null +++ b/Qwen2-0.5B-ORPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6304e1e67bd968598f8ce0bda95e35434fa1ec93727e5d48110fd3e5d9d86ac7 +size 397806208 diff --git a/Qwen2-0.5B-ORPO.Q4_K_S.gguf b/Qwen2-0.5B-ORPO.Q4_K_S.gguf new file mode 100644 index 0000000..2ba535c --- /dev/null +++ b/Qwen2-0.5B-ORPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:105310e5ee17ffa240d1e6eaf7f88f07eb329b47c88ae2cb765cd6a5507d066c +size 385470080 diff --git a/Qwen2-0.5B-ORPO.Q5_K_M.gguf b/Qwen2-0.5B-ORPO.Q5_K_M.gguf new file mode 100644 index 0000000..83f86c5 --- /dev/null +++ b/Qwen2-0.5B-ORPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbb1141c4e829ad067fd043a7b5c84c8965725b3b9c3063d8243c8c49bc9efd6 +size 420084352 diff --git a/Qwen2-0.5B-ORPO.Q5_K_S.gguf b/Qwen2-0.5B-ORPO.Q5_K_S.gguf new file mode 100644 index 0000000..5a2908d --- /dev/null +++ b/Qwen2-0.5B-ORPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd22e9e5e5ebf7b7dbbda6fbfe6d4380f52430d4318db338598638e8b251a574 +size 412708480 diff --git a/Qwen2-0.5B-ORPO.Q6_K.gguf b/Qwen2-0.5B-ORPO.Q6_K.gguf new file mode 100644 index 0000000..4ac41a5 --- /dev/null +++ b/Qwen2-0.5B-ORPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1021cdba55025185d36cfcfd1817fe41d00af340ea53896a5c6a596eb15d4204 +size 505734784 diff --git a/Qwen2-0.5B-ORPO.Q8_0.gguf b/Qwen2-0.5B-ORPO.Q8_0.gguf new file mode 100644 index 0000000..d8abdcf --- /dev/null +++ b/Qwen2-0.5B-ORPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00f7fac601525837c2e01aed4b8a9f0752c1323b85d8b18174d8c76f06632e07 +size 531066496 diff --git a/Qwen2-0.5B-ORPO.f16.gguf b/Qwen2-0.5B-ORPO.f16.gguf new file mode 100644 index 0000000..eda7ce2 --- /dev/null +++ b/Qwen2-0.5B-ORPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a9252cc2ec68c2259470fd62e66e769cb2adbda75c84d7d5b745928d1bdee66 +size 994155136 diff --git a/README.md b/README.md new file mode 100644 index 0000000..49ea32b --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: trl-lib/Qwen2-0.5B-ORPO +datasets: trl-lib/ultrafeedback_binarized +language: +- en +library_name: transformers +model_name: Qwen2-0.5B-ORPO +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- orpo +--- +## About + + + + + + +static quants of https://huggingface.co/trl-lib/Qwen2-0.5B-ORPO + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2-0.5B-ORPO-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2-0.5B-ORPO-i1-GGUF +## 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/Qwen2-0.5B-ORPO-GGUF/resolve/main/Qwen2-0.5B-ORPO.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-ORPO-GGUF/resolve/main/Qwen2-0.5B-ORPO.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-ORPO-GGUF/resolve/main/Qwen2-0.5B-ORPO.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-ORPO-GGUF/resolve/main/Qwen2-0.5B-ORPO.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-ORPO-GGUF/resolve/main/Qwen2-0.5B-ORPO.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-ORPO-GGUF/resolve/main/Qwen2-0.5B-ORPO.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-ORPO-GGUF/resolve/main/Qwen2-0.5B-ORPO.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-ORPO-GGUF/resolve/main/Qwen2-0.5B-ORPO.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-ORPO-GGUF/resolve/main/Qwen2-0.5B-ORPO.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-ORPO-GGUF/resolve/main/Qwen2-0.5B-ORPO.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-ORPO-GGUF/resolve/main/Qwen2-0.5B-ORPO.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2-0.5B-ORPO-GGUF/resolve/main/Qwen2-0.5B-ORPO.f16.gguf) | f16 | 1.1 | 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. + +