commit 01848b2bacdf5354b5d68d432b16c3812de08a0b Author: ModelHub XC Date: Wed Jun 17 13:43:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-0.5B-Instruct-medical-dpo-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b692a88 --- /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 +Qwen2.5-0.5B-Instruct-medical-dpo.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-medical-dpo.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-medical-dpo.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-medical-dpo.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-medical-dpo.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-medical-dpo.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-medical-dpo.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-medical-dpo.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-medical-dpo.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-medical-dpo.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-medical-dpo.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-0.5B-Instruct-medical-dpo.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-0.5B-Instruct-medical-dpo.IQ4_XS.gguf b/Qwen2.5-0.5B-Instruct-medical-dpo.IQ4_XS.gguf new file mode 100644 index 0000000..a029cef --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-medical-dpo.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:212aae16efd38ce443746202206ca92d7bb739f7153508675adeca3f98ceca3d +size 351178816 diff --git a/Qwen2.5-0.5B-Instruct-medical-dpo.Q2_K.gguf b/Qwen2.5-0.5B-Instruct-medical-dpo.Q2_K.gguf new file mode 100644 index 0000000..091bf69 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-medical-dpo.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa508e406881ad025844ea64a0ced1c94e7f9204ad5ba8c55b65f496a0f124c9 +size 338340928 diff --git a/Qwen2.5-0.5B-Instruct-medical-dpo.Q3_K_L.gguf b/Qwen2.5-0.5B-Instruct-medical-dpo.Q3_K_L.gguf new file mode 100644 index 0000000..5dcf181 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-medical-dpo.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d6656dacb10e64cb6a8a0bffe9916aa23d80cc855bb876fc800a3ecc5633208 +size 369091648 diff --git a/Qwen2.5-0.5B-Instruct-medical-dpo.Q3_K_M.gguf b/Qwen2.5-0.5B-Instruct-medical-dpo.Q3_K_M.gguf new file mode 100644 index 0000000..25136cb --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-medical-dpo.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e384f70befbe43334a22ed788731286951ac2bc2a7aa560bc27a43e84c575bb +size 355200064 diff --git a/Qwen2.5-0.5B-Instruct-medical-dpo.Q3_K_S.gguf b/Qwen2.5-0.5B-Instruct-medical-dpo.Q3_K_S.gguf new file mode 100644 index 0000000..d2630d5 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-medical-dpo.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18ba1625129f479d628c6359964f0d70d2e649e372d8b51e2106e1cc7ab0ad5b +size 337996864 diff --git a/Qwen2.5-0.5B-Instruct-medical-dpo.Q4_K_M.gguf b/Qwen2.5-0.5B-Instruct-medical-dpo.Q4_K_M.gguf new file mode 100644 index 0000000..62489e2 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-medical-dpo.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53efd61dc924c414f2e8c6c18f0f230c6e2c31bec11ad57447fae528651d299a +size 397541440 diff --git a/Qwen2.5-0.5B-Instruct-medical-dpo.Q4_K_S.gguf b/Qwen2.5-0.5B-Instruct-medical-dpo.Q4_K_S.gguf new file mode 100644 index 0000000..f36adce --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-medical-dpo.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:add7c7cd6335a4e6f8b44f897310d25f7d88ad4254c4ebf1f47ff374b0e6faa2 +size 385205312 diff --git a/Qwen2.5-0.5B-Instruct-medical-dpo.Q5_K_M.gguf b/Qwen2.5-0.5B-Instruct-medical-dpo.Q5_K_M.gguf new file mode 100644 index 0000000..e4357d6 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-medical-dpo.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a0f09de679e73fe9c33eb28e59ff76ada621d8c05355d27eb97d7890e627a6a +size 419819584 diff --git a/Qwen2.5-0.5B-Instruct-medical-dpo.Q5_K_S.gguf b/Qwen2.5-0.5B-Instruct-medical-dpo.Q5_K_S.gguf new file mode 100644 index 0000000..8fde7ba --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-medical-dpo.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dedb5af3224d1128ad348f74a286549a46b6fb7b3aaa81d536b44e7f7daf431c +size 412443712 diff --git a/Qwen2.5-0.5B-Instruct-medical-dpo.Q6_K.gguf b/Qwen2.5-0.5B-Instruct-medical-dpo.Q6_K.gguf new file mode 100644 index 0000000..0c0aca0 --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-medical-dpo.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0469bb19d76144b4cc533948a0c541c1324362f185acaddbf36d55fdc2d776d +size 505470016 diff --git a/Qwen2.5-0.5B-Instruct-medical-dpo.Q8_0.gguf b/Qwen2.5-0.5B-Instruct-medical-dpo.Q8_0.gguf new file mode 100644 index 0000000..a4c519f --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-medical-dpo.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2ffe40276fd2d71911b1b74300688350c55bd8cc8bc3aa191d2e35be6614f0b +size 530801728 diff --git a/Qwen2.5-0.5B-Instruct-medical-dpo.f16.gguf b/Qwen2.5-0.5B-Instruct-medical-dpo.f16.gguf new file mode 100644 index 0000000..86eec4d --- /dev/null +++ b/Qwen2.5-0.5B-Instruct-medical-dpo.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd4e8bfa7792cd7c0451c261cd91e5862b0d3e8ddac5e4cbeaca53951389ac66 +size 993662720 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a312c8c --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: nuriyev/Qwen2.5-0.5B-Instruct-medical-dpo +datasets: +- nuriyev/medical-question-answering-rl-labeled-qwen-0.5B-binarized_v2 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/nuriyev/Qwen2.5-0.5B-Instruct-medical-dpo + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-0.5B-Instruct-medical-dpo-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-medical-dpo-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/Qwen2.5-0.5B-Instruct-medical-dpo-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-medical-dpo.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-medical-dpo-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-medical-dpo.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-medical-dpo-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-medical-dpo.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-medical-dpo-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-medical-dpo.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-medical-dpo-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-medical-dpo.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-medical-dpo-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-medical-dpo.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-medical-dpo-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-medical-dpo.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-medical-dpo-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-medical-dpo.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-medical-dpo-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-medical-dpo.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-medical-dpo-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-medical-dpo.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-medical-dpo-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-medical-dpo.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-0.5B-Instruct-medical-dpo-GGUF/resolve/main/Qwen2.5-0.5B-Instruct-medical-dpo.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. + +