commit 67e2eabb32ad7930ae9a9f6bc7b8784d4f93fc56 Author: ModelHub XC Date: Mon Apr 13 06:14:00 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2.5-3B-DPO-TinyStories-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..aaf68af --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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 +Qwen2.5-3B-DPO-TinyStories.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-DPO-TinyStories.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-DPO-TinyStories.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-DPO-TinyStories.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-DPO-TinyStories.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-DPO-TinyStories.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-DPO-TinyStories.f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-DPO-TinyStories.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-DPO-TinyStories.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-DPO-TinyStories.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-DPO-TinyStories.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-DPO-TinyStories.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2.5-3B-DPO-TinyStories.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2.5-3B-DPO-TinyStories.IQ4_XS.gguf b/Qwen2.5-3B-DPO-TinyStories.IQ4_XS.gguf new file mode 100644 index 0000000..4923716 --- /dev/null +++ b/Qwen2.5-3B-DPO-TinyStories.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cece1746e01e19b2a68cc5dfd4b28902b96d0031a3b61d90215f492560b90c15 +size 1753183072 diff --git a/Qwen2.5-3B-DPO-TinyStories.Q2_K.gguf b/Qwen2.5-3B-DPO-TinyStories.Q2_K.gguf new file mode 100644 index 0000000..41fe9a8 --- /dev/null +++ b/Qwen2.5-3B-DPO-TinyStories.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf29edc7a825036e4a995813e5b50c6817a7ec1d7fcabfc5531167667253cdb +size 1274753888 diff --git a/Qwen2.5-3B-DPO-TinyStories.Q3_K_L.gguf b/Qwen2.5-3B-DPO-TinyStories.Q3_K_L.gguf new file mode 100644 index 0000000..4b13ae2 --- /dev/null +++ b/Qwen2.5-3B-DPO-TinyStories.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7396ac7fa380f54730fbc802ed1afeda4033cbe23797fd359923edf8772b4c83 +size 1707389792 diff --git a/Qwen2.5-3B-DPO-TinyStories.Q3_K_M.gguf b/Qwen2.5-3B-DPO-TinyStories.Q3_K_M.gguf new file mode 100644 index 0000000..f075e5c --- /dev/null +++ b/Qwen2.5-3B-DPO-TinyStories.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f44ac1da2aa6f13b5c89fe279c8d45f388da22a2cd5024883e9546908c083e51 +size 1590473568 diff --git a/Qwen2.5-3B-DPO-TinyStories.Q3_K_S.gguf b/Qwen2.5-3B-DPO-TinyStories.Q3_K_S.gguf new file mode 100644 index 0000000..a4e3735 --- /dev/null +++ b/Qwen2.5-3B-DPO-TinyStories.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bf6b70b3a27199c7fb9376605f83cc85952e0124b222bdb432e011ab157999f +size 1454355296 diff --git a/Qwen2.5-3B-DPO-TinyStories.Q4_0_4_4.gguf b/Qwen2.5-3B-DPO-TinyStories.Q4_0_4_4.gguf new file mode 100644 index 0000000..22a62ff --- /dev/null +++ b/Qwen2.5-3B-DPO-TinyStories.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e969746367274c6bcf881ea0d4c2a7a3d437df829c2a7c0043ed4bded2b44832 +size 1822847840 diff --git a/Qwen2.5-3B-DPO-TinyStories.Q4_K_M.gguf b/Qwen2.5-3B-DPO-TinyStories.Q4_K_M.gguf new file mode 100644 index 0000000..cdf61de --- /dev/null +++ b/Qwen2.5-3B-DPO-TinyStories.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d473318b44716a5840efb11f4ddca1b441a9ef1f9b711e578212b56b7a6a573 +size 1929900896 diff --git a/Qwen2.5-3B-DPO-TinyStories.Q4_K_S.gguf b/Qwen2.5-3B-DPO-TinyStories.Q4_K_S.gguf new file mode 100644 index 0000000..20f69ac --- /dev/null +++ b/Qwen2.5-3B-DPO-TinyStories.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:281578b6f6c4a993ca4f51b97052bddf725317202662746da6931e37e0e52df1 +size 1834382176 diff --git a/Qwen2.5-3B-DPO-TinyStories.Q5_K_M.gguf b/Qwen2.5-3B-DPO-TinyStories.Q5_K_M.gguf new file mode 100644 index 0000000..18323ed --- /dev/null +++ b/Qwen2.5-3B-DPO-TinyStories.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e952e0ab6c63a9fcc2e71d24db8906d37848adff4094bf90a6af2eb005674649 +size 2224812896 diff --git a/Qwen2.5-3B-DPO-TinyStories.Q5_K_S.gguf b/Qwen2.5-3B-DPO-TinyStories.Q5_K_S.gguf new file mode 100644 index 0000000..217e519 --- /dev/null +++ b/Qwen2.5-3B-DPO-TinyStories.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85a629227adc9d5b837b6cafb325501bf078e3fa18946a93b3c0a9dae2d00608 +size 2169664352 diff --git a/Qwen2.5-3B-DPO-TinyStories.Q6_K.gguf b/Qwen2.5-3B-DPO-TinyStories.Q6_K.gguf new file mode 100644 index 0000000..5b34c33 --- /dev/null +++ b/Qwen2.5-3B-DPO-TinyStories.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55d4e31d650d1525aea8604a6b9538db3811f76a4127b907dc8eb9830c0fc9a0 +size 2538156896 diff --git a/Qwen2.5-3B-DPO-TinyStories.Q8_0.gguf b/Qwen2.5-3B-DPO-TinyStories.Q8_0.gguf new file mode 100644 index 0000000..57e4ed9 --- /dev/null +++ b/Qwen2.5-3B-DPO-TinyStories.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2c9045b80be912d22220d9a9fae92fea0b402fb52478706fa5c7257fdb9c91f +size 3285474144 diff --git a/Qwen2.5-3B-DPO-TinyStories.f16.gguf b/Qwen2.5-3B-DPO-TinyStories.f16.gguf new file mode 100644 index 0000000..71adfc7 --- /dev/null +++ b/Qwen2.5-3B-DPO-TinyStories.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed282e489ecc7614b67c393fb388df45bb1750f0169a491c37b1d46e0e00fffd +size 6178315104 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ca1a8eb --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: tanquangduong/Qwen2.5-3B-DPO-TinyStories +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- dpo +--- +## About + + + + + + +static quants of https://huggingface.co/tanquangduong/Qwen2.5-3B-DPO-TinyStories + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2.5-3B-DPO-TinyStories-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/Qwen2.5-3B-DPO-TinyStories-GGUF/resolve/main/Qwen2.5-3B-DPO-TinyStories.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-DPO-TinyStories-GGUF/resolve/main/Qwen2.5-3B-DPO-TinyStories.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-DPO-TinyStories-GGUF/resolve/main/Qwen2.5-3B-DPO-TinyStories.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-DPO-TinyStories-GGUF/resolve/main/Qwen2.5-3B-DPO-TinyStories.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-DPO-TinyStories-GGUF/resolve/main/Qwen2.5-3B-DPO-TinyStories.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-DPO-TinyStories-GGUF/resolve/main/Qwen2.5-3B-DPO-TinyStories.Q4_0_4_4.gguf) | Q4_0_4_4 | 1.9 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-DPO-TinyStories-GGUF/resolve/main/Qwen2.5-3B-DPO-TinyStories.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-DPO-TinyStories-GGUF/resolve/main/Qwen2.5-3B-DPO-TinyStories.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-DPO-TinyStories-GGUF/resolve/main/Qwen2.5-3B-DPO-TinyStories.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-DPO-TinyStories-GGUF/resolve/main/Qwen2.5-3B-DPO-TinyStories.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-DPO-TinyStories-GGUF/resolve/main/Qwen2.5-3B-DPO-TinyStories.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-DPO-TinyStories-GGUF/resolve/main/Qwen2.5-3B-DPO-TinyStories.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-3B-DPO-TinyStories-GGUF/resolve/main/Qwen2.5-3B-DPO-TinyStories.f16.gguf) | f16 | 6.3 | 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. + +