commit c0824d40db4c9eeba2edc70a866123fbddd005cd Author: ModelHub XC Date: Thu Aug 6 19:33:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-DPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8758d93 --- /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 +Llama-3.2-3B-DPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-DPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-DPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-DPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-DPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-DPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-DPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-DPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-DPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-DPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-DPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-DPO.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-DPO.IQ4_XS.gguf b/Llama-3.2-3B-DPO.IQ4_XS.gguf new file mode 100644 index 0000000..39cf1d3 --- /dev/null +++ b/Llama-3.2-3B-DPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:175b01414ad6b5d2ab13061bac5186d7fed910d83cf743242d2c2eb1cf01d6ff +size 2050218592 diff --git a/Llama-3.2-3B-DPO.Q2_K.gguf b/Llama-3.2-3B-DPO.Q2_K.gguf new file mode 100644 index 0000000..8baa1d9 --- /dev/null +++ b/Llama-3.2-3B-DPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e15204bbd413b914c6e362a321fab19475002ce469aa43552dd0f23c25e1b766 +size 1493215840 diff --git a/Llama-3.2-3B-DPO.Q3_K_L.gguf b/Llama-3.2-3B-DPO.Q3_K_L.gguf new file mode 100644 index 0000000..79725fc --- /dev/null +++ b/Llama-3.2-3B-DPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:157c226e4389cc4cd93fca3af555768694a52347d9214d73b1518d608c0fb0d2 +size 1984643680 diff --git a/Llama-3.2-3B-DPO.Q3_K_M.gguf b/Llama-3.2-3B-DPO.Q3_K_M.gguf new file mode 100644 index 0000000..94f66f4 --- /dev/null +++ b/Llama-3.2-3B-DPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ca8be0f03676baf26d1d96dbbf97835e37fe69d1c6350eeb896a7b51ac9af71 +size 1856455264 diff --git a/Llama-3.2-3B-DPO.Q3_K_S.gguf b/Llama-3.2-3B-DPO.Q3_K_S.gguf new file mode 100644 index 0000000..86d2ce1 --- /dev/null +++ b/Llama-3.2-3B-DPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1671e126b5c1b77441ac701a2fb4f65e6e6fdc5b4feced05b59b4df2d2b61f07 +size 1712144992 diff --git a/Llama-3.2-3B-DPO.Q4_K_M.gguf b/Llama-3.2-3B-DPO.Q4_K_M.gguf new file mode 100644 index 0000000..40e7b52 --- /dev/null +++ b/Llama-3.2-3B-DPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1aa1484bca4d77e98ed763c181096df5fbf40204e54638f68d36f0e002a997a +size 2241002080 diff --git a/Llama-3.2-3B-DPO.Q4_K_S.gguf b/Llama-3.2-3B-DPO.Q4_K_S.gguf new file mode 100644 index 0000000..a20f8cc --- /dev/null +++ b/Llama-3.2-3B-DPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f66704e1060247547ed77f5d4d30a83fe0af288fe497b4eaccb7888df8052b6 +size 2149825120 diff --git a/Llama-3.2-3B-DPO.Q5_K_M.gguf b/Llama-3.2-3B-DPO.Q5_K_M.gguf new file mode 100644 index 0000000..5980c2e --- /dev/null +++ b/Llama-3.2-3B-DPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:741b27ddda453c6eb7e40fd1ccc047b7571138a2af33caca1e0c07ae35d5fbed +size 2593028704 diff --git a/Llama-3.2-3B-DPO.Q5_K_S.gguf b/Llama-3.2-3B-DPO.Q5_K_S.gguf new file mode 100644 index 0000000..71100d8 --- /dev/null +++ b/Llama-3.2-3B-DPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc97b588746eaddd072e4a568e71026b8a0fd5ddf11d928101ca43762dd99b6d +size 2540386912 diff --git a/Llama-3.2-3B-DPO.Q6_K.gguf b/Llama-3.2-3B-DPO.Q6_K.gguf new file mode 100644 index 0000000..217418d --- /dev/null +++ b/Llama-3.2-3B-DPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:586a16e7766a9801402e9b0c18dd36f54e2e50883b7c026b06ee2032c87334df +size 2967056992 diff --git a/Llama-3.2-3B-DPO.Q8_0.gguf b/Llama-3.2-3B-DPO.Q8_0.gguf new file mode 100644 index 0000000..ea83051 --- /dev/null +++ b/Llama-3.2-3B-DPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d53fffb4bbf4cc5aed64b2483613125e0083418014e905b37484bcaea3cbc6c +size 3840524896 diff --git a/Llama-3.2-3B-DPO.f16.gguf b/Llama-3.2-3B-DPO.f16.gguf new file mode 100644 index 0000000..9f38fed --- /dev/null +++ b/Llama-3.2-3B-DPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcbd7612ca4139d06bba89888b72c9213185a471d61bd49b945d2080eec20530 +size 7221690976 diff --git a/README.md b/README.md new file mode 100644 index 0000000..1940643 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: AIR-hl/Llama-3.2-3B-DPO +datasets: +- HuggingFaceH4/ultrafeedback_binarized +language: +- en +library_name: transformers +license: llama3.2 +quantized_by: mradermacher +tags: +- trl +- llama +- dpo +- alignment +- transformers +- custome +- chat +--- +## About + + + + + + +static quants of https://huggingface.co/AIR-hl/Llama-3.2-3B-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/Llama-3.2-3B-DPO-GGUF/resolve/main/Llama-3.2-3B-DPO.Q2_K.gguf) | Q2_K | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-DPO-GGUF/resolve/main/Llama-3.2-3B-DPO.Q3_K_S.gguf) | Q3_K_S | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-DPO-GGUF/resolve/main/Llama-3.2-3B-DPO.Q3_K_M.gguf) | Q3_K_M | 2.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-DPO-GGUF/resolve/main/Llama-3.2-3B-DPO.Q3_K_L.gguf) | Q3_K_L | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-DPO-GGUF/resolve/main/Llama-3.2-3B-DPO.IQ4_XS.gguf) | IQ4_XS | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-DPO-GGUF/resolve/main/Llama-3.2-3B-DPO.Q4_K_S.gguf) | Q4_K_S | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-DPO-GGUF/resolve/main/Llama-3.2-3B-DPO.Q4_K_M.gguf) | Q4_K_M | 2.3 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-DPO-GGUF/resolve/main/Llama-3.2-3B-DPO.Q5_K_S.gguf) | Q5_K_S | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-DPO-GGUF/resolve/main/Llama-3.2-3B-DPO.Q5_K_M.gguf) | Q5_K_M | 2.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-DPO-GGUF/resolve/main/Llama-3.2-3B-DPO.Q6_K.gguf) | Q6_K | 3.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-DPO-GGUF/resolve/main/Llama-3.2-3B-DPO.Q8_0.gguf) | Q8_0 | 3.9 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-DPO-GGUF/resolve/main/Llama-3.2-3B-DPO.f16.gguf) | f16 | 7.3 | 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. + +