commit 34ef04bca451ddcb2a17ca7234b9d65648e69183 Author: ModelHub XC Date: Wed Jun 3 11:07:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama3.2-3b-dpo-vanilla-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..c2fb599 --- /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 +llama3.2-3b-dpo-vanilla.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-dpo-vanilla.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-dpo-vanilla.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-dpo-vanilla.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-dpo-vanilla.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-dpo-vanilla.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-dpo-vanilla.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-dpo-vanilla.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-dpo-vanilla.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-dpo-vanilla.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-dpo-vanilla.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama3.2-3b-dpo-vanilla.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..f818222 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: obiwit/llama3.2-3b-dpo-vanilla +language: +- en +library_name: transformers +model_name: llama3.2-3b-dpo-vanilla +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- trl +- dpo +--- +## About + + + + + + + + + +static quants of https://huggingface.co/obiwit/llama3.2-3b-dpo-vanilla + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama3.2-3b-dpo-vanilla-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/llama3.2-3b-dpo-vanilla-GGUF/resolve/main/llama3.2-3b-dpo-vanilla.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-dpo-vanilla-GGUF/resolve/main/llama3.2-3b-dpo-vanilla.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-dpo-vanilla-GGUF/resolve/main/llama3.2-3b-dpo-vanilla.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-dpo-vanilla-GGUF/resolve/main/llama3.2-3b-dpo-vanilla.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-dpo-vanilla-GGUF/resolve/main/llama3.2-3b-dpo-vanilla.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-dpo-vanilla-GGUF/resolve/main/llama3.2-3b-dpo-vanilla.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-dpo-vanilla-GGUF/resolve/main/llama3.2-3b-dpo-vanilla.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-dpo-vanilla-GGUF/resolve/main/llama3.2-3b-dpo-vanilla.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-dpo-vanilla-GGUF/resolve/main/llama3.2-3b-dpo-vanilla.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-dpo-vanilla-GGUF/resolve/main/llama3.2-3b-dpo-vanilla.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-dpo-vanilla-GGUF/resolve/main/llama3.2-3b-dpo-vanilla.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama3.2-3b-dpo-vanilla-GGUF/resolve/main/llama3.2-3b-dpo-vanilla.f16.gguf) | f16 | 6.5 | 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. + + diff --git a/llama3.2-3b-dpo-vanilla.IQ4_XS.gguf b/llama3.2-3b-dpo-vanilla.IQ4_XS.gguf new file mode 100644 index 0000000..3b8b3bc --- /dev/null +++ b/llama3.2-3b-dpo-vanilla.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caf9d553d65d8b25c4c868052d746fbbe2b4c6decd7a38a064e58a0d42457c9b +size 1840907200 diff --git a/llama3.2-3b-dpo-vanilla.Q2_K.gguf b/llama3.2-3b-dpo-vanilla.Q2_K.gguf new file mode 100644 index 0000000..7959da2 --- /dev/null +++ b/llama3.2-3b-dpo-vanilla.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4dab35ffb0122793918f022254199230b35bd16ee66861b4b0f0aa791e90de1 +size 1363936192 diff --git a/llama3.2-3b-dpo-vanilla.Q3_K_L.gguf b/llama3.2-3b-dpo-vanilla.Q3_K_L.gguf new file mode 100644 index 0000000..59da296 --- /dev/null +++ b/llama3.2-3b-dpo-vanilla.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bff430b5ed63e79740e107ac723f44fa5f18877c1a6594a20ce98b3078164a7 +size 1815348160 diff --git a/llama3.2-3b-dpo-vanilla.Q3_K_M.gguf b/llama3.2-3b-dpo-vanilla.Q3_K_M.gguf new file mode 100644 index 0000000..2471a3b --- /dev/null +++ b/llama3.2-3b-dpo-vanilla.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39ec774398d60a71af4ee26e19ad06a78e16e80d92ef61f5c7ed8a52e236321d +size 1687159744 diff --git a/llama3.2-3b-dpo-vanilla.Q3_K_S.gguf b/llama3.2-3b-dpo-vanilla.Q3_K_S.gguf new file mode 100644 index 0000000..034779d --- /dev/null +++ b/llama3.2-3b-dpo-vanilla.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cc0eee7d8f6a5b7b43a1b5b4287f7357a66e9e0697fd592021fbc3c31701ed3 +size 1542849472 diff --git a/llama3.2-3b-dpo-vanilla.Q4_K_M.gguf b/llama3.2-3b-dpo-vanilla.Q4_K_M.gguf new file mode 100644 index 0000000..f67b6f8 --- /dev/null +++ b/llama3.2-3b-dpo-vanilla.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cd4d4642a6d4aecdd094109fc21610253f49ed99386cad7a1f0ce64182bc758 +size 2019378112 diff --git a/llama3.2-3b-dpo-vanilla.Q4_K_S.gguf b/llama3.2-3b-dpo-vanilla.Q4_K_S.gguf new file mode 100644 index 0000000..6ad8123 --- /dev/null +++ b/llama3.2-3b-dpo-vanilla.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:783c3faf1133d66e1575d44af66e323538807f1a95057b1566470eaa7192e16e +size 1928201152 diff --git a/llama3.2-3b-dpo-vanilla.Q5_K_M.gguf b/llama3.2-3b-dpo-vanilla.Q5_K_M.gguf new file mode 100644 index 0000000..444f469 --- /dev/null +++ b/llama3.2-3b-dpo-vanilla.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dc5e366dfc73117e8d8480ccae0cd7753007675ac7b8dba21642fae9383869e +size 2322154432 diff --git a/llama3.2-3b-dpo-vanilla.Q5_K_S.gguf b/llama3.2-3b-dpo-vanilla.Q5_K_S.gguf new file mode 100644 index 0000000..647bc1a --- /dev/null +++ b/llama3.2-3b-dpo-vanilla.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0723c0f6caddb07662837033d52d202df68d3af8cd82f876b9de3ffbb8691bd +size 2269512640 diff --git a/llama3.2-3b-dpo-vanilla.Q6_K.gguf b/llama3.2-3b-dpo-vanilla.Q6_K.gguf new file mode 100644 index 0000000..351de69 --- /dev/null +++ b/llama3.2-3b-dpo-vanilla.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9d53b874130d8b3d001561dacd5c8691c07c6bfc07fe1ea7534f7e902262197 +size 2643854272 diff --git a/llama3.2-3b-dpo-vanilla.Q8_0.gguf b/llama3.2-3b-dpo-vanilla.Q8_0.gguf new file mode 100644 index 0000000..d8c12f9 --- /dev/null +++ b/llama3.2-3b-dpo-vanilla.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1e07762335392b4f871084a31baa4fe1602cc3f8da8667692bd9b56bd92272c +size 3421899712 diff --git a/llama3.2-3b-dpo-vanilla.f16.gguf b/llama3.2-3b-dpo-vanilla.f16.gguf new file mode 100644 index 0000000..9fdd5aa --- /dev/null +++ b/llama3.2-3b-dpo-vanilla.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:045390d5b5014880449062ec5d552c11ce8db29dd2777c8e64b91e76ce56c4e9 +size 6433688512