commit 02a78a1f47e7b4d42d3c78c37da83f6e0ab3245c Author: ModelHub XC Date: Mon Sep 21 08:38:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-pubMedQA-DPO-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e0244dd --- /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 +Llama-3.2-3B-pubMedQA-DPO.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-DPO.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-DPO.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-DPO.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-DPO.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-DPO.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-DPO.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-DPO.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-DPO.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-DPO.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-DPO.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-DPO.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-DPO.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-pubMedQA-DPO.IQ4_XS.gguf b/Llama-3.2-3B-pubMedQA-DPO.IQ4_XS.gguf new file mode 100644 index 0000000..f0e6728 --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-DPO.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0dabd292dbc187a65da963254cf05dd9a00edcf043cb9177dddadcf8c2cb8512 +size 1840906752 diff --git a/Llama-3.2-3B-pubMedQA-DPO.Q2_K.gguf b/Llama-3.2-3B-pubMedQA-DPO.Q2_K.gguf new file mode 100644 index 0000000..a54f82b --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-DPO.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c4b9c2cd618e6f222213828b785e9d2a6ac0b749c9b60f2ed05cf822d09c41a +size 1363935744 diff --git a/Llama-3.2-3B-pubMedQA-DPO.Q3_K_L.gguf b/Llama-3.2-3B-pubMedQA-DPO.Q3_K_L.gguf new file mode 100644 index 0000000..3333110 --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-DPO.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b66dadd71673faf270e8049898c3a6f28bbe326cecc70828d99d7b1a709681f9 +size 1815347712 diff --git a/Llama-3.2-3B-pubMedQA-DPO.Q3_K_M.gguf b/Llama-3.2-3B-pubMedQA-DPO.Q3_K_M.gguf new file mode 100644 index 0000000..8fcf23f --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-DPO.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dae8a21d409539979c8d24505481a936eb53affd25f5449f2f52729a9d0eca5 +size 1687159296 diff --git a/Llama-3.2-3B-pubMedQA-DPO.Q3_K_S.gguf b/Llama-3.2-3B-pubMedQA-DPO.Q3_K_S.gguf new file mode 100644 index 0000000..9e80b0d --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-DPO.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48208402ccfc67b1c233ff85a9de580b556c1ac27135d9d773f9e46d29d4b2c5 +size 1542849024 diff --git a/Llama-3.2-3B-pubMedQA-DPO.Q4_0_4_4.gguf b/Llama-3.2-3B-pubMedQA-DPO.Q4_0_4_4.gguf new file mode 100644 index 0000000..831e75a --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-DPO.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3a78635800294c09069d92fb50bdad300ac46e84aefe17d5870913417f3803a +size 1917190656 diff --git a/Llama-3.2-3B-pubMedQA-DPO.Q4_K_M.gguf b/Llama-3.2-3B-pubMedQA-DPO.Q4_K_M.gguf new file mode 100644 index 0000000..260f60e --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-DPO.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:485c25d2395fecf7e6a52de79eeb3eee723f9981ecffe2bc5999f39f117da7c4 +size 2019377664 diff --git a/Llama-3.2-3B-pubMedQA-DPO.Q4_K_S.gguf b/Llama-3.2-3B-pubMedQA-DPO.Q4_K_S.gguf new file mode 100644 index 0000000..54361f5 --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-DPO.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a56babc869964e41f013fd9899ae06af7c5e5bebbae7f2470056f7eb200ab1e4 +size 1928200704 diff --git a/Llama-3.2-3B-pubMedQA-DPO.Q5_K_M.gguf b/Llama-3.2-3B-pubMedQA-DPO.Q5_K_M.gguf new file mode 100644 index 0000000..b369297 --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-DPO.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:655a0a03151a31b5bfac1ab8e777b9a1072d4cc1e489f708f6c9b263f3c436d1 +size 2322153984 diff --git a/Llama-3.2-3B-pubMedQA-DPO.Q5_K_S.gguf b/Llama-3.2-3B-pubMedQA-DPO.Q5_K_S.gguf new file mode 100644 index 0000000..9aaba52 --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-DPO.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a46e43a113881de6dbd25dc4f34e332953935c8f4756ba83d3e39df638cdfa6 +size 2269512192 diff --git a/Llama-3.2-3B-pubMedQA-DPO.Q6_K.gguf b/Llama-3.2-3B-pubMedQA-DPO.Q6_K.gguf new file mode 100644 index 0000000..d2a85e2 --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-DPO.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96a4e010dfa4b97622ce88396d2abd48f7a612117ed76bd3fd69a83a8c377322 +size 2643853824 diff --git a/Llama-3.2-3B-pubMedQA-DPO.Q8_0.gguf b/Llama-3.2-3B-pubMedQA-DPO.Q8_0.gguf new file mode 100644 index 0000000..e36a152 --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-DPO.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7380ddc948f019057637f604879b05f9a4f9c66b303a84127c34f0d81c57728 +size 3421899264 diff --git a/Llama-3.2-3B-pubMedQA-DPO.f16.gguf b/Llama-3.2-3B-pubMedQA-DPO.f16.gguf new file mode 100644 index 0000000..a1fccec --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-DPO.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dc27fe35b75f3c596fe7c9b68ce1c0040748a4aa4ee441909bda0e0b991a861 +size 6433688064 diff --git a/README.md b/README.md new file mode 100644 index 0000000..aeaa8c2 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: harrysyz/Llama-3.2-3B-pubMedQA-DPO +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/harrysyz/Llama-3.2-3B-pubMedQA-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-pubMedQA-DPO-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-DPO.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-DPO-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-DPO.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-DPO-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-DPO.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-DPO-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-DPO.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-DPO-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-DPO.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-DPO-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-DPO.Q4_0_4_4.gguf) | Q4_0_4_4 | 2.0 | fast on arm, low quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-DPO-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-DPO.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-DPO-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-DPO.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-DPO-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-DPO.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-DPO-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-DPO.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-DPO-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-DPO.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-DPO-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-DPO.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-DPO-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-DPO.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. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + +