commit d9a4be2d3eac7f7bdd207e43f271a0922a24b020 Author: ModelHub XC Date: Sun Sep 20 12:46:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3B-pubMedQA-longAnswer-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8d2bc41 --- /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-longAnswer.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-longAnswer.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-longAnswer.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-longAnswer.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-longAnswer.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-longAnswer.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-longAnswer.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-longAnswer.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-longAnswer.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-longAnswer.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-longAnswer.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-longAnswer.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3B-pubMedQA-longAnswer.Q4_0_4_4.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-pubMedQA-longAnswer.IQ4_XS.gguf b/Llama-3.2-3B-pubMedQA-longAnswer.IQ4_XS.gguf new file mode 100644 index 0000000..282edbf --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-longAnswer.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7581e49a8b518a9fca9c55d901651e069a6628c270a964cca4b2cb798c47db4e +size 1840906784 diff --git a/Llama-3.2-3B-pubMedQA-longAnswer.Q2_K.gguf b/Llama-3.2-3B-pubMedQA-longAnswer.Q2_K.gguf new file mode 100644 index 0000000..407272c --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-longAnswer.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a97ce2394011468700cf50ede27edc399b7ce777723be70c7c21217fbdc9a068 +size 1363935776 diff --git a/Llama-3.2-3B-pubMedQA-longAnswer.Q3_K_L.gguf b/Llama-3.2-3B-pubMedQA-longAnswer.Q3_K_L.gguf new file mode 100644 index 0000000..f8169c1 --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-longAnswer.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06e2172561fb9d2e8fb84367142da1a665b67b565f988e007635fc223b02d590 +size 1815347744 diff --git a/Llama-3.2-3B-pubMedQA-longAnswer.Q3_K_M.gguf b/Llama-3.2-3B-pubMedQA-longAnswer.Q3_K_M.gguf new file mode 100644 index 0000000..e188743 --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-longAnswer.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c95f75fe41bd6de0bde027235ef0f767496a8b48b5adc35a1497b3bf24d97945 +size 1687159328 diff --git a/Llama-3.2-3B-pubMedQA-longAnswer.Q3_K_S.gguf b/Llama-3.2-3B-pubMedQA-longAnswer.Q3_K_S.gguf new file mode 100644 index 0000000..c05d5e5 --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-longAnswer.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb68c994db4ba1046b391297b3303c42798168c31f99dfaf694854f7174c80c4 +size 1542849056 diff --git a/Llama-3.2-3B-pubMedQA-longAnswer.Q4_0_4_4.gguf b/Llama-3.2-3B-pubMedQA-longAnswer.Q4_0_4_4.gguf new file mode 100644 index 0000000..9ff4c13 --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-longAnswer.Q4_0_4_4.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49547e173673085dc4725bb68f70744a98f1da946e62c293f95080b2914cf413 +size 1917190688 diff --git a/Llama-3.2-3B-pubMedQA-longAnswer.Q4_K_M.gguf b/Llama-3.2-3B-pubMedQA-longAnswer.Q4_K_M.gguf new file mode 100644 index 0000000..248110a --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-longAnswer.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb4ef067d45f357213557084556bf3b5523413db742cfa1990493b0fb63749c5 +size 2019377696 diff --git a/Llama-3.2-3B-pubMedQA-longAnswer.Q4_K_S.gguf b/Llama-3.2-3B-pubMedQA-longAnswer.Q4_K_S.gguf new file mode 100644 index 0000000..f1784b1 --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-longAnswer.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f23fca3d496059918c870ec86a1ac5e8d15b731c24d08cbde3c4f8b0e0783f56 +size 1928200736 diff --git a/Llama-3.2-3B-pubMedQA-longAnswer.Q5_K_M.gguf b/Llama-3.2-3B-pubMedQA-longAnswer.Q5_K_M.gguf new file mode 100644 index 0000000..cf77f2e --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-longAnswer.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8944c8c3258f5cba42b48054e9d49ee0e7c6e0c51edfae572a68de5d7048f6e4 +size 2322154016 diff --git a/Llama-3.2-3B-pubMedQA-longAnswer.Q5_K_S.gguf b/Llama-3.2-3B-pubMedQA-longAnswer.Q5_K_S.gguf new file mode 100644 index 0000000..d06b54b --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-longAnswer.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d7372b7408cf2c3672e6d5cbed880cb626c8c749f1a8ea7c6fe30ffddf2c14e +size 2269512224 diff --git a/Llama-3.2-3B-pubMedQA-longAnswer.Q6_K.gguf b/Llama-3.2-3B-pubMedQA-longAnswer.Q6_K.gguf new file mode 100644 index 0000000..e161e41 --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-longAnswer.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08b0bd9a0b9555dc3160bbfc0e862801644d60c34908850708ce364e7ab4a094 +size 2643853856 diff --git a/Llama-3.2-3B-pubMedQA-longAnswer.Q8_0.gguf b/Llama-3.2-3B-pubMedQA-longAnswer.Q8_0.gguf new file mode 100644 index 0000000..f2f907c --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-longAnswer.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cf0c092415b7a1da72a9f76f00b6ad6e27dbe7514769741b277921592d7ed5c +size 3421899296 diff --git a/Llama-3.2-3B-pubMedQA-longAnswer.f16.gguf b/Llama-3.2-3B-pubMedQA-longAnswer.f16.gguf new file mode 100644 index 0000000..b5d6d20 --- /dev/null +++ b/Llama-3.2-3B-pubMedQA-longAnswer.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27214015b8751d0c6d233692a477b7f98d9357f96f3c35e15e3e1c1367366ba0 +size 6433688096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..d2bc623 --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: harrysyz/Llama-3.2-3B-pubMedQA-longAnswer +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/harrysyz/Llama-3.2-3B-pubMedQA-longAnswer + + +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-longAnswer-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-longAnswer.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-longAnswer-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-longAnswer.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-longAnswer-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-longAnswer.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-longAnswer-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-longAnswer.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-longAnswer-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-longAnswer.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-longAnswer-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-longAnswer.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-longAnswer-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-longAnswer.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-longAnswer-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-longAnswer.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-longAnswer-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-longAnswer.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-longAnswer-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-longAnswer.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-longAnswer-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-longAnswer.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-longAnswer-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-longAnswer.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3B-pubMedQA-longAnswer-GGUF/resolve/main/Llama-3.2-3B-pubMedQA-longAnswer.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. + +