commit d8fa27f2507ba655593ffd7127d2fdb8cd3095ce Author: ModelHub XC Date: Sun Jul 5 12:57:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/PubMedLLaMa-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3bdd2e5 --- /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 +PubMedLLaMa.f16.gguf filter=lfs diff=lfs merge=lfs -text +PubMedLLaMa.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PubMedLLaMa.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +PubMedLLaMa.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +PubMedLLaMa.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +PubMedLLaMa.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PubMedLLaMa.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PubMedLLaMa.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +PubMedLLaMa.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PubMedLLaMa.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +PubMedLLaMa.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +PubMedLLaMa.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/PubMedLLaMa.IQ4_XS.gguf b/PubMedLLaMa.IQ4_XS.gguf new file mode 100644 index 0000000..46a4411 --- /dev/null +++ b/PubMedLLaMa.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db9d815e099db91d6457edc05f23e1ef564f4dcaa9a25198b9b5117ebb3335bd +size 3647517888 diff --git a/PubMedLLaMa.Q2_K.gguf b/PubMedLLaMa.Q2_K.gguf new file mode 100644 index 0000000..bf9a341 --- /dev/null +++ b/PubMedLLaMa.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d34a6ed77293b9f25845f79ac46865601ce644b61380c190570d73fbb61173f6 +size 2532865216 diff --git a/PubMedLLaMa.Q3_K_L.gguf b/PubMedLLaMa.Q3_K_L.gguf new file mode 100644 index 0000000..97207b2 --- /dev/null +++ b/PubMedLLaMa.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ca8dd1ed5da963615660114dac230899076e14603c9d8875f9dbc0e4d68a374 +size 3597112512 diff --git a/PubMedLLaMa.Q3_K_M.gguf b/PubMedLLaMa.Q3_K_M.gguf new file mode 100644 index 0000000..fdb7c54 --- /dev/null +++ b/PubMedLLaMa.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:688463495e377a29498783146b18bb17fbeb21b59ffb7f23a796584202532192 +size 3298006208 diff --git a/PubMedLLaMa.Q3_K_S.gguf b/PubMedLLaMa.Q3_K_S.gguf new file mode 100644 index 0000000..772b3ee --- /dev/null +++ b/PubMedLLaMa.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba583aa69e1f13482115e409efd68c0aca825ada33a000922ef9013209e3f137 +size 2948306112 diff --git a/PubMedLLaMa.Q4_K_M.gguf b/PubMedLLaMa.Q4_K_M.gguf new file mode 100644 index 0000000..21e5715 --- /dev/null +++ b/PubMedLLaMa.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1b5bad7f2627b7d63af7797b24beef400b26ca46fba5b699e9fdb5ed2856952 +size 4081005760 diff --git a/PubMedLLaMa.Q4_K_S.gguf b/PubMedLLaMa.Q4_K_S.gguf new file mode 100644 index 0000000..8519936 --- /dev/null +++ b/PubMedLLaMa.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1361de74962942ad3bd80de6d872415ee04afaa3bfdbb5c5caf5d7716688b4ae +size 3856741568 diff --git a/PubMedLLaMa.Q5_K_M.gguf b/PubMedLLaMa.Q5_K_M.gguf new file mode 100644 index 0000000..e562b70 --- /dev/null +++ b/PubMedLLaMa.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d73f4d0967cf9c5857d7ba63a51594eef69880ab4e825d14f21a75258b0a05a +size 4783158464 diff --git a/PubMedLLaMa.Q5_K_S.gguf b/PubMedLLaMa.Q5_K_S.gguf new file mode 100644 index 0000000..16f15f2 --- /dev/null +++ b/PubMedLLaMa.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b3b3f430f331be93c04d2df27772d3bfe061853c998f5bf54597c261350744d +size 4651693248 diff --git a/PubMedLLaMa.Q6_K.gguf b/PubMedLLaMa.Q6_K.gguf new file mode 100644 index 0000000..6afb37a --- /dev/null +++ b/PubMedLLaMa.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6066090fd098d520e357bf3fe549d267dd5d0d9274ac8285f8bb202be64c0d68 +size 5529195712 diff --git a/PubMedLLaMa.Q8_0.gguf b/PubMedLLaMa.Q8_0.gguf new file mode 100644 index 0000000..f789bed --- /dev/null +++ b/PubMedLLaMa.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55a116c0448fc87f551f11c9a4624bafccb5845e925c3d9cf6d5aacf9a97b54b +size 7161091264 diff --git a/PubMedLLaMa.f16.gguf b/PubMedLLaMa.f16.gguf new file mode 100644 index 0000000..f2e6a3f --- /dev/null +++ b/PubMedLLaMa.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e38b5b878d5d6db29c144da5172dc2b59f24089ec65eed930092b4579615239 +size 13478106304 diff --git a/README.md b/README.md new file mode 100644 index 0000000..7fe57e2 --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: NMantegazza/PubMedLLaMa +datasets: +- qiaojin/PubMedQA +language: +- en +library_name: transformers +license: llama2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +--- +## About + + + + + + + + + +static quants of https://huggingface.co/NMantegazza/PubMedLLaMa + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#PubMedLLaMa-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/PubMedLLaMa-GGUF/resolve/main/PubMedLLaMa.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/PubMedLLaMa-GGUF/resolve/main/PubMedLLaMa.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/PubMedLLaMa-GGUF/resolve/main/PubMedLLaMa.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/PubMedLLaMa-GGUF/resolve/main/PubMedLLaMa.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/PubMedLLaMa-GGUF/resolve/main/PubMedLLaMa.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/PubMedLLaMa-GGUF/resolve/main/PubMedLLaMa.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PubMedLLaMa-GGUF/resolve/main/PubMedLLaMa.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/PubMedLLaMa-GGUF/resolve/main/PubMedLLaMa.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/PubMedLLaMa-GGUF/resolve/main/PubMedLLaMa.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/PubMedLLaMa-GGUF/resolve/main/PubMedLLaMa.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/PubMedLLaMa-GGUF/resolve/main/PubMedLLaMa.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/PubMedLLaMa-GGUF/resolve/main/PubMedLLaMa.f16.gguf) | f16 | 13.6 | 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. + +