commit 65916e16f9d0a26ab5be4c7d36e6e98c24fc38d8 Author: ModelHub XC Date: Fri Jul 10 05:36:09 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/DeepRetrieval-PubMed-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b9f43da --- /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 +DeepRetrieval-PubMed-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +DeepRetrieval-PubMed-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepRetrieval-PubMed-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +DeepRetrieval-PubMed-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepRetrieval-PubMed-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepRetrieval-PubMed-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepRetrieval-PubMed-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepRetrieval-PubMed-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +DeepRetrieval-PubMed-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +DeepRetrieval-PubMed-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +DeepRetrieval-PubMed-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +DeepRetrieval-PubMed-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/DeepRetrieval-PubMed-3B.IQ4_XS.gguf b/DeepRetrieval-PubMed-3B.IQ4_XS.gguf new file mode 100644 index 0000000..e97582b --- /dev/null +++ b/DeepRetrieval-PubMed-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1caf23e6fc10042d38fd83bbccce447afa0278b3fb97096a070d48546cd458b1 +size 1918491520 diff --git a/DeepRetrieval-PubMed-3B.Q2_K.gguf b/DeepRetrieval-PubMed-3B.Q2_K.gguf new file mode 100644 index 0000000..67d7e33 --- /dev/null +++ b/DeepRetrieval-PubMed-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc29444d4f64360c978665e107aa6107f9a78894ea4352eadcd81774630aadd7 +size 1376856960 diff --git a/DeepRetrieval-PubMed-3B.Q3_K_L.gguf b/DeepRetrieval-PubMed-3B.Q3_K_L.gguf new file mode 100644 index 0000000..887626b --- /dev/null +++ b/DeepRetrieval-PubMed-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a02f625bb851c80a4c31901bd90f0cd35342a3777c9e88b15a84c34630324cd6 +size 1841095552 diff --git a/DeepRetrieval-PubMed-3B.Q3_K_M.gguf b/DeepRetrieval-PubMed-3B.Q3_K_M.gguf new file mode 100644 index 0000000..bdf5f31 --- /dev/null +++ b/DeepRetrieval-PubMed-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac017c19f1dc0fd86d63fbe9ec0cb8e0eb0f49d0e13cd543dcd566941153f24c +size 1724179328 diff --git a/DeepRetrieval-PubMed-3B.Q3_K_S.gguf b/DeepRetrieval-PubMed-3B.Q3_K_S.gguf new file mode 100644 index 0000000..d837219 --- /dev/null +++ b/DeepRetrieval-PubMed-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e41b46786919ae8622964d5c197904014bbd18d4645afc3e7f89ab23014f9de9 +size 1588061056 diff --git a/DeepRetrieval-PubMed-3B.Q4_K_M.gguf b/DeepRetrieval-PubMed-3B.Q4_K_M.gguf new file mode 100644 index 0000000..8a3e90d --- /dev/null +++ b/DeepRetrieval-PubMed-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7915123d9d89aadc733c1bd34bfcc72d546ad5b0ca184a819305b6edab7fa24c +size 2104933248 diff --git a/DeepRetrieval-PubMed-3B.Q4_K_S.gguf b/DeepRetrieval-PubMed-3B.Q4_K_S.gguf new file mode 100644 index 0000000..e4191d9 --- /dev/null +++ b/DeepRetrieval-PubMed-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a85c444dc1b0d5b63157507980a5cf5b826f3f30d73ab1f5622d32a114405df9 +size 2009414528 diff --git a/DeepRetrieval-PubMed-3B.Q5_K_M.gguf b/DeepRetrieval-PubMed-3B.Q5_K_M.gguf new file mode 100644 index 0000000..f730b56 --- /dev/null +++ b/DeepRetrieval-PubMed-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2b4cd9fce96f368c23a7ec24cf7c980b3f0b454972c134cad63f0edabc9664f +size 2438740864 diff --git a/DeepRetrieval-PubMed-3B.Q5_K_S.gguf b/DeepRetrieval-PubMed-3B.Q5_K_S.gguf new file mode 100644 index 0000000..298e2cb --- /dev/null +++ b/DeepRetrieval-PubMed-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:866c72af67d3f0347154151bcd350e87c0d755c7c2e055490b876701a758ded3 +size 2383592320 diff --git a/DeepRetrieval-PubMed-3B.Q6_K.gguf b/DeepRetrieval-PubMed-3B.Q6_K.gguf new file mode 100644 index 0000000..6600f02 --- /dev/null +++ b/DeepRetrieval-PubMed-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb2baeb777026c1fb66651fe41cee64c276eef05a10e7639ae6799ff275c8252 +size 2793411456 diff --git a/DeepRetrieval-PubMed-3B.Q8_0.gguf b/DeepRetrieval-PubMed-3B.Q8_0.gguf new file mode 100644 index 0000000..f4b9be6 --- /dev/null +++ b/DeepRetrieval-PubMed-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c149c811ca4f0b2e79f798cd6619dcbf2eb7ed84be23ce182dd7a63f3c3a7657 +size 3616088960 diff --git a/DeepRetrieval-PubMed-3B.f16.gguf b/DeepRetrieval-PubMed-3B.f16.gguf new file mode 100644 index 0000000..586d1be --- /dev/null +++ b/DeepRetrieval-PubMed-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:774572fbff924056f8da55cdfa6baa818fde2629e5a489defd667712a7964f25 +size 6800647040 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b8ff75c --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: DeepRetrieval/DeepRetrieval-PubMed-3B +language: +- zho +- eng +- fra +- spa +- por +- deu +- ita +- rus +- jpn +- kor +- vie +- tha +- ara +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/DeepRetrieval/DeepRetrieval-PubMed-3B + + +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/DeepRetrieval-PubMed-3B-GGUF/resolve/main/DeepRetrieval-PubMed-3B.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepRetrieval-PubMed-3B-GGUF/resolve/main/DeepRetrieval-PubMed-3B.Q3_K_S.gguf) | Q3_K_S | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/DeepRetrieval-PubMed-3B-GGUF/resolve/main/DeepRetrieval-PubMed-3B.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/DeepRetrieval-PubMed-3B-GGUF/resolve/main/DeepRetrieval-PubMed-3B.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/DeepRetrieval-PubMed-3B-GGUF/resolve/main/DeepRetrieval-PubMed-3B.IQ4_XS.gguf) | IQ4_XS | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/DeepRetrieval-PubMed-3B-GGUF/resolve/main/DeepRetrieval-PubMed-3B.Q4_K_S.gguf) | Q4_K_S | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepRetrieval-PubMed-3B-GGUF/resolve/main/DeepRetrieval-PubMed-3B.Q4_K_M.gguf) | Q4_K_M | 2.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/DeepRetrieval-PubMed-3B-GGUF/resolve/main/DeepRetrieval-PubMed-3B.Q5_K_S.gguf) | Q5_K_S | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepRetrieval-PubMed-3B-GGUF/resolve/main/DeepRetrieval-PubMed-3B.Q5_K_M.gguf) | Q5_K_M | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/DeepRetrieval-PubMed-3B-GGUF/resolve/main/DeepRetrieval-PubMed-3B.Q6_K.gguf) | Q6_K | 2.9 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/DeepRetrieval-PubMed-3B-GGUF/resolve/main/DeepRetrieval-PubMed-3B.Q8_0.gguf) | Q8_0 | 3.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/DeepRetrieval-PubMed-3B-GGUF/resolve/main/DeepRetrieval-PubMed-3B.f16.gguf) | f16 | 6.9 | 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. + +