commit db611d2b7b180a98a455b5694ef86d80282c0a69 Author: ModelHub XC Date: Thu Oct 22 14:32:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MDCure-Qwen2-1.5B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9e1cf7b --- /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 +MDCure-Qwen2-1.5B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +MDCure-Qwen2-1.5B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MDCure-Qwen2-1.5B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MDCure-Qwen2-1.5B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MDCure-Qwen2-1.5B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MDCure-Qwen2-1.5B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MDCure-Qwen2-1.5B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MDCure-Qwen2-1.5B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MDCure-Qwen2-1.5B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MDCure-Qwen2-1.5B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MDCure-Qwen2-1.5B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MDCure-Qwen2-1.5B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MDCure-Qwen2-1.5B-Instruct.IQ4_XS.gguf b/MDCure-Qwen2-1.5B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..783541a --- /dev/null +++ b/MDCure-Qwen2-1.5B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e44eea84531b37b02b458141726a2ec680e241a6b1e28d5eb55f61f1655b3165 +size 902181408 diff --git a/MDCure-Qwen2-1.5B-Instruct.Q2_K.gguf b/MDCure-Qwen2-1.5B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..b7e678b --- /dev/null +++ b/MDCure-Qwen2-1.5B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1db6954ef9c9022ff70ba7278aaa6e62b5fe26b074c3b7cc8ef99d5c4a50272 +size 676303392 diff --git a/MDCure-Qwen2-1.5B-Instruct.Q3_K_L.gguf b/MDCure-Qwen2-1.5B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..f2074b2 --- /dev/null +++ b/MDCure-Qwen2-1.5B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c091f85cc16b9411d1aa38d0b2097871637794c9e417ab29136e874bf93655da +size 880161312 diff --git a/MDCure-Qwen2-1.5B-Instruct.Q3_K_M.gguf b/MDCure-Qwen2-1.5B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..b871b38 --- /dev/null +++ b/MDCure-Qwen2-1.5B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51041ba6789cb0be33dbea0dc17c8fc439986e845a042e3e779e9ce307d616c7 +size 824177184 diff --git a/MDCure-Qwen2-1.5B-Instruct.Q3_K_S.gguf b/MDCure-Qwen2-1.5B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..2785ac7 --- /dev/null +++ b/MDCure-Qwen2-1.5B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2acef1653dc4c8684f5db31603cb041c03f54cd521811dc478f094e113eac8a7 +size 760943136 diff --git a/MDCure-Qwen2-1.5B-Instruct.Q4_K_M.gguf b/MDCure-Qwen2-1.5B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..0564fe2 --- /dev/null +++ b/MDCure-Qwen2-1.5B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a79e11cd92be0b6c16a023c295dc461ac9cce2da0a39cd36845a0a5f6df34fa +size 986047008 diff --git a/MDCure-Qwen2-1.5B-Instruct.Q4_K_S.gguf b/MDCure-Qwen2-1.5B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..820d768 --- /dev/null +++ b/MDCure-Qwen2-1.5B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:836048791697263e9bf0e7328caf16a3419ef135f84d2fa8419c4f0e5a25e364 +size 940311072 diff --git a/MDCure-Qwen2-1.5B-Instruct.Q5_K_M.gguf b/MDCure-Qwen2-1.5B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..70eefc1 --- /dev/null +++ b/MDCure-Qwen2-1.5B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2744884288ae9b278ebfa3ff56195448013003240f651a95892552233d5bdb83 +size 1125048864 diff --git a/MDCure-Qwen2-1.5B-Instruct.Q5_K_S.gguf b/MDCure-Qwen2-1.5B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..0bcbcb8 --- /dev/null +++ b/MDCure-Qwen2-1.5B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0210266d5ef0e64b8b3b9808f6a87133e5ddee83d4c5a33777b466d9da16941d +size 1098727968 diff --git a/MDCure-Qwen2-1.5B-Instruct.Q6_K.gguf b/MDCure-Qwen2-1.5B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..0fa622f --- /dev/null +++ b/MDCure-Qwen2-1.5B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baf1d46254e1c859b0f459f846a0c8c953fb3b675b143329b4e2e929fa9bd680 +size 1272738336 diff --git a/MDCure-Qwen2-1.5B-Instruct.Q8_0.gguf b/MDCure-Qwen2-1.5B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..b2d4394 --- /dev/null +++ b/MDCure-Qwen2-1.5B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:391b08026ee8158bddbb28a799d5855039d5cb7536717ef5b0dbbaaa4f7bb78b +size 1646571552 diff --git a/MDCure-Qwen2-1.5B-Instruct.f16.gguf b/MDCure-Qwen2-1.5B-Instruct.f16.gguf new file mode 100644 index 0000000..01c8a73 --- /dev/null +++ b/MDCure-Qwen2-1.5B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6cdb017d19338ce9539f75e7ab229964f5870cf8712ab46d79fbaa93288eba5 +size 3093667872 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c18013b --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: yale-nlp/MDCure-Qwen2-1.5B-Instruct +datasets: +- yale-nlp/MDCure-72k +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- multi-document +- long-context +- Long Context +--- +## About + + + + + + +static quants of https://huggingface.co/yale-nlp/MDCure-Qwen2-1.5B-Instruct + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#MDCure-Qwen2-1.5B-Instruct-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/MDCure-Qwen2-1.5B-Instruct-GGUF/resolve/main/MDCure-Qwen2-1.5B-Instruct.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/MDCure-Qwen2-1.5B-Instruct-GGUF/resolve/main/MDCure-Qwen2-1.5B-Instruct.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/MDCure-Qwen2-1.5B-Instruct-GGUF/resolve/main/MDCure-Qwen2-1.5B-Instruct.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MDCure-Qwen2-1.5B-Instruct-GGUF/resolve/main/MDCure-Qwen2-1.5B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/MDCure-Qwen2-1.5B-Instruct-GGUF/resolve/main/MDCure-Qwen2-1.5B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/MDCure-Qwen2-1.5B-Instruct-GGUF/resolve/main/MDCure-Qwen2-1.5B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MDCure-Qwen2-1.5B-Instruct-GGUF/resolve/main/MDCure-Qwen2-1.5B-Instruct.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MDCure-Qwen2-1.5B-Instruct-GGUF/resolve/main/MDCure-Qwen2-1.5B-Instruct.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/MDCure-Qwen2-1.5B-Instruct-GGUF/resolve/main/MDCure-Qwen2-1.5B-Instruct.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/MDCure-Qwen2-1.5B-Instruct-GGUF/resolve/main/MDCure-Qwen2-1.5B-Instruct.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MDCure-Qwen2-1.5B-Instruct-GGUF/resolve/main/MDCure-Qwen2-1.5B-Instruct.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MDCure-Qwen2-1.5B-Instruct-GGUF/resolve/main/MDCure-Qwen2-1.5B-Instruct.f16.gguf) | f16 | 3.2 | 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. + +