commit ddf0752671081dae36709fc8210acaa1e5f2e1ce Author: ModelHub XC Date: Sat May 16 17:24:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Med-Llama-3.2-1B-DeepSeek67B-Distilled-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e601d1b --- /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 +Med-Llama-3.2-1B-DeepSeek67B-Distilled.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Med-Llama-3.2-1B-DeepSeek67B-Distilled.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Med-Llama-3.2-1B-DeepSeek67B-Distilled.IQ4_XS.gguf b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.IQ4_XS.gguf new file mode 100644 index 0000000..b99af70 --- /dev/null +++ b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cd1c7905454d3ce13d1dc706d6f5da04797f68ae60ac5e9a6bbbf4d6aa5b5b6 +size 748380864 diff --git a/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q2_K.gguf b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q2_K.gguf new file mode 100644 index 0000000..5c3c748 --- /dev/null +++ b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e2e0734912723e302a189d77c713b36455249a52ef2de6a0e935817758c6e2b +size 580870848 diff --git a/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q3_K_L.gguf b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q3_K_L.gguf new file mode 100644 index 0000000..e16eae9 --- /dev/null +++ b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23ebefd148f7f026657ac59bd608946567cb186f3e7ad989dcac641ec627f9e7 +size 732521152 diff --git a/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q3_K_M.gguf b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q3_K_M.gguf new file mode 100644 index 0000000..998636b --- /dev/null +++ b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc71b03556246a7d160bc6c69ae20e9eacd8e85ce8a2abb6565bf8cbc3ecea49 +size 690840256 diff --git a/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q3_K_S.gguf b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q3_K_S.gguf new file mode 100644 index 0000000..b31a7de --- /dev/null +++ b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ae6a3606ba016275034ab798f6bc53ab8cd3e6b29ba371dfff6339d0600ed81 +size 641688256 diff --git a/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q4_K_M.gguf b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q4_K_M.gguf new file mode 100644 index 0000000..738d858 --- /dev/null +++ b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69980f5a390be5aa0c656d2cf319340d9709a89333375a05a611fa2ce482f4bb +size 807690944 diff --git a/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q4_K_S.gguf b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q4_K_S.gguf new file mode 100644 index 0000000..64e2007 --- /dev/null +++ b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e5fb03a8064347e3e2cc45fdac401683ada8d3046dba00c6f83de19b177786c +size 775643840 diff --git a/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q5_K_M.gguf b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q5_K_M.gguf new file mode 100644 index 0000000..1d430a6 --- /dev/null +++ b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d4ccd89f981725a390bc36fe9690fad28d7c6d5109cbb4b35517f0e1f466cde +size 911499968 diff --git a/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q5_K_S.gguf b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q5_K_S.gguf new file mode 100644 index 0000000..b0e103f --- /dev/null +++ b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53f62075ca893b073812b7299eb472a3ba9f0483558947bb7aa69286d8766341 +size 892560064 diff --git a/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q6_K.gguf b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q6_K.gguf new file mode 100644 index 0000000..cc09e9c --- /dev/null +++ b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f662b8f3e9feb0badfe61defb8450875245147ecc454907d889855bb78036813 +size 1021797056 diff --git a/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q8_0.gguf b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q8_0.gguf new file mode 100644 index 0000000..273f844 --- /dev/null +++ b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca3835c65a41dc90146f5ac1a707a9589370a1e6ab05417c09ef46a6717adbfc +size 1321079488 diff --git a/Med-Llama-3.2-1B-DeepSeek67B-Distilled.f16.gguf b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.f16.gguf new file mode 100644 index 0000000..fbe8919 --- /dev/null +++ b/Med-Llama-3.2-1B-DeepSeek67B-Distilled.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bcd3155ad0851d288d7ce76b04de24b954b69a7c602fec74256ebede9e4d70d +size 2479592128 diff --git a/README.md b/README.md new file mode 100644 index 0000000..79685aa --- /dev/null +++ b/README.md @@ -0,0 +1,66 @@ +--- +base_model: enesarda22/Med-Llama-3.2-1B-DeepSeek67B-Distilled +datasets: +- bigbio/med_qa +- qiaojin/PubMedQA +language: +- en +library_name: transformers +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/enesarda22/Med-Llama-3.2-1B-DeepSeek67B-Distilled + + +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/Med-Llama-3.2-1B-DeepSeek67B-Distilled-GGUF/resolve/main/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.2-1B-DeepSeek67B-Distilled-GGUF/resolve/main/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.2-1B-DeepSeek67B-Distilled-GGUF/resolve/main/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.2-1B-DeepSeek67B-Distilled-GGUF/resolve/main/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.2-1B-DeepSeek67B-Distilled-GGUF/resolve/main/Med-Llama-3.2-1B-DeepSeek67B-Distilled.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.2-1B-DeepSeek67B-Distilled-GGUF/resolve/main/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.2-1B-DeepSeek67B-Distilled-GGUF/resolve/main/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.2-1B-DeepSeek67B-Distilled-GGUF/resolve/main/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.2-1B-DeepSeek67B-Distilled-GGUF/resolve/main/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.2-1B-DeepSeek67B-Distilled-GGUF/resolve/main/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.2-1B-DeepSeek67B-Distilled-GGUF/resolve/main/Med-Llama-3.2-1B-DeepSeek67B-Distilled.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Med-Llama-3.2-1B-DeepSeek67B-Distilled-GGUF/resolve/main/Med-Llama-3.2-1B-DeepSeek67B-Distilled.f16.gguf) | f16 | 2.6 | 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. + +