commit bd822560c4cd588a566a0c621c85c086b3476696 Author: ModelHub XC Date: Sat Sep 19 06:30:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/MedLlama-3-8B_DARE-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..7f00eda --- /dev/null +++ b/.gitattributes @@ -0,0 +1,50 @@ +*.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 +MedLlama-3-8B_DARE.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +MedLlama-3-8B_DARE.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +MedLlama-3-8B_DARE.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedLlama-3-8B_DARE.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +MedLlama-3-8B_DARE.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +MedLlama-3-8B_DARE.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedLlama-3-8B_DARE.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedLlama-3-8B_DARE.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +MedLlama-3-8B_DARE.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +MedLlama-3-8B_DARE.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedLlama-3-8B_DARE.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +MedLlama-3-8B_DARE.f16.gguf filter=lfs diff=lfs merge=lfs -text +MedLlama-3-8B_DARE.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +MedLlama-3-8B_DARE.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +MedLlama-3-8B_DARE.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/MedLlama-3-8B_DARE.IQ3_M.gguf b/MedLlama-3-8B_DARE.IQ3_M.gguf new file mode 100644 index 0000000..8c4f34b --- /dev/null +++ b/MedLlama-3-8B_DARE.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b510e0c3af6c9a53fee8f6acaf0ba13f63fecbabf71cb4bd073850b682077a3 +size 3784823072 diff --git a/MedLlama-3-8B_DARE.IQ3_S.gguf b/MedLlama-3-8B_DARE.IQ3_S.gguf new file mode 100644 index 0000000..c26ee84 --- /dev/null +++ b/MedLlama-3-8B_DARE.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:959e365e8c4e8ecf8402e3276634a1125d00827d6037c879cc557546b512b601 +size 3682324768 diff --git a/MedLlama-3-8B_DARE.IQ3_XS.gguf b/MedLlama-3-8B_DARE.IQ3_XS.gguf new file mode 100644 index 0000000..883778f --- /dev/null +++ b/MedLlama-3-8B_DARE.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6058a5f5747b4277f4e4120a163dc52ed474ee6ff2fe052b3b2b4bdf8fd2abc +size 3518746912 diff --git a/MedLlama-3-8B_DARE.IQ4_XS.gguf b/MedLlama-3-8B_DARE.IQ4_XS.gguf new file mode 100644 index 0000000..9e807b5 --- /dev/null +++ b/MedLlama-3-8B_DARE.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a87edbdc082e565f8f0eb3eb67fe1e7cdc56db25ff0efd06816326f72ddbf58 +size 4484362528 diff --git a/MedLlama-3-8B_DARE.Q2_K.gguf b/MedLlama-3-8B_DARE.Q2_K.gguf new file mode 100644 index 0000000..7f24209 --- /dev/null +++ b/MedLlama-3-8B_DARE.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2604ac6f7b698b78fe4991b3b2b814986424f0b8ec83c6083da33efed120e43d +size 3179131168 diff --git a/MedLlama-3-8B_DARE.Q3_K_L.gguf b/MedLlama-3-8B_DARE.Q3_K_L.gguf new file mode 100644 index 0000000..8f3a6b7 --- /dev/null +++ b/MedLlama-3-8B_DARE.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:917a340895af3e3698c19f7ec8f65acd4b519350ec9f0831a52040bc807f0e69 +size 4321956128 diff --git a/MedLlama-3-8B_DARE.Q3_K_M.gguf b/MedLlama-3-8B_DARE.Q3_K_M.gguf new file mode 100644 index 0000000..4431564 --- /dev/null +++ b/MedLlama-3-8B_DARE.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e04999932cdf38865681cdbff25db679a2469d4a3708eeffeccb79feb1a60da5 +size 4018917664 diff --git a/MedLlama-3-8B_DARE.Q3_K_S.gguf b/MedLlama-3-8B_DARE.Q3_K_S.gguf new file mode 100644 index 0000000..36c9d07 --- /dev/null +++ b/MedLlama-3-8B_DARE.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4c063769479b899a91239e257ca34a3c6f2b1c3893c2c6a20a29357c453e57d +size 3664498976 diff --git a/MedLlama-3-8B_DARE.Q4_K_M.gguf b/MedLlama-3-8B_DARE.Q4_K_M.gguf new file mode 100644 index 0000000..17fd68f --- /dev/null +++ b/MedLlama-3-8B_DARE.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87213bd797254407cd8ea3c044c77fa842568a3ed7ed3d81926c071e66da3df8 +size 4920733984 diff --git a/MedLlama-3-8B_DARE.Q4_K_S.gguf b/MedLlama-3-8B_DARE.Q4_K_S.gguf new file mode 100644 index 0000000..e49c436 --- /dev/null +++ b/MedLlama-3-8B_DARE.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a94bbd888f5129a14f91080cd1c72f8a95e6db8802eee950eaf78fb2f3437d24 +size 4692668704 diff --git a/MedLlama-3-8B_DARE.Q5_K_M.gguf b/MedLlama-3-8B_DARE.Q5_K_M.gguf new file mode 100644 index 0000000..61e0b58 --- /dev/null +++ b/MedLlama-3-8B_DARE.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85b4f674994e2c65d36bc2951cdd0b18de97bd217a97bb37519263ec15dd25ab +size 5732987168 diff --git a/MedLlama-3-8B_DARE.Q5_K_S.gguf b/MedLlama-3-8B_DARE.Q5_K_S.gguf new file mode 100644 index 0000000..0b53ddc --- /dev/null +++ b/MedLlama-3-8B_DARE.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca05331267574c4d3955127db155b524c9979ca62ada4781fb541ee5c5875d0 +size 5599293728 diff --git a/MedLlama-3-8B_DARE.Q6_K.gguf b/MedLlama-3-8B_DARE.Q6_K.gguf new file mode 100644 index 0000000..e77d772 --- /dev/null +++ b/MedLlama-3-8B_DARE.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af3de0c2aa1a3c6d590a7efb7e744f9f3e25b019d5dd112ff102984277a9d3e0 +size 6596006176 diff --git a/MedLlama-3-8B_DARE.Q8_0.gguf b/MedLlama-3-8B_DARE.Q8_0.gguf new file mode 100644 index 0000000..7992e06 --- /dev/null +++ b/MedLlama-3-8B_DARE.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:316e9d2912ec65254fafec112a738ff9f0f3739f464a9c31194009e8887bf180 +size 8540770592 diff --git a/MedLlama-3-8B_DARE.f16.gguf b/MedLlama-3-8B_DARE.f16.gguf new file mode 100644 index 0000000..3347b86 --- /dev/null +++ b/MedLlama-3-8B_DARE.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:181d31dc89eebd8eba33817cae56c025438d095cc6839c1cd8fc6de9594ee9ee +size 16068890912 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dc3d06d --- /dev/null +++ b/README.md @@ -0,0 +1,69 @@ +--- +base_model: ChenWeiLi/MedLlama-3-8B_DARE +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +tags: +- mergekit +- merge +--- +## About + + + + + +static quants of https://huggingface.co/ChenWeiLi/MedLlama-3-8B_DARE + + +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/MedLlama-3-8B_DARE-GGUF/resolve/main/MedLlama-3-8B_DARE.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/MedLlama-3-8B_DARE-GGUF/resolve/main/MedLlama-3-8B_DARE.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/MedLlama-3-8B_DARE-GGUF/resolve/main/MedLlama-3-8B_DARE.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/MedLlama-3-8B_DARE-GGUF/resolve/main/MedLlama-3-8B_DARE.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/MedLlama-3-8B_DARE-GGUF/resolve/main/MedLlama-3-8B_DARE.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/MedLlama-3-8B_DARE-GGUF/resolve/main/MedLlama-3-8B_DARE.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/MedLlama-3-8B_DARE-GGUF/resolve/main/MedLlama-3-8B_DARE.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/MedLlama-3-8B_DARE-GGUF/resolve/main/MedLlama-3-8B_DARE.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/MedLlama-3-8B_DARE-GGUF/resolve/main/MedLlama-3-8B_DARE.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedLlama-3-8B_DARE-GGUF/resolve/main/MedLlama-3-8B_DARE.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/MedLlama-3-8B_DARE-GGUF/resolve/main/MedLlama-3-8B_DARE.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/MedLlama-3-8B_DARE-GGUF/resolve/main/MedLlama-3-8B_DARE.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/MedLlama-3-8B_DARE-GGUF/resolve/main/MedLlama-3-8B_DARE.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/MedLlama-3-8B_DARE-GGUF/resolve/main/MedLlama-3-8B_DARE.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/MedLlama-3-8B_DARE-GGUF/resolve/main/MedLlama-3-8B_DARE.f16.gguf) | f16 | 16.2 | 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. + +