commit 9ec59cdcb0dfd57fa0335c07af3ea1b0c9e1987e Author: ModelHub XC Date: Tue May 19 13:39:00 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/LLaMa-1-MedicWizard-7B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b206512 --- /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 +LLaMa-1-MedicWizard-7B.f16.gguf filter=lfs diff=lfs merge=lfs -text +LLaMa-1-MedicWizard-7B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +LLaMa-1-MedicWizard-7B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMa-1-MedicWizard-7B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMa-1-MedicWizard-7B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMa-1-MedicWizard-7B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMa-1-MedicWizard-7B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMa-1-MedicWizard-7B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +LLaMa-1-MedicWizard-7B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +LLaMa-1-MedicWizard-7B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +LLaMa-1-MedicWizard-7B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +LLaMa-1-MedicWizard-7B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/LLaMa-1-MedicWizard-7B.IQ4_XS.gguf b/LLaMa-1-MedicWizard-7B.IQ4_XS.gguf new file mode 100644 index 0000000..39479fd --- /dev/null +++ b/LLaMa-1-MedicWizard-7B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70c80257a3c305741f948167ea405cd4d8f9f038daf95acce6f10e5d1371a94d +size 3647522880 diff --git a/LLaMa-1-MedicWizard-7B.Q2_K.gguf b/LLaMa-1-MedicWizard-7B.Q2_K.gguf new file mode 100644 index 0000000..09b0119 --- /dev/null +++ b/LLaMa-1-MedicWizard-7B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdc94a5f56a65d8664731a494e43076886a3981aecabb6bd8a4c8a897e154fdf +size 2532869376 diff --git a/LLaMa-1-MedicWizard-7B.Q3_K_L.gguf b/LLaMa-1-MedicWizard-7B.Q3_K_L.gguf new file mode 100644 index 0000000..b64d235 --- /dev/null +++ b/LLaMa-1-MedicWizard-7B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef4c61ab157bdeaec2b7d97038d3f25cfa26bdad814854c1f9e4da71d2fef030 +size 3597117088 diff --git a/LLaMa-1-MedicWizard-7B.Q3_K_M.gguf b/LLaMa-1-MedicWizard-7B.Q3_K_M.gguf new file mode 100644 index 0000000..8b0c842 --- /dev/null +++ b/LLaMa-1-MedicWizard-7B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72307b3b99836aaf9771cffcf5ba19bd449756ec1ab66e9834a90b21f9ebefaa +size 3298010784 diff --git a/LLaMa-1-MedicWizard-7B.Q3_K_S.gguf b/LLaMa-1-MedicWizard-7B.Q3_K_S.gguf new file mode 100644 index 0000000..cba342f --- /dev/null +++ b/LLaMa-1-MedicWizard-7B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1827305717854a21a38f28310c878cc4b4fae832e525b7c4d90ce055c19ac5e +size 2948310688 diff --git a/LLaMa-1-MedicWizard-7B.Q4_K_M.gguf b/LLaMa-1-MedicWizard-7B.Q4_K_M.gguf new file mode 100644 index 0000000..b83ddb5 --- /dev/null +++ b/LLaMa-1-MedicWizard-7B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38a9615d17960eb8cccfe7491b3811cfa1cefffc75f47e01cc25535349e05451 +size 4081010880 diff --git a/LLaMa-1-MedicWizard-7B.Q4_K_S.gguf b/LLaMa-1-MedicWizard-7B.Q4_K_S.gguf new file mode 100644 index 0000000..e430c9c --- /dev/null +++ b/LLaMa-1-MedicWizard-7B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27478838a8a6224d88e9a8ca4d6d7d5707f144283e1be58f49965a88dcd3ba6e +size 3856746688 diff --git a/LLaMa-1-MedicWizard-7B.Q5_K_M.gguf b/LLaMa-1-MedicWizard-7B.Q5_K_M.gguf new file mode 100644 index 0000000..7594e9b --- /dev/null +++ b/LLaMa-1-MedicWizard-7B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bee797f1d26b540a08071391753b43be44ef8509216720725df29f8201481885 +size 4783164096 diff --git a/LLaMa-1-MedicWizard-7B.Q5_K_S.gguf b/LLaMa-1-MedicWizard-7B.Q5_K_S.gguf new file mode 100644 index 0000000..69e2707 --- /dev/null +++ b/LLaMa-1-MedicWizard-7B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f50c044d2d9d20ee45ed96737d1fe7ccd7128be6e64805f160b0cd1a1e2d76c6 +size 4651698880 diff --git a/LLaMa-1-MedicWizard-7B.Q6_K.gguf b/LLaMa-1-MedicWizard-7B.Q6_K.gguf new file mode 100644 index 0000000..76653c5 --- /dev/null +++ b/LLaMa-1-MedicWizard-7B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f51761963f71ff05d12bca66d6f69cd41fcc18b9fddd342f1234f4b85ab8f7a4 +size 5529201888 diff --git a/LLaMa-1-MedicWizard-7B.Q8_0.gguf b/LLaMa-1-MedicWizard-7B.Q8_0.gguf new file mode 100644 index 0000000..fadbda2 --- /dev/null +++ b/LLaMa-1-MedicWizard-7B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8a7ab7f1ac116285b29b3b7166b3f51fa525e78cbfbc496923122e9bb3e49b2 +size 7161099424 diff --git a/LLaMa-1-MedicWizard-7B.f16.gguf b/LLaMa-1-MedicWizard-7B.f16.gguf new file mode 100644 index 0000000..d765c96 --- /dev/null +++ b/LLaMa-1-MedicWizard-7B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f65b3d42ff1084f33da739baca70837d08512c3abc4c6f108becc8f02980dec +size 13478122144 diff --git a/README.md b/README.md new file mode 100644 index 0000000..720f305 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: PJMixers-Archive/LLaMa-1-MedicWizard-7B +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- llama +- alpaca +--- +## About + + + + + + + + + +static quants of https://huggingface.co/PJMixers-Archive/LLaMa-1-MedicWizard-7B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LLaMa-1-MedicWizard-7B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/LLaMa-1-MedicWizard-7B-i1-GGUF +## 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/LLaMa-1-MedicWizard-7B-GGUF/resolve/main/LLaMa-1-MedicWizard-7B.Q2_K.gguf) | Q2_K | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMa-1-MedicWizard-7B-GGUF/resolve/main/LLaMa-1-MedicWizard-7B.Q3_K_S.gguf) | Q3_K_S | 3.0 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMa-1-MedicWizard-7B-GGUF/resolve/main/LLaMa-1-MedicWizard-7B.Q3_K_M.gguf) | Q3_K_M | 3.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMa-1-MedicWizard-7B-GGUF/resolve/main/LLaMa-1-MedicWizard-7B.Q3_K_L.gguf) | Q3_K_L | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMa-1-MedicWizard-7B-GGUF/resolve/main/LLaMa-1-MedicWizard-7B.IQ4_XS.gguf) | IQ4_XS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMa-1-MedicWizard-7B-GGUF/resolve/main/LLaMa-1-MedicWizard-7B.Q4_K_S.gguf) | Q4_K_S | 4.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMa-1-MedicWizard-7B-GGUF/resolve/main/LLaMa-1-MedicWizard-7B.Q4_K_M.gguf) | Q4_K_M | 4.2 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/LLaMa-1-MedicWizard-7B-GGUF/resolve/main/LLaMa-1-MedicWizard-7B.Q5_K_S.gguf) | Q5_K_S | 4.8 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMa-1-MedicWizard-7B-GGUF/resolve/main/LLaMa-1-MedicWizard-7B.Q5_K_M.gguf) | Q5_K_M | 4.9 | | +| [GGUF](https://huggingface.co/mradermacher/LLaMa-1-MedicWizard-7B-GGUF/resolve/main/LLaMa-1-MedicWizard-7B.Q6_K.gguf) | Q6_K | 5.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMa-1-MedicWizard-7B-GGUF/resolve/main/LLaMa-1-MedicWizard-7B.Q8_0.gguf) | Q8_0 | 7.3 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/LLaMa-1-MedicWizard-7B-GGUF/resolve/main/LLaMa-1-MedicWizard-7B.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. + +