commit 7bc825bbe4f4c29b20fedee5b533484c3f8fa60f Author: ModelHub XC Date: Tue Sep 1 22:46:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3-Physician-8B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..147fa60 --- /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 +Llama-3-Physician-8B-Instruct.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Physician-8B-Instruct.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Physician-8B-Instruct.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Physician-8B-Instruct.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Physician-8B-Instruct.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Physician-8B-Instruct.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Physician-8B-Instruct.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Physician-8B-Instruct.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Physician-8B-Instruct.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Physician-8B-Instruct.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Physician-8B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Physician-8B-Instruct.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Physician-8B-Instruct.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Physician-8B-Instruct.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3-Physician-8B-Instruct.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3-Physician-8B-Instruct.IQ3_M.gguf b/Llama-3-Physician-8B-Instruct.IQ3_M.gguf new file mode 100644 index 0000000..d21d1f5 --- /dev/null +++ b/Llama-3-Physician-8B-Instruct.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c1f8ead7f6367f0b2552d16300e4f185685bf38c21fec937a72f2ad8e3951a0 +size 3784823104 diff --git a/Llama-3-Physician-8B-Instruct.IQ3_S.gguf b/Llama-3-Physician-8B-Instruct.IQ3_S.gguf new file mode 100644 index 0000000..f01259e --- /dev/null +++ b/Llama-3-Physician-8B-Instruct.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bb968bef5aca9b0f8742b719edb50130d10e0920dbb7bfdf756bdbc05fc6b12 +size 3682324800 diff --git a/Llama-3-Physician-8B-Instruct.IQ3_XS.gguf b/Llama-3-Physician-8B-Instruct.IQ3_XS.gguf new file mode 100644 index 0000000..7e48735 --- /dev/null +++ b/Llama-3-Physician-8B-Instruct.IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd40c0979cfd30890a7927d44e98adfd9409fcc259c1434b5842f6859f54115e +size 3518746944 diff --git a/Llama-3-Physician-8B-Instruct.IQ4_XS.gguf b/Llama-3-Physician-8B-Instruct.IQ4_XS.gguf new file mode 100644 index 0000000..9a8dc28 --- /dev/null +++ b/Llama-3-Physician-8B-Instruct.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:499cedefa389afdf6ed617b0aca2cd1f2490353897bf7556a4ebcbfbb123ff7c +size 4484362560 diff --git a/Llama-3-Physician-8B-Instruct.Q2_K.gguf b/Llama-3-Physician-8B-Instruct.Q2_K.gguf new file mode 100644 index 0000000..1541e26 --- /dev/null +++ b/Llama-3-Physician-8B-Instruct.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91d563f40efd549fae33231edcca9762268f4f978d5fd5627599b1ca767229c4 +size 3179131200 diff --git a/Llama-3-Physician-8B-Instruct.Q3_K_L.gguf b/Llama-3-Physician-8B-Instruct.Q3_K_L.gguf new file mode 100644 index 0000000..9e00e11 --- /dev/null +++ b/Llama-3-Physician-8B-Instruct.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaeaa5376f29935f5b32cb9261f51848855ff7d92a40afe24b5079502e8f8ea4 +size 4321956160 diff --git a/Llama-3-Physician-8B-Instruct.Q3_K_M.gguf b/Llama-3-Physician-8B-Instruct.Q3_K_M.gguf new file mode 100644 index 0000000..84a0658 --- /dev/null +++ b/Llama-3-Physician-8B-Instruct.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c23cc8c4effdee980df4670ed0325b45e4e96a63e7bbbf006d2806313799d9c +size 4018917696 diff --git a/Llama-3-Physician-8B-Instruct.Q3_K_S.gguf b/Llama-3-Physician-8B-Instruct.Q3_K_S.gguf new file mode 100644 index 0000000..c9ff172 --- /dev/null +++ b/Llama-3-Physician-8B-Instruct.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dc1fa6df2d35fe919b0e29cb3bb087365e220d14c286739434055ba67fd0151 +size 3664499008 diff --git a/Llama-3-Physician-8B-Instruct.Q4_K_M.gguf b/Llama-3-Physician-8B-Instruct.Q4_K_M.gguf new file mode 100644 index 0000000..aba2725 --- /dev/null +++ b/Llama-3-Physician-8B-Instruct.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00fcfdbaf9795b908fb05bb9df2019b5565db1215fea19056ba6d510393e9345 +size 4920734016 diff --git a/Llama-3-Physician-8B-Instruct.Q4_K_S.gguf b/Llama-3-Physician-8B-Instruct.Q4_K_S.gguf new file mode 100644 index 0000000..24bc09e --- /dev/null +++ b/Llama-3-Physician-8B-Instruct.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efb07f95f7cfa2285de0b32ce92dbb51f49dde88cab948acd4817d149adeb99b +size 4692668736 diff --git a/Llama-3-Physician-8B-Instruct.Q5_K_M.gguf b/Llama-3-Physician-8B-Instruct.Q5_K_M.gguf new file mode 100644 index 0000000..a0fdad8 --- /dev/null +++ b/Llama-3-Physician-8B-Instruct.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9529a75f62766a62b87f541ffebc156165beb71dfcf292d966be02d88d568bc6 +size 5732987200 diff --git a/Llama-3-Physician-8B-Instruct.Q5_K_S.gguf b/Llama-3-Physician-8B-Instruct.Q5_K_S.gguf new file mode 100644 index 0000000..cf1275d --- /dev/null +++ b/Llama-3-Physician-8B-Instruct.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ef699469cb0f26d00bcbf07cfb07a2ebc14747011f671cdfff8dcdb1b84f215 +size 5599293760 diff --git a/Llama-3-Physician-8B-Instruct.Q6_K.gguf b/Llama-3-Physician-8B-Instruct.Q6_K.gguf new file mode 100644 index 0000000..c40af5c --- /dev/null +++ b/Llama-3-Physician-8B-Instruct.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0920f1fb5a9ef6e44d05ae9f90d20c8842341dbbe34d69a2219b95aea900ef27 +size 6596006208 diff --git a/Llama-3-Physician-8B-Instruct.Q8_0.gguf b/Llama-3-Physician-8B-Instruct.Q8_0.gguf new file mode 100644 index 0000000..059d6f8 --- /dev/null +++ b/Llama-3-Physician-8B-Instruct.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e12dd4f10cd0164296f584433934afae2abadcc9456600d4803464e05948c2e +size 8540770624 diff --git a/Llama-3-Physician-8B-Instruct.f16.gguf b/Llama-3-Physician-8B-Instruct.f16.gguf new file mode 100644 index 0000000..b8eea4d --- /dev/null +++ b/Llama-3-Physician-8B-Instruct.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b7cb7230de3a45cc6570710d709ab1cec53dc3de076ec10d7a265973dc29af6 +size 16068890944 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bd0e799 --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: YiDuo1999/Llama-3-Physician-8B-Instruct +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/YiDuo1999/Llama-3-Physician-8B-Instruct + + +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/Llama-3-Physician-8B-Instruct-GGUF/resolve/main/Llama-3-Physician-8B-Instruct.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Physician-8B-Instruct-GGUF/resolve/main/Llama-3-Physician-8B-Instruct.IQ3_XS.gguf) | IQ3_XS | 3.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Physician-8B-Instruct-GGUF/resolve/main/Llama-3-Physician-8B-Instruct.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Physician-8B-Instruct-GGUF/resolve/main/Llama-3-Physician-8B-Instruct.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Physician-8B-Instruct-GGUF/resolve/main/Llama-3-Physician-8B-Instruct.IQ3_M.gguf) | IQ3_M | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Physician-8B-Instruct-GGUF/resolve/main/Llama-3-Physician-8B-Instruct.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Physician-8B-Instruct-GGUF/resolve/main/Llama-3-Physician-8B-Instruct.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Physician-8B-Instruct-GGUF/resolve/main/Llama-3-Physician-8B-Instruct.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Physician-8B-Instruct-GGUF/resolve/main/Llama-3-Physician-8B-Instruct.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Physician-8B-Instruct-GGUF/resolve/main/Llama-3-Physician-8B-Instruct.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Physician-8B-Instruct-GGUF/resolve/main/Llama-3-Physician-8B-Instruct.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Physician-8B-Instruct-GGUF/resolve/main/Llama-3-Physician-8B-Instruct.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Physician-8B-Instruct-GGUF/resolve/main/Llama-3-Physician-8B-Instruct.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Physician-8B-Instruct-GGUF/resolve/main/Llama-3-Physician-8B-Instruct.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3-Physician-8B-Instruct-GGUF/resolve/main/Llama-3-Physician-8B-Instruct.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. + +