commit b665b39c05f5f501691a8ab6d8476a584db2ac5e Author: ModelHub XC Date: Wed Oct 7 03:51:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/llama-3.1-8b-clinical-V1.4-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..44543d7 --- /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-3.1-8b-clinical-V1.4.f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-clinical-V1.4.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-clinical-V1.4.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-clinical-V1.4.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-clinical-V1.4.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-clinical-V1.4.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-clinical-V1.4.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-clinical-V1.4.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-clinical-V1.4.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-clinical-V1.4.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-clinical-V1.4.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.1-8b-clinical-V1.4.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..215a68b --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: CodCodingCode/llama-3.1-8b-clinical-V1.4 +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/CodCodingCode/llama-3.1-8b-clinical-V1.4 + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#llama-3.1-8b-clinical-V1.4-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/llama-3.1-8b-clinical-V1.4-GGUF/resolve/main/llama-3.1-8b-clinical-V1.4.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-clinical-V1.4-GGUF/resolve/main/llama-3.1-8b-clinical-V1.4.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-clinical-V1.4-GGUF/resolve/main/llama-3.1-8b-clinical-V1.4.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-clinical-V1.4-GGUF/resolve/main/llama-3.1-8b-clinical-V1.4.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-clinical-V1.4-GGUF/resolve/main/llama-3.1-8b-clinical-V1.4.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-clinical-V1.4-GGUF/resolve/main/llama-3.1-8b-clinical-V1.4.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-clinical-V1.4-GGUF/resolve/main/llama-3.1-8b-clinical-V1.4.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-clinical-V1.4-GGUF/resolve/main/llama-3.1-8b-clinical-V1.4.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-clinical-V1.4-GGUF/resolve/main/llama-3.1-8b-clinical-V1.4.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-clinical-V1.4-GGUF/resolve/main/llama-3.1-8b-clinical-V1.4.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-clinical-V1.4-GGUF/resolve/main/llama-3.1-8b-clinical-V1.4.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/llama-3.1-8b-clinical-V1.4-GGUF/resolve/main/llama-3.1-8b-clinical-V1.4.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. + + diff --git a/llama-3.1-8b-clinical-V1.4.IQ4_XS.gguf b/llama-3.1-8b-clinical-V1.4.IQ4_XS.gguf new file mode 100644 index 0000000..ce75011 --- /dev/null +++ b/llama-3.1-8b-clinical-V1.4.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2490332b76b634148ae5a19ef6331ba10f44f56162cab8673782250936dbfe97 +size 4484363264 diff --git a/llama-3.1-8b-clinical-V1.4.Q2_K.gguf b/llama-3.1-8b-clinical-V1.4.Q2_K.gguf new file mode 100644 index 0000000..2d91706 --- /dev/null +++ b/llama-3.1-8b-clinical-V1.4.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae20ea705ef6904f7eb8fd6cdd9093914d37ded97589fb87b76a42518f805ceb +size 3179131904 diff --git a/llama-3.1-8b-clinical-V1.4.Q3_K_L.gguf b/llama-3.1-8b-clinical-V1.4.Q3_K_L.gguf new file mode 100644 index 0000000..f890683 --- /dev/null +++ b/llama-3.1-8b-clinical-V1.4.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a8959917db94b8337c01e98bfee1887b9106f42d0ae6c0716533056f4642951 +size 4321956864 diff --git a/llama-3.1-8b-clinical-V1.4.Q3_K_M.gguf b/llama-3.1-8b-clinical-V1.4.Q3_K_M.gguf new file mode 100644 index 0000000..5aef3c0 --- /dev/null +++ b/llama-3.1-8b-clinical-V1.4.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:610e637be8f852d557692c30e840239f2fc244856d45729003f3e1ee22ed4473 +size 4018918400 diff --git a/llama-3.1-8b-clinical-V1.4.Q3_K_S.gguf b/llama-3.1-8b-clinical-V1.4.Q3_K_S.gguf new file mode 100644 index 0000000..63592a0 --- /dev/null +++ b/llama-3.1-8b-clinical-V1.4.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55f666ca0e133b4051ca9f20f695251a56bfa09b20960c0240d822e04d0ace79 +size 3664499712 diff --git a/llama-3.1-8b-clinical-V1.4.Q4_K_M.gguf b/llama-3.1-8b-clinical-V1.4.Q4_K_M.gguf new file mode 100644 index 0000000..a9c2ce6 --- /dev/null +++ b/llama-3.1-8b-clinical-V1.4.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a1576b3fd07e457a31ca487cd166628e5bf4d91acb0476ff071ec80e76ed2b9 +size 4920734720 diff --git a/llama-3.1-8b-clinical-V1.4.Q4_K_S.gguf b/llama-3.1-8b-clinical-V1.4.Q4_K_S.gguf new file mode 100644 index 0000000..9abb354 --- /dev/null +++ b/llama-3.1-8b-clinical-V1.4.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73cb50dbe2f843bb82e8635a2f1bc8b028dda1b6700f3681453ef9daceb14967 +size 4692669440 diff --git a/llama-3.1-8b-clinical-V1.4.Q5_K_M.gguf b/llama-3.1-8b-clinical-V1.4.Q5_K_M.gguf new file mode 100644 index 0000000..ea2d65f --- /dev/null +++ b/llama-3.1-8b-clinical-V1.4.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8cb0d29a9356fb5dba903b8a85789bf3bcf961ab9cf25ec88f91adc78616d23 +size 5732987904 diff --git a/llama-3.1-8b-clinical-V1.4.Q5_K_S.gguf b/llama-3.1-8b-clinical-V1.4.Q5_K_S.gguf new file mode 100644 index 0000000..ca6af50 --- /dev/null +++ b/llama-3.1-8b-clinical-V1.4.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d44575ed0c866363346b28c4900e147efb323646032e1e7360602ae6f1a2a1a5 +size 5599294464 diff --git a/llama-3.1-8b-clinical-V1.4.Q6_K.gguf b/llama-3.1-8b-clinical-V1.4.Q6_K.gguf new file mode 100644 index 0000000..bf144d7 --- /dev/null +++ b/llama-3.1-8b-clinical-V1.4.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afdd3ae144cc0cf5a3b7dfc9ec131d3b13103e560baab63011e55f53f24468d6 +size 6596006912 diff --git a/llama-3.1-8b-clinical-V1.4.Q8_0.gguf b/llama-3.1-8b-clinical-V1.4.Q8_0.gguf new file mode 100644 index 0000000..50aa011 --- /dev/null +++ b/llama-3.1-8b-clinical-V1.4.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aaed5d14b2f6a1ef878420e0a062bb1a811a8c0e64b7f8cc4bb88484fe3c115 +size 8540771328 diff --git a/llama-3.1-8b-clinical-V1.4.f16.gguf b/llama-3.1-8b-clinical-V1.4.f16.gguf new file mode 100644 index 0000000..a8f294f --- /dev/null +++ b/llama-3.1-8b-clinical-V1.4.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:465b385182aa7f4a02e8972a16415b60a14dc5c1adad6efdaea54b499d3d032d +size 16068891648