commit 24622dda71a3928e1f4948c59fea336eada00f3e Author: ModelHub XC Date: Sun May 10 08:33:19 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Clinical-AI-llama-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..575578a --- /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 +Clinical-AI-llama.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Clinical-AI-llama.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Clinical-AI-llama.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Clinical-AI-llama.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Clinical-AI-llama.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Clinical-AI-llama.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Clinical-AI-llama.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Clinical-AI-llama.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Clinical-AI-llama.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Clinical-AI-llama.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Clinical-AI-llama.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Clinical-AI-llama.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Clinical-AI-llama.IQ4_XS.gguf b/Clinical-AI-llama.IQ4_XS.gguf new file mode 100644 index 0000000..9ad330c --- /dev/null +++ b/Clinical-AI-llama.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07b69d63cc3de8fd0c6c525cbdd12a1e22c1756f7ab7ec9f3382e81aef70fe0a +size 1840906784 diff --git a/Clinical-AI-llama.Q2_K.gguf b/Clinical-AI-llama.Q2_K.gguf new file mode 100644 index 0000000..e5ad462 --- /dev/null +++ b/Clinical-AI-llama.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fff614ba3a50ddff095ffe2590e2b1edce518a951499bb22ca4d293e698579db +size 1363935776 diff --git a/Clinical-AI-llama.Q3_K_L.gguf b/Clinical-AI-llama.Q3_K_L.gguf new file mode 100644 index 0000000..30ea7fb --- /dev/null +++ b/Clinical-AI-llama.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5834ba4c185f7d2f1e62b3bf81f0af74057e4bac855edac92eaad7044d6168a3 +size 1815347744 diff --git a/Clinical-AI-llama.Q3_K_M.gguf b/Clinical-AI-llama.Q3_K_M.gguf new file mode 100644 index 0000000..be74ef4 --- /dev/null +++ b/Clinical-AI-llama.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac4e12ce66ed7cffbe4edbebc4bf462ba106833921c7b86a3c95b20b2979fd80 +size 1687159328 diff --git a/Clinical-AI-llama.Q3_K_S.gguf b/Clinical-AI-llama.Q3_K_S.gguf new file mode 100644 index 0000000..4f7965f --- /dev/null +++ b/Clinical-AI-llama.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e803e5b81d94a9342c521f25f8f398cebfa6693cc99b6c67ea8a09036dc8d8a +size 1542849056 diff --git a/Clinical-AI-llama.Q4_K_M.gguf b/Clinical-AI-llama.Q4_K_M.gguf new file mode 100644 index 0000000..eac7f8b --- /dev/null +++ b/Clinical-AI-llama.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc7ad937bd0334c309b815ebc4c5f48ae37d4d4523ecee5e075be3c0a1e5e9dc +size 2019377696 diff --git a/Clinical-AI-llama.Q4_K_S.gguf b/Clinical-AI-llama.Q4_K_S.gguf new file mode 100644 index 0000000..aecd855 --- /dev/null +++ b/Clinical-AI-llama.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:403f10d87b6a85cb4ab48e78df6b6712900a9ca130c19a9d264ed35ddb179f0f +size 1928200736 diff --git a/Clinical-AI-llama.Q5_K_M.gguf b/Clinical-AI-llama.Q5_K_M.gguf new file mode 100644 index 0000000..abc5793 --- /dev/null +++ b/Clinical-AI-llama.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7960a8e18c131d4c2c4d0cec10fd02585df20a0a7b877d1b4d3e80785c66e2fb +size 2322154016 diff --git a/Clinical-AI-llama.Q5_K_S.gguf b/Clinical-AI-llama.Q5_K_S.gguf new file mode 100644 index 0000000..a49fb07 --- /dev/null +++ b/Clinical-AI-llama.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26d14e842fd9ef2fb0da6b98ff83344b6c840e6bd40e9649fe47dd35e9594462 +size 2269512224 diff --git a/Clinical-AI-llama.Q6_K.gguf b/Clinical-AI-llama.Q6_K.gguf new file mode 100644 index 0000000..02e516c --- /dev/null +++ b/Clinical-AI-llama.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:249f1d4fe2ae2622a7110b633670dfb4fe2267e33e4eb1b888f414903c78ecba +size 2643853856 diff --git a/Clinical-AI-llama.Q8_0.gguf b/Clinical-AI-llama.Q8_0.gguf new file mode 100644 index 0000000..7401406 --- /dev/null +++ b/Clinical-AI-llama.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bf4b8448180ba8e39699a938827d87cc4ee8bb6737d4386bf872fe47f2eb57d +size 3421899296 diff --git a/Clinical-AI-llama.f16.gguf b/Clinical-AI-llama.f16.gguf new file mode 100644 index 0000000..a8bead9 --- /dev/null +++ b/Clinical-AI-llama.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4bf374ab7d237251dded244e653c46acdc89a26dccdc1b6c53ac7db2b2a7517 +size 6433688096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..46641ea --- /dev/null +++ b/README.md @@ -0,0 +1,75 @@ +--- +base_model: yash33123/Clinical-AI-llama +language: +- en +library_name: transformers +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- unsloth +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/yash33123/Clinical-AI-llama + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Clinical-AI-llama-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/Clinical-AI-llama-GGUF/resolve/main/Clinical-AI-llama.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Clinical-AI-llama-GGUF/resolve/main/Clinical-AI-llama.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Clinical-AI-llama-GGUF/resolve/main/Clinical-AI-llama.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Clinical-AI-llama-GGUF/resolve/main/Clinical-AI-llama.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Clinical-AI-llama-GGUF/resolve/main/Clinical-AI-llama.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Clinical-AI-llama-GGUF/resolve/main/Clinical-AI-llama.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Clinical-AI-llama-GGUF/resolve/main/Clinical-AI-llama.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Clinical-AI-llama-GGUF/resolve/main/Clinical-AI-llama.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Clinical-AI-llama-GGUF/resolve/main/Clinical-AI-llama.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Clinical-AI-llama-GGUF/resolve/main/Clinical-AI-llama.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Clinical-AI-llama-GGUF/resolve/main/Clinical-AI-llama.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Clinical-AI-llama-GGUF/resolve/main/Clinical-AI-llama.f16.gguf) | f16 | 6.5 | 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. + +