commit bf18def86b9408e5d30fa5d790d8e0e97fcd5203 Author: ModelHub XC Date: Mon Jul 27 16:26:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.1-8B-UltraMedical-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d3288d1 --- /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-UltraMedical.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.1-8B-UltraMedical.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.1-8B-UltraMedical.IQ4_XS.gguf b/Llama-3.1-8B-UltraMedical.IQ4_XS.gguf new file mode 100644 index 0000000..f33ec8d --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa6ba1eee195d2ad0eb3b5b1a3d5740483d7f0c3f59bb38f21bd7056031dd6d2 +size 4484364320 diff --git a/Llama-3.1-8B-UltraMedical.Q2_K.gguf b/Llama-3.1-8B-UltraMedical.Q2_K.gguf new file mode 100644 index 0000000..6b41950 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0ae8caa8c8dd53f71eeed8340d5a8f0f62eb7102b6a45e9f264e118055db4b2 +size 3179132960 diff --git a/Llama-3.1-8B-UltraMedical.Q3_K_L.gguf b/Llama-3.1-8B-UltraMedical.Q3_K_L.gguf new file mode 100644 index 0000000..5adaefe --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bce8fc8d7efe9770498ac4d174a6fd168474fae43867a10894abad48e228f917 +size 4321957920 diff --git a/Llama-3.1-8B-UltraMedical.Q3_K_M.gguf b/Llama-3.1-8B-UltraMedical.Q3_K_M.gguf new file mode 100644 index 0000000..0745304 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aa88f9c46a0a1fe77e3831d2ce59f955ac09496f80bda54722cb275bfcc033d +size 4018919456 diff --git a/Llama-3.1-8B-UltraMedical.Q3_K_S.gguf b/Llama-3.1-8B-UltraMedical.Q3_K_S.gguf new file mode 100644 index 0000000..7d36598 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ea3133c20ffe5f0dfd6ce94b559e8c9ea3a6d1dc6947f037edba780a2c76750 +size 3664500768 diff --git a/Llama-3.1-8B-UltraMedical.Q4_K_M.gguf b/Llama-3.1-8B-UltraMedical.Q4_K_M.gguf new file mode 100644 index 0000000..547dd3d --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3412a31560356d57c866681b3f162172376eba2b5d9206f640b47ee599891f9 +size 4920735776 diff --git a/Llama-3.1-8B-UltraMedical.Q4_K_S.gguf b/Llama-3.1-8B-UltraMedical.Q4_K_S.gguf new file mode 100644 index 0000000..9ff1233 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26cc6197bb377c13e4dce52efd732bd1f8ea27db33015047f4f1d29450e4a6c9 +size 4692670496 diff --git a/Llama-3.1-8B-UltraMedical.Q5_K_M.gguf b/Llama-3.1-8B-UltraMedical.Q5_K_M.gguf new file mode 100644 index 0000000..da05922 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a37ed803286d9aa52530f80c926d86b995f600975b827a65aeb9bae733f326ec +size 5732988960 diff --git a/Llama-3.1-8B-UltraMedical.Q5_K_S.gguf b/Llama-3.1-8B-UltraMedical.Q5_K_S.gguf new file mode 100644 index 0000000..fbdf19c --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9847eff852ace1a1e76fc6847b25d226ff74552e95943ac066259343fec9e84c +size 5599295520 diff --git a/Llama-3.1-8B-UltraMedical.Q6_K.gguf b/Llama-3.1-8B-UltraMedical.Q6_K.gguf new file mode 100644 index 0000000..07a68fd --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1efa179c5fce45cd313eb700d9ea2f0fcd836bc050559eb5764feedf86069983 +size 6596007968 diff --git a/Llama-3.1-8B-UltraMedical.Q8_0.gguf b/Llama-3.1-8B-UltraMedical.Q8_0.gguf new file mode 100644 index 0000000..b9a0280 --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46a2750565b5981999bad4a3293e7cb54bb0c2d7937b3f2f0cd8f66c91c81dfc +size 8540772384 diff --git a/Llama-3.1-8B-UltraMedical.f16.gguf b/Llama-3.1-8B-UltraMedical.f16.gguf new file mode 100644 index 0000000..e25409e --- /dev/null +++ b/Llama-3.1-8B-UltraMedical.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3293fcaa5fe1e7b481b50928704c6f24e387fa6f1cca1070fd5359041db6727 +size 16068892704 diff --git a/README.md b/README.md new file mode 100644 index 0000000..38f9f5d --- /dev/null +++ b/README.md @@ -0,0 +1,67 @@ +--- +base_model: TsinghuaC3I/Llama-3.1-8B-UltraMedical +datasets: +- TsinghuaC3I/UltraMedical +- TsinghuaC3I/UltraMedical-Preference +language: +- en +library_name: transformers +license: llama3 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/TsinghuaC3I/Llama-3.1-8B-UltraMedical + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-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-3.1-8B-UltraMedical-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.1-8B-UltraMedical-GGUF/resolve/main/Llama-3.1-8B-UltraMedical.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. + +