commit a7fbeecc46a6bfd90e9090c24954c6f1d97f88c8 Author: ModelHub XC Date: Sun May 31 12:21:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama3-Aloe-8B-Alpha-Patient-Descriptions-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d2bfe46 --- /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 +Llama3-Aloe-8B-Alpha-Patient-Descriptions.f16.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama3-Aloe-8B-Alpha-Patient-Descriptions.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama3-Aloe-8B-Alpha-Patient-Descriptions.IQ4_XS.gguf b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.IQ4_XS.gguf new file mode 100644 index 0000000..c30f4a2 --- /dev/null +++ b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e77b5f07682c570ab5e0507478c9cc9d34a42406c22d7e580b911031dcb010df +size 4484365824 diff --git a/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q2_K.gguf b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q2_K.gguf new file mode 100644 index 0000000..832c4fe --- /dev/null +++ b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75944bc6faf4c959470d66b9102a680e70d9a20075442f241b67344bd32afb39 +size 3179134464 diff --git a/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q3_K_L.gguf b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q3_K_L.gguf new file mode 100644 index 0000000..bb75064 --- /dev/null +++ b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12f813b862cb00fc46134ee95bace5cf8d459f1b88d8cd47a9c383a41ce4aa71 +size 4321959424 diff --git a/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q3_K_M.gguf b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q3_K_M.gguf new file mode 100644 index 0000000..a063a54 --- /dev/null +++ b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28706fda786412a0cc9872973ae27b1f49157359705e689eaede49847d369bbf +size 4018920960 diff --git a/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q3_K_S.gguf b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q3_K_S.gguf new file mode 100644 index 0000000..58b3b18 --- /dev/null +++ b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:741c318564b80b3687668bb0a0b556a6e4e31863dbb2ecce0a5e25d647a6666f +size 3664502272 diff --git a/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q4_K_M.gguf b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q4_K_M.gguf new file mode 100644 index 0000000..9084dd8 --- /dev/null +++ b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dace21aa8db457b2996b6bce41adaf2a346c58a1a8ec2f3d5826fa899b8e710 +size 4920737280 diff --git a/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q4_K_S.gguf b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q4_K_S.gguf new file mode 100644 index 0000000..09cf876 --- /dev/null +++ b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71e01323b59e63b4b5edddbb07877cb4f6eec0514a04c5b6b6c2b09d8e1fe94a +size 4692672000 diff --git a/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q5_K_M.gguf b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q5_K_M.gguf new file mode 100644 index 0000000..5741527 --- /dev/null +++ b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7f0231bfa9a8088288c989b170e2a95647cc7bf4cf1fb349e13670a8c13a50e +size 5732990464 diff --git a/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q5_K_S.gguf b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q5_K_S.gguf new file mode 100644 index 0000000..4df9a0e --- /dev/null +++ b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ff39ba8f0aebaf0ddd3a9ca939d00a1c0feca6953e6876615240936f5476f00 +size 5599297024 diff --git a/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q6_K.gguf b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q6_K.gguf new file mode 100644 index 0000000..648083a --- /dev/null +++ b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc439d8738e272002afbe30f463932f05d1fe27e1b31f23b52a92cb15744e737 +size 6596009472 diff --git a/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q8_0.gguf b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q8_0.gguf new file mode 100644 index 0000000..659f4d5 --- /dev/null +++ b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5455d7ea0cc7bf0662baa6ae580c1f8219426ad40fc9bb45e6497e84cebed8e +size 8540773888 diff --git a/Llama3-Aloe-8B-Alpha-Patient-Descriptions.f16.gguf b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.f16.gguf new file mode 100644 index 0000000..35d31a1 --- /dev/null +++ b/Llama3-Aloe-8B-Alpha-Patient-Descriptions.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69943d01dec83134d52ae2e9a9b215eb6f69a82c858d12cc211f2d10cabd9a85 +size 16068894208 diff --git a/README.md b/README.md new file mode 100644 index 0000000..bf8c8c8 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: mikkel-werling/Llama3-Aloe-8B-Alpha-Patient-Descriptions +datasets: mikkel-werling/cardiovascular_biobank_patient_descriptions +language: +- en +library_name: transformers +model_name: Llama3-Aloe-8B-Alpha-Patient-Descriptions +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- generated_from_trainer +- open-r1 +- trl +- sft +--- +## About + + + + + + + + + +static quants of https://huggingface.co/mikkel-werling/Llama3-Aloe-8B-Alpha-Patient-Descriptions + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Llama3-Aloe-8B-Alpha-Patient-Descriptions-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/Llama3-Aloe-8B-Alpha-Patient-Descriptions-GGUF/resolve/main/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Aloe-8B-Alpha-Patient-Descriptions-GGUF/resolve/main/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Aloe-8B-Alpha-Patient-Descriptions-GGUF/resolve/main/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Aloe-8B-Alpha-Patient-Descriptions-GGUF/resolve/main/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Aloe-8B-Alpha-Patient-Descriptions-GGUF/resolve/main/Llama3-Aloe-8B-Alpha-Patient-Descriptions.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Aloe-8B-Alpha-Patient-Descriptions-GGUF/resolve/main/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Aloe-8B-Alpha-Patient-Descriptions-GGUF/resolve/main/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Aloe-8B-Alpha-Patient-Descriptions-GGUF/resolve/main/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Aloe-8B-Alpha-Patient-Descriptions-GGUF/resolve/main/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Aloe-8B-Alpha-Patient-Descriptions-GGUF/resolve/main/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Aloe-8B-Alpha-Patient-Descriptions-GGUF/resolve/main/Llama3-Aloe-8B-Alpha-Patient-Descriptions.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama3-Aloe-8B-Alpha-Patient-Descriptions-GGUF/resolve/main/Llama3-Aloe-8B-Alpha-Patient-Descriptions.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. + +