commit f9b116c96d276e8ede39453ca74339c5cfc4fbd8 Author: ModelHub XC Date: Fri Apr 24 00:53:07 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b476ef4 --- /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 +HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.f16.gguf filter=lfs diff=lfs merge=lfs -text +HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.IQ4_XS.gguf b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.IQ4_XS.gguf new file mode 100644 index 0000000..4ae3a4c --- /dev/null +++ b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de35e44bdac35149f77fae6668e4aaf90bd8043a52098f651cf4b6529945b7d8 +size 4484368416 diff --git a/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q2_K.gguf b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q2_K.gguf new file mode 100644 index 0000000..2070deb --- /dev/null +++ b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ac5a669cd7987d98a91a2a148f6025e4c4dc3be9873f291e68a97b85bfbb4bf +size 3179137056 diff --git a/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q3_K_L.gguf b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q3_K_L.gguf new file mode 100644 index 0000000..4062354 --- /dev/null +++ b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:162e7f79865e970f0ecdb1370e7b79eaaa28ec6ec1d8d62721e276529d2bda2b +size 4321962016 diff --git a/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q3_K_M.gguf b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q3_K_M.gguf new file mode 100644 index 0000000..d869bab --- /dev/null +++ b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dbb1d21746f14a2089cbbb3901a4e310075774741d88a91ef037400f918a345 +size 4018923552 diff --git a/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q3_K_S.gguf b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q3_K_S.gguf new file mode 100644 index 0000000..31fc189 --- /dev/null +++ b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e0c90966f172cc1fa92bb06998acbe229a54cb4cbaa3a6905a4517790bb658c +size 3664504864 diff --git a/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q4_K_M.gguf b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q4_K_M.gguf new file mode 100644 index 0000000..4173283 --- /dev/null +++ b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd0e6711f404c0b655b381ae455dfb4e175dc1cf3462cc4423c486d71949ca85 +size 4920739872 diff --git a/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q4_K_S.gguf b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q4_K_S.gguf new file mode 100644 index 0000000..87805e4 --- /dev/null +++ b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af98eb4b6ee158532eb775eb6de5821128066b8d85fbe79421c43b4afbb673c1 +size 4692674592 diff --git a/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q5_K_M.gguf b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q5_K_M.gguf new file mode 100644 index 0000000..aec5823 --- /dev/null +++ b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4361223f1defa1225e3c989c7acc1844e106b84dd84e6af3db9dc6f45e9f52e5 +size 5732993056 diff --git a/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q5_K_S.gguf b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q5_K_S.gguf new file mode 100644 index 0000000..6e023a4 --- /dev/null +++ b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd8fcca60e76564f84de4a993a632b4c2251db8c08352b4036978adc4b2cf4df +size 5599299616 diff --git a/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q6_K.gguf b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q6_K.gguf new file mode 100644 index 0000000..2812201 --- /dev/null +++ b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2595b221e0640dafcbd2b4c0bb3927725db11cc4c3468d6f427dea29781ca815 +size 6596012064 diff --git a/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q8_0.gguf b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q8_0.gguf new file mode 100644 index 0000000..04801ca --- /dev/null +++ b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbb9a5e9af485f0bd1c3352f167e3bfbd0cb3e2accbddaab996e719efa474715 +size 8540776480 diff --git a/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.f16.gguf b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.f16.gguf new file mode 100644 index 0000000..af90057 --- /dev/null +++ b/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e209f7a9e2dace0afb0bb93cb2300755afb283e46574ceb7d0708cfa4d2f3e3 +size 16068896800 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ea9a34f --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: reedmayhew/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/reedmayhew/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF + + +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/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF-GGUF/resolve/main/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q2_K.gguf) | Q2_K | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF-GGUF/resolve/main/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q3_K_S.gguf) | Q3_K_S | 3.8 | | +| [GGUF](https://huggingface.co/mradermacher/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF-GGUF/resolve/main/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF-GGUF/resolve/main/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q3_K_L.gguf) | Q3_K_L | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF-GGUF/resolve/main/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.IQ4_XS.gguf) | IQ4_XS | 4.6 | | +| [GGUF](https://huggingface.co/mradermacher/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF-GGUF/resolve/main/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF-GGUF/resolve/main/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF-GGUF/resolve/main/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q5_K_S.gguf) | Q5_K_S | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF-GGUF/resolve/main/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q5_K_M.gguf) | Q5_K_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF-GGUF/resolve/main/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q6_K.gguf) | Q6_K | 6.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF-GGUF/resolve/main/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF-GGUF/resolve/main/HealthCare-Reasoning-Assistant-Llama-3.1-8B-HF.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. + +