commit 4c646895bec5252f494d8d37eaec0c84a13eeb45 Author: ModelHub XC Date: Sun Aug 9 13:39:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/HuatuoGPT-3-8B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..96e1f47 --- /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 +HuatuoGPT-3-8B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT-3-8B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT-3-8B.f16.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT-3-8B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT-3-8B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT-3-8B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT-3-8B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT-3-8B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT-3-8B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT-3-8B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT-3-8B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HuatuoGPT-3-8B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/HuatuoGPT-3-8B.IQ4_XS.gguf b/HuatuoGPT-3-8B.IQ4_XS.gguf new file mode 100644 index 0000000..b6561b5 --- /dev/null +++ b/HuatuoGPT-3-8B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81307bdb7214ab8288b2e76204e29508eeddfa0f1dd666e31a8f9cb34638bec6 +size 4593297120 diff --git a/HuatuoGPT-3-8B.Q2_K.gguf b/HuatuoGPT-3-8B.Q2_K.gguf new file mode 100644 index 0000000..d093ce3 --- /dev/null +++ b/HuatuoGPT-3-8B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2671c78e6e36e6b982d5021525eab3259a276f57f633a352eab0ad71c42df452 +size 3281733344 diff --git a/HuatuoGPT-3-8B.Q3_K_L.gguf b/HuatuoGPT-3-8B.Q3_K_L.gguf new file mode 100644 index 0000000..0935570 --- /dev/null +++ b/HuatuoGPT-3-8B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdaccb21e68053b13857b74c3045cb74e0bbfc18b74ef7fd3dd4b494830d309f +size 4431394528 diff --git a/HuatuoGPT-3-8B.Q3_K_M.gguf b/HuatuoGPT-3-8B.Q3_K_M.gguf new file mode 100644 index 0000000..28e0e56 --- /dev/null +++ b/HuatuoGPT-3-8B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5abb6e69931c68da22854df88b95b1ed46860f98ab1f854e1d8d468f1248238a +size 4124161760 diff --git a/HuatuoGPT-3-8B.Q3_K_S.gguf b/HuatuoGPT-3-8B.Q3_K_S.gguf new file mode 100644 index 0000000..5172bdd --- /dev/null +++ b/HuatuoGPT-3-8B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20dda0182eb49065f3d23fe4d3c3cbc2cfb86ca02c4c70a048765265b88f79f2 +size 3769612000 diff --git a/HuatuoGPT-3-8B.Q4_K_M.gguf b/HuatuoGPT-3-8B.Q4_K_M.gguf new file mode 100644 index 0000000..1b9bff5 --- /dev/null +++ b/HuatuoGPT-3-8B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09b02b8142c6456a41c5e913b71258d32e6afe02bec831a31381e1e95b0add28 +size 5027784416 diff --git a/HuatuoGPT-3-8B.Q4_K_S.gguf b/HuatuoGPT-3-8B.Q4_K_S.gguf new file mode 100644 index 0000000..ba0cee3 --- /dev/null +++ b/HuatuoGPT-3-8B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b814d5eac3348e6b5396cb12009cc22bd90e20a4f77a16ad26ca9ff3c68adb5 +size 4802012896 diff --git a/HuatuoGPT-3-8B.Q5_K_M.gguf b/HuatuoGPT-3-8B.Q5_K_M.gguf new file mode 100644 index 0000000..582a21f --- /dev/null +++ b/HuatuoGPT-3-8B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b49a3a4e84053fcc9e53ef86c192b38958ad237a0ed521b0c923139e99f5e87 +size 5851113184 diff --git a/HuatuoGPT-3-8B.Q5_K_S.gguf b/HuatuoGPT-3-8B.Q5_K_S.gguf new file mode 100644 index 0000000..244d8b6 --- /dev/null +++ b/HuatuoGPT-3-8B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9da497c6510ce75e69ea04fbccf9399113ad6be90a7d86f9aa9ff7278943db24 +size 5720762080 diff --git a/HuatuoGPT-3-8B.Q6_K.gguf b/HuatuoGPT-3-8B.Q6_K.gguf new file mode 100644 index 0000000..46cbb1d --- /dev/null +++ b/HuatuoGPT-3-8B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b13fbc20b0ecd435b706f606a2c5ffa62bee6fb889bc9b4f494e3c717d984235 +size 6725900000 diff --git a/HuatuoGPT-3-8B.Q8_0.gguf b/HuatuoGPT-3-8B.Q8_0.gguf new file mode 100644 index 0000000..b2659f4 --- /dev/null +++ b/HuatuoGPT-3-8B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62ba27b0d230f366b5048992318bc93457c107daef5e4a4e218496d8c267061f +size 8709519072 diff --git a/HuatuoGPT-3-8B.f16.gguf b/HuatuoGPT-3-8B.f16.gguf new file mode 100644 index 0000000..8cdac3b --- /dev/null +++ b/HuatuoGPT-3-8B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34cb0c375abefa371220121948611f625fbe726cd7ee99a34ba7fa0009dc9ca7 +size 16388044512 diff --git a/README.md b/README.md new file mode 100644 index 0000000..01d819f --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: FreedomIntelligence/HuatuoGPT-3-8B +language: +- en +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- medical +- reasoning +--- +## About + + + + + + + + + +static quants of https://huggingface.co/FreedomIntelligence/HuatuoGPT-3-8B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#HuatuoGPT-3-8B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/HuatuoGPT-3-8B-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/HuatuoGPT-3-8B-GGUF/resolve/main/HuatuoGPT-3-8B.Q2_K.gguf) | Q2_K | 3.4 | | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT-3-8B-GGUF/resolve/main/HuatuoGPT-3-8B.Q3_K_S.gguf) | Q3_K_S | 3.9 | | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT-3-8B-GGUF/resolve/main/HuatuoGPT-3-8B.Q3_K_M.gguf) | Q3_K_M | 4.2 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT-3-8B-GGUF/resolve/main/HuatuoGPT-3-8B.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT-3-8B-GGUF/resolve/main/HuatuoGPT-3-8B.IQ4_XS.gguf) | IQ4_XS | 4.7 | | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT-3-8B-GGUF/resolve/main/HuatuoGPT-3-8B.Q4_K_S.gguf) | Q4_K_S | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT-3-8B-GGUF/resolve/main/HuatuoGPT-3-8B.Q4_K_M.gguf) | Q4_K_M | 5.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT-3-8B-GGUF/resolve/main/HuatuoGPT-3-8B.Q5_K_S.gguf) | Q5_K_S | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT-3-8B-GGUF/resolve/main/HuatuoGPT-3-8B.Q5_K_M.gguf) | Q5_K_M | 6.0 | | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT-3-8B-GGUF/resolve/main/HuatuoGPT-3-8B.Q6_K.gguf) | Q6_K | 6.8 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT-3-8B-GGUF/resolve/main/HuatuoGPT-3-8B.Q8_0.gguf) | Q8_0 | 8.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/HuatuoGPT-3-8B-GGUF/resolve/main/HuatuoGPT-3-8B.f16.gguf) | f16 | 16.5 | 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. + +