commit b77a7d57c9d7de57aea35d6a6039d0eb76e76a4a Author: ModelHub XC Date: Mon Jun 15 18:38:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Chat-Doctor-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3ac5aca --- /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 +Chat-Doctor.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Chat-Doctor.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Chat-Doctor.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Chat-Doctor.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Chat-Doctor.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Chat-Doctor.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Chat-Doctor.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Chat-Doctor.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Chat-Doctor.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Chat-Doctor.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Chat-Doctor.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Chat-Doctor.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Chat-Doctor.IQ4_XS.gguf b/Chat-Doctor.IQ4_XS.gguf new file mode 100644 index 0000000..b95432b --- /dev/null +++ b/Chat-Doctor.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4866b4dbc290f0148c3155c8a3fed28c192b6c1af396d96087d0578b9275511 +size 351443488 diff --git a/Chat-Doctor.Q2_K.gguf b/Chat-Doctor.Q2_K.gguf new file mode 100644 index 0000000..c108464 --- /dev/null +++ b/Chat-Doctor.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64284f7087b8fb793e9aa41bc522b861b7a608a429933600698c78c324f958f0 +size 338605600 diff --git a/Chat-Doctor.Q3_K_L.gguf b/Chat-Doctor.Q3_K_L.gguf new file mode 100644 index 0000000..6cc7127 --- /dev/null +++ b/Chat-Doctor.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d8e0ff0de2cdf39be8beeb3eeb04c0db40be49c70a1d65c25ce60f44d4b72ec +size 369356320 diff --git a/Chat-Doctor.Q3_K_M.gguf b/Chat-Doctor.Q3_K_M.gguf new file mode 100644 index 0000000..3a55762 --- /dev/null +++ b/Chat-Doctor.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77a6fe38b16ab0ac01598e5971689be8a9138a21aa8396609310b623dafa655e +size 355464736 diff --git a/Chat-Doctor.Q3_K_S.gguf b/Chat-Doctor.Q3_K_S.gguf new file mode 100644 index 0000000..d84531d --- /dev/null +++ b/Chat-Doctor.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16be94daf1b2950c8bdadc5b91c329b2fbf0f1cc2266fca563030f54f0a86236 +size 338261536 diff --git a/Chat-Doctor.Q4_K_M.gguf b/Chat-Doctor.Q4_K_M.gguf new file mode 100644 index 0000000..f42744b --- /dev/null +++ b/Chat-Doctor.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53296238931e32e6b82e628f7293f3f2b268a38c047bedfff60d36b65c592157 +size 397806112 diff --git a/Chat-Doctor.Q4_K_S.gguf b/Chat-Doctor.Q4_K_S.gguf new file mode 100644 index 0000000..9469e4d --- /dev/null +++ b/Chat-Doctor.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04956d383104850970d44997ec9337057e94d970fbd5f641a05ae377688b83ae +size 385469984 diff --git a/Chat-Doctor.Q5_K_M.gguf b/Chat-Doctor.Q5_K_M.gguf new file mode 100644 index 0000000..9e29d5d --- /dev/null +++ b/Chat-Doctor.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8d0b14c72d8b23c85fad9a50db1e2ec027ad02f7e87c1f5755a2142d9f2e31a +size 420084256 diff --git a/Chat-Doctor.Q5_K_S.gguf b/Chat-Doctor.Q5_K_S.gguf new file mode 100644 index 0000000..277d258 --- /dev/null +++ b/Chat-Doctor.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47853e42072c9d6eb04dbe4ce6269bbf299a3a3a1ac3e02239ec320df73ab6cf +size 412708384 diff --git a/Chat-Doctor.Q6_K.gguf b/Chat-Doctor.Q6_K.gguf new file mode 100644 index 0000000..d008968 --- /dev/null +++ b/Chat-Doctor.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:748bc22a361f46857913dc8f39c04da163966511abb13e4dbe08f91ff17fe989 +size 505734688 diff --git a/Chat-Doctor.Q8_0.gguf b/Chat-Doctor.Q8_0.gguf new file mode 100644 index 0000000..049a6cc --- /dev/null +++ b/Chat-Doctor.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b8d5f5c33c083b854f068b9c3a994bf3c2664802bd33130498d1b87e809e174 +size 531066400 diff --git a/Chat-Doctor.f16.gguf b/Chat-Doctor.f16.gguf new file mode 100644 index 0000000..5ae81b1 --- /dev/null +++ b/Chat-Doctor.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:454d83bf53022c441001ac454f76d85931328ad309845909b07e3adc71f3bfd7 +size 994155040 diff --git a/README.md b/README.md new file mode 100644 index 0000000..dda947e --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: ar08/Chat-Doctor +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- text-generation-inference +- transformers +- unsloth +- qwen2 +- trl +- sft +--- +## About + + + + + + +static quants of https://huggingface.co/ar08/Chat-Doctor + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Chat-Doctor-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Chat-Doctor-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/Chat-Doctor-GGUF/resolve/main/Chat-Doctor.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Chat-Doctor-GGUF/resolve/main/Chat-Doctor.Q2_K.gguf) | Q2_K | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Chat-Doctor-GGUF/resolve/main/Chat-Doctor.IQ4_XS.gguf) | IQ4_XS | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Chat-Doctor-GGUF/resolve/main/Chat-Doctor.Q3_K_M.gguf) | Q3_K_M | 0.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Chat-Doctor-GGUF/resolve/main/Chat-Doctor.Q3_K_L.gguf) | Q3_K_L | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Chat-Doctor-GGUF/resolve/main/Chat-Doctor.Q4_K_S.gguf) | Q4_K_S | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Chat-Doctor-GGUF/resolve/main/Chat-Doctor.Q4_K_M.gguf) | Q4_K_M | 0.5 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Chat-Doctor-GGUF/resolve/main/Chat-Doctor.Q5_K_S.gguf) | Q5_K_S | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Chat-Doctor-GGUF/resolve/main/Chat-Doctor.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Chat-Doctor-GGUF/resolve/main/Chat-Doctor.Q6_K.gguf) | Q6_K | 0.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Chat-Doctor-GGUF/resolve/main/Chat-Doctor.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Chat-Doctor-GGUF/resolve/main/Chat-Doctor.f16.gguf) | f16 | 1.1 | 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. + +