commit 36f6adaf29b9280eeddaed528ade08c3b487ccde Author: ModelHub XC Date: Tue Sep 8 02:28:15 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Medictron-0.5B-Chat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9c8edeb --- /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 +Medictron-0.5B-Chat.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Medictron-0.5B-Chat.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Medictron-0.5B-Chat.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Medictron-0.5B-Chat.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Medictron-0.5B-Chat.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Medictron-0.5B-Chat.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Medictron-0.5B-Chat.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Medictron-0.5B-Chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Medictron-0.5B-Chat.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Medictron-0.5B-Chat.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Medictron-0.5B-Chat.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Medictron-0.5B-Chat.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Medictron-0.5B-Chat.IQ4_XS.gguf b/Medictron-0.5B-Chat.IQ4_XS.gguf new file mode 100644 index 0000000..3c49ec5 --- /dev/null +++ b/Medictron-0.5B-Chat.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e457ea300bfadfd00a1a7cfb1f3d15783b68ee734aa45421e22657e78452d92 +size 299191968 diff --git a/Medictron-0.5B-Chat.Q2_K.gguf b/Medictron-0.5B-Chat.Q2_K.gguf new file mode 100644 index 0000000..e2dd367 --- /dev/null +++ b/Medictron-0.5B-Chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edd661737e0b0d89c3ee8cc46492858a67c6dba5cfeca804c09682b6acda1d9c +size 247361184 diff --git a/Medictron-0.5B-Chat.Q3_K_L.gguf b/Medictron-0.5B-Chat.Q3_K_L.gguf new file mode 100644 index 0000000..d1948c5 --- /dev/null +++ b/Medictron-0.5B-Chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce23c2ab827ba49cea3880505ab169c1727ac06c4caef77f45fa3bc956d3f962 +size 297348768 diff --git a/Medictron-0.5B-Chat.Q3_K_M.gguf b/Medictron-0.5B-Chat.Q3_K_M.gguf new file mode 100644 index 0000000..3eb434a --- /dev/null +++ b/Medictron-0.5B-Chat.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5db28d32123668203ce30516e27bb41a2bc3409a6cda7d611f91eff68656561 +size 283029152 diff --git a/Medictron-0.5B-Chat.Q3_K_S.gguf b/Medictron-0.5B-Chat.Q3_K_S.gguf new file mode 100644 index 0000000..47df075 --- /dev/null +++ b/Medictron-0.5B-Chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd4119a12467e2725bb69495cbe6641ec60658b627a8543cb6c55931a43d36ac +size 266530464 diff --git a/Medictron-0.5B-Chat.Q4_K_M.gguf b/Medictron-0.5B-Chat.Q4_K_M.gguf new file mode 100644 index 0000000..6dc748b --- /dev/null +++ b/Medictron-0.5B-Chat.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a339b3b9764babc2ac871ab00186cf41aefde1b2af31a4348cb2597786ef1c9 +size 319639200 diff --git a/Medictron-0.5B-Chat.Q4_K_S.gguf b/Medictron-0.5B-Chat.Q4_K_S.gguf new file mode 100644 index 0000000..c4083b2 --- /dev/null +++ b/Medictron-0.5B-Chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8d0353c4ff6d72d71be41ec5af7c3274370d55f6be7aa477f137d00bc8b4816 +size 309079712 diff --git a/Medictron-0.5B-Chat.Q5_K_M.gguf b/Medictron-0.5B-Chat.Q5_K_M.gguf new file mode 100644 index 0000000..fced812 --- /dev/null +++ b/Medictron-0.5B-Chat.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d99a58f833370c03ee268544cabe02687d01e51a0c7a5d55fd536d9d7a16ea6 +size 352276128 diff --git a/Medictron-0.5B-Chat.Q5_K_S.gguf b/Medictron-0.5B-Chat.Q5_K_S.gguf new file mode 100644 index 0000000..beda8e8 --- /dev/null +++ b/Medictron-0.5B-Chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab3d36462f27e6c59770b76ecb1ce85937dc91123d658ec20edf62e1bc75595b +size 346009248 diff --git a/Medictron-0.5B-Chat.Q6_K.gguf b/Medictron-0.5B-Chat.Q6_K.gguf new file mode 100644 index 0000000..8bb419c --- /dev/null +++ b/Medictron-0.5B-Chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab1890501443f0dc1927e848dcf0a189aef2be6f96401dad81a12b96dbcc811c +size 386952864 diff --git a/Medictron-0.5B-Chat.Q8_0.gguf b/Medictron-0.5B-Chat.Q8_0.gguf new file mode 100644 index 0000000..70128e4 --- /dev/null +++ b/Medictron-0.5B-Chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dff699e15ed55718529b736791ad0c0fe98cce01408fea2663cfacee9ad2646 +size 499294880 diff --git a/Medictron-0.5B-Chat.f16.gguf b/Medictron-0.5B-Chat.f16.gguf new file mode 100644 index 0000000..1d89911 --- /dev/null +++ b/Medictron-0.5B-Chat.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17bd46e2ecc8e35d1c20f311c2b8c36ea0c59eff6c1a127fcfa964d51a463f7b +size 934167200 diff --git a/README.md b/README.md new file mode 100644 index 0000000..3e903df --- /dev/null +++ b/README.md @@ -0,0 +1,65 @@ +--- +base_model: praveen-reddy/Medictron-0.5B-Chat +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: +- llama-factory +--- +## About + + + + + + +static quants of https://huggingface.co/praveen-reddy/Medictron-0.5B-Chat + + +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/Medictron-0.5B-Chat-GGUF/resolve/main/Medictron-0.5B-Chat.Q2_K.gguf) | Q2_K | 0.3 | | +| [GGUF](https://huggingface.co/mradermacher/Medictron-0.5B-Chat-GGUF/resolve/main/Medictron-0.5B-Chat.Q3_K_S.gguf) | Q3_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Medictron-0.5B-Chat-GGUF/resolve/main/Medictron-0.5B-Chat.Q3_K_M.gguf) | Q3_K_M | 0.4 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Medictron-0.5B-Chat-GGUF/resolve/main/Medictron-0.5B-Chat.Q3_K_L.gguf) | Q3_K_L | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Medictron-0.5B-Chat-GGUF/resolve/main/Medictron-0.5B-Chat.IQ4_XS.gguf) | IQ4_XS | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Medictron-0.5B-Chat-GGUF/resolve/main/Medictron-0.5B-Chat.Q4_K_S.gguf) | Q4_K_S | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Medictron-0.5B-Chat-GGUF/resolve/main/Medictron-0.5B-Chat.Q4_K_M.gguf) | Q4_K_M | 0.4 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Medictron-0.5B-Chat-GGUF/resolve/main/Medictron-0.5B-Chat.Q5_K_S.gguf) | Q5_K_S | 0.4 | | +| [GGUF](https://huggingface.co/mradermacher/Medictron-0.5B-Chat-GGUF/resolve/main/Medictron-0.5B-Chat.Q5_K_M.gguf) | Q5_K_M | 0.5 | | +| [GGUF](https://huggingface.co/mradermacher/Medictron-0.5B-Chat-GGUF/resolve/main/Medictron-0.5B-Chat.Q6_K.gguf) | Q6_K | 0.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Medictron-0.5B-Chat-GGUF/resolve/main/Medictron-0.5B-Chat.Q8_0.gguf) | Q8_0 | 0.6 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Medictron-0.5B-Chat-GGUF/resolve/main/Medictron-0.5B-Chat.f16.gguf) | f16 | 1.0 | 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. + +