commit dea08992c8e78c3e1a546cfae6aad6d6b13264d8 Author: ModelHub XC Date: Sat May 16 02:15:57 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Llama-3.2-3b-finetune-radiology-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..bcce9d0 --- /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 +Llama-3.2-3b-finetune-radiology.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-finetune-radiology.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-finetune-radiology.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-finetune-radiology.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-finetune-radiology.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-finetune-radiology.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-finetune-radiology.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-finetune-radiology.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-finetune-radiology.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-finetune-radiology.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-finetune-radiology.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Llama-3.2-3b-finetune-radiology.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3b-finetune-radiology.IQ4_XS.gguf b/Llama-3.2-3b-finetune-radiology.IQ4_XS.gguf new file mode 100644 index 0000000..2f806fb --- /dev/null +++ b/Llama-3.2-3b-finetune-radiology.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48418bf5a923328b9a429e5ea7eac68664257c7f3d8be3d6a29123dca96b40cd +size 1840906784 diff --git a/Llama-3.2-3b-finetune-radiology.Q2_K.gguf b/Llama-3.2-3b-finetune-radiology.Q2_K.gguf new file mode 100644 index 0000000..46e5cbb --- /dev/null +++ b/Llama-3.2-3b-finetune-radiology.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e69a2b8882ce42e1ecc568718b7bc44fb75f211acad241909478b605bf2de60f +size 1363935776 diff --git a/Llama-3.2-3b-finetune-radiology.Q3_K_L.gguf b/Llama-3.2-3b-finetune-radiology.Q3_K_L.gguf new file mode 100644 index 0000000..8cce5df --- /dev/null +++ b/Llama-3.2-3b-finetune-radiology.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a95e6ac0ca6c4e5ed3ae9c587e45ab13682c93b2fb77bbeea2ec86b2ab44caf +size 1815347744 diff --git a/Llama-3.2-3b-finetune-radiology.Q3_K_M.gguf b/Llama-3.2-3b-finetune-radiology.Q3_K_M.gguf new file mode 100644 index 0000000..30f07b4 --- /dev/null +++ b/Llama-3.2-3b-finetune-radiology.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15e94bfa24de8371f0c5bc5513c4cd9bfd16bb41ae7ed4043bec7fcb253ac7d3 +size 1687159328 diff --git a/Llama-3.2-3b-finetune-radiology.Q3_K_S.gguf b/Llama-3.2-3b-finetune-radiology.Q3_K_S.gguf new file mode 100644 index 0000000..eaf837e --- /dev/null +++ b/Llama-3.2-3b-finetune-radiology.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0a001ea1480b8bb66ff8e2f008cb3627dd40230d6d2d8aae896419aaa29a1ef +size 1542849056 diff --git a/Llama-3.2-3b-finetune-radiology.Q4_K_M.gguf b/Llama-3.2-3b-finetune-radiology.Q4_K_M.gguf new file mode 100644 index 0000000..66607a9 --- /dev/null +++ b/Llama-3.2-3b-finetune-radiology.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87b5f72aa4c1ed7d922fff9324e71606a7148db1a28b4de1ab075cb190c47dae +size 2019377696 diff --git a/Llama-3.2-3b-finetune-radiology.Q4_K_S.gguf b/Llama-3.2-3b-finetune-radiology.Q4_K_S.gguf new file mode 100644 index 0000000..b9c3d1a --- /dev/null +++ b/Llama-3.2-3b-finetune-radiology.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de5ed5fa6a4d4cd9021b65b4c6e4218c2122b3a77e556c27401012f5d8a348ff +size 1928200736 diff --git a/Llama-3.2-3b-finetune-radiology.Q5_K_M.gguf b/Llama-3.2-3b-finetune-radiology.Q5_K_M.gguf new file mode 100644 index 0000000..9d8d3b5 --- /dev/null +++ b/Llama-3.2-3b-finetune-radiology.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d20cccfd8c50a77170bc306eafadac8abbcf39237f0de7682c05274f73a5d14 +size 2322154016 diff --git a/Llama-3.2-3b-finetune-radiology.Q5_K_S.gguf b/Llama-3.2-3b-finetune-radiology.Q5_K_S.gguf new file mode 100644 index 0000000..5b94dd3 --- /dev/null +++ b/Llama-3.2-3b-finetune-radiology.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b63084829a7022d7da876d617834b16336927949e51279862ff702ff97204cb5 +size 2269512224 diff --git a/Llama-3.2-3b-finetune-radiology.Q6_K.gguf b/Llama-3.2-3b-finetune-radiology.Q6_K.gguf new file mode 100644 index 0000000..1f685f5 --- /dev/null +++ b/Llama-3.2-3b-finetune-radiology.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73e779deb7bfc026e1d56b008518b2a979302287a30c921fe85b1cc671c29b23 +size 2643853856 diff --git a/Llama-3.2-3b-finetune-radiology.Q8_0.gguf b/Llama-3.2-3b-finetune-radiology.Q8_0.gguf new file mode 100644 index 0000000..bb7753a --- /dev/null +++ b/Llama-3.2-3b-finetune-radiology.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:caecd3a38b0025ae7e304a4b75d359d922cfefc6001392b8496ae9c33c2fc57d +size 3421899296 diff --git a/Llama-3.2-3b-finetune-radiology.f16.gguf b/Llama-3.2-3b-finetune-radiology.f16.gguf new file mode 100644 index 0000000..6332600 --- /dev/null +++ b/Llama-3.2-3b-finetune-radiology.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1003aafb98b4f252dfc80fc93e3fad13be9825a8b2a4ce1bdc00b47b9a2e2c2b +size 6433688096 diff --git a/README.md b/README.md new file mode 100644 index 0000000..2246655 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: chatsdude/Llama-3.2-3b-finetune-radiology +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/chatsdude/Llama-3.2-3b-finetune-radiology + + +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/Llama-3.2-3b-finetune-radiology-GGUF/resolve/main/Llama-3.2-3b-finetune-radiology.Q2_K.gguf) | Q2_K | 1.5 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-finetune-radiology-GGUF/resolve/main/Llama-3.2-3b-finetune-radiology.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-finetune-radiology-GGUF/resolve/main/Llama-3.2-3b-finetune-radiology.Q3_K_M.gguf) | Q3_K_M | 1.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-finetune-radiology-GGUF/resolve/main/Llama-3.2-3b-finetune-radiology.Q3_K_L.gguf) | Q3_K_L | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-finetune-radiology-GGUF/resolve/main/Llama-3.2-3b-finetune-radiology.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-finetune-radiology-GGUF/resolve/main/Llama-3.2-3b-finetune-radiology.Q4_K_S.gguf) | Q4_K_S | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-finetune-radiology-GGUF/resolve/main/Llama-3.2-3b-finetune-radiology.Q4_K_M.gguf) | Q4_K_M | 2.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-finetune-radiology-GGUF/resolve/main/Llama-3.2-3b-finetune-radiology.Q5_K_S.gguf) | Q5_K_S | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-finetune-radiology-GGUF/resolve/main/Llama-3.2-3b-finetune-radiology.Q5_K_M.gguf) | Q5_K_M | 2.4 | | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-finetune-radiology-GGUF/resolve/main/Llama-3.2-3b-finetune-radiology.Q6_K.gguf) | Q6_K | 2.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-finetune-radiology-GGUF/resolve/main/Llama-3.2-3b-finetune-radiology.Q8_0.gguf) | Q8_0 | 3.5 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Llama-3.2-3b-finetune-radiology-GGUF/resolve/main/Llama-3.2-3b-finetune-radiology.f16.gguf) | f16 | 6.5 | 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. + +