commit 3c2671230420efe3512e88c196cb225aae5d34bd Author: ModelHub XC Date: Tue Jun 2 06:18:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/InfiMed-SFT-3B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..62ae3f4 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +InfiMed-SFT-3B.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +InfiMed-SFT-3B.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +InfiMed-SFT-3B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +InfiMed-SFT-3B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +InfiMed-SFT-3B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +InfiMed-SFT-3B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InfiMed-SFT-3B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InfiMed-SFT-3B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InfiMed-SFT-3B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InfiMed-SFT-3B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +InfiMed-SFT-3B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +InfiMed-SFT-3B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +InfiMed-SFT-3B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +InfiMed-SFT-3B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/InfiMed-SFT-3B.IQ4_XS.gguf b/InfiMed-SFT-3B.IQ4_XS.gguf new file mode 100644 index 0000000..3d92827 --- /dev/null +++ b/InfiMed-SFT-3B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99d26468c0a3ce645f075b25fd0ca0f9a80d196f86f1ff7129da030df08d7b6e +size 1753185056 diff --git a/InfiMed-SFT-3B.Q2_K.gguf b/InfiMed-SFT-3B.Q2_K.gguf new file mode 100644 index 0000000..c2299ec --- /dev/null +++ b/InfiMed-SFT-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82174984a0ad7d502cfe6d902fbb8c74d25f0bdd382a7dc545aef88016266ad9 +size 1274755872 diff --git a/InfiMed-SFT-3B.Q3_K_L.gguf b/InfiMed-SFT-3B.Q3_K_L.gguf new file mode 100644 index 0000000..7aeedec --- /dev/null +++ b/InfiMed-SFT-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8aaaad097c4037fe192fb3862c9cc81efa82b934d6226a2d1d9dd93c59145d96 +size 1707391776 diff --git a/InfiMed-SFT-3B.Q3_K_M.gguf b/InfiMed-SFT-3B.Q3_K_M.gguf new file mode 100644 index 0000000..d9d0f86 --- /dev/null +++ b/InfiMed-SFT-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0fd4fabe8354b8ae1afc807d1d1cb32be392ddd2aa4b1fdca62496484add652 +size 1590475552 diff --git a/InfiMed-SFT-3B.Q3_K_S.gguf b/InfiMed-SFT-3B.Q3_K_S.gguf new file mode 100644 index 0000000..2ffc202 --- /dev/null +++ b/InfiMed-SFT-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa03c44ff716ccf080943fa075ca467226fece6974f34417d512d7715c34326e +size 1454357280 diff --git a/InfiMed-SFT-3B.Q4_K_M.gguf b/InfiMed-SFT-3B.Q4_K_M.gguf new file mode 100644 index 0000000..110860a --- /dev/null +++ b/InfiMed-SFT-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0a13d73addbebc1ccc9ec08b04b8dcc5405568d50aeb0113df0cfe559e45721 +size 1929902880 diff --git a/InfiMed-SFT-3B.Q4_K_S.gguf b/InfiMed-SFT-3B.Q4_K_S.gguf new file mode 100644 index 0000000..f81e448 --- /dev/null +++ b/InfiMed-SFT-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8da2ab891d8a48aa36137cf2ab93df6d5cb225fe867125c26955e8d7b52fa84 +size 1834384160 diff --git a/InfiMed-SFT-3B.Q5_K_M.gguf b/InfiMed-SFT-3B.Q5_K_M.gguf new file mode 100644 index 0000000..e1969ed --- /dev/null +++ b/InfiMed-SFT-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e5dbe77db98f0f4992db19e04bcf7e2cd6f28c106cbd1b6ead2992a464374e2 +size 2224814880 diff --git a/InfiMed-SFT-3B.Q5_K_S.gguf b/InfiMed-SFT-3B.Q5_K_S.gguf new file mode 100644 index 0000000..85314a8 --- /dev/null +++ b/InfiMed-SFT-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0ddb18bb5bafe0c8407fbe3ef3ed175e4bd047f7a7cb568411cff9427a2b07d +size 2169666336 diff --git a/InfiMed-SFT-3B.Q6_K.gguf b/InfiMed-SFT-3B.Q6_K.gguf new file mode 100644 index 0000000..f4ea9d0 --- /dev/null +++ b/InfiMed-SFT-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d74b1d142dc40098016cd1de885560328c46622dc590cc93c3dfdb4b95379323 +size 2538158880 diff --git a/InfiMed-SFT-3B.Q8_0.gguf b/InfiMed-SFT-3B.Q8_0.gguf new file mode 100644 index 0000000..665af79 --- /dev/null +++ b/InfiMed-SFT-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00d2259619b5d478757671829634139c5946c4afde074aa0be6128641afca26b +size 3285476128 diff --git a/InfiMed-SFT-3B.f16.gguf b/InfiMed-SFT-3B.f16.gguf new file mode 100644 index 0000000..b593837 --- /dev/null +++ b/InfiMed-SFT-3B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d10204fe57e0927971e57459470a85103be71d46824ed041dca384157c860906 +size 6178317088 diff --git a/InfiMed-SFT-3B.mmproj-Q8_0.gguf b/InfiMed-SFT-3B.mmproj-Q8_0.gguf new file mode 100644 index 0000000..11854b7 --- /dev/null +++ b/InfiMed-SFT-3B.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2851e1e03959ef5702219bc757a9593528426f7d07345e750091fdcd37da14bd +size 847768320 diff --git a/InfiMed-SFT-3B.mmproj-f16.gguf b/InfiMed-SFT-3B.mmproj-f16.gguf new file mode 100644 index 0000000..adc2229 --- /dev/null +++ b/InfiMed-SFT-3B.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeff085678e84156da7608c3f8021225c724be700c5302ed57d4ce652f3ccb63 +size 1338428160 diff --git a/README.md b/README.md new file mode 100644 index 0000000..0ee5670 --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: InfiX-ai/InfiMed-SFT-3B +language: +- en +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/InfiX-ai/InfiMed-SFT-3B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#InfiMed-SFT-3B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/InfiMed-SFT-3B-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/InfiMed-SFT-3B-GGUF/resolve/main/InfiMed-SFT-3B.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.9 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/InfiMed-SFT-3B-GGUF/resolve/main/InfiMed-SFT-3B.Q2_K.gguf) | Q2_K | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/InfiMed-SFT-3B-GGUF/resolve/main/InfiMed-SFT-3B.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/InfiMed-SFT-3B-GGUF/resolve/main/InfiMed-SFT-3B.Q3_K_S.gguf) | Q3_K_S | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/InfiMed-SFT-3B-GGUF/resolve/main/InfiMed-SFT-3B.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/InfiMed-SFT-3B-GGUF/resolve/main/InfiMed-SFT-3B.Q3_K_L.gguf) | Q3_K_L | 1.8 | | +| [GGUF](https://huggingface.co/mradermacher/InfiMed-SFT-3B-GGUF/resolve/main/InfiMed-SFT-3B.IQ4_XS.gguf) | IQ4_XS | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/InfiMed-SFT-3B-GGUF/resolve/main/InfiMed-SFT-3B.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InfiMed-SFT-3B-GGUF/resolve/main/InfiMed-SFT-3B.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/InfiMed-SFT-3B-GGUF/resolve/main/InfiMed-SFT-3B.Q5_K_S.gguf) | Q5_K_S | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/InfiMed-SFT-3B-GGUF/resolve/main/InfiMed-SFT-3B.Q5_K_M.gguf) | Q5_K_M | 2.3 | | +| [GGUF](https://huggingface.co/mradermacher/InfiMed-SFT-3B-GGUF/resolve/main/InfiMed-SFT-3B.Q6_K.gguf) | Q6_K | 2.6 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/InfiMed-SFT-3B-GGUF/resolve/main/InfiMed-SFT-3B.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/InfiMed-SFT-3B-GGUF/resolve/main/InfiMed-SFT-3B.f16.gguf) | f16 | 6.3 | 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. + +