commit 921407090e032b702abd1d597b76d1903f12d790 Author: ModelHub XC Date: Tue Aug 18 03:01:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Phi_medQuad_finetuned_model-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..8a140e3 --- /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 +Phi_medQuad_finetuned_model.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Phi_medQuad_finetuned_model.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi_medQuad_finetuned_model.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi_medQuad_finetuned_model.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi_medQuad_finetuned_model.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi_medQuad_finetuned_model.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi_medQuad_finetuned_model.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi_medQuad_finetuned_model.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi_medQuad_finetuned_model.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi_medQuad_finetuned_model.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi_medQuad_finetuned_model.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi_medQuad_finetuned_model.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Phi_medQuad_finetuned_model.IQ4_XS.gguf b/Phi_medQuad_finetuned_model.IQ4_XS.gguf new file mode 100644 index 0000000..bbcdbea --- /dev/null +++ b/Phi_medQuad_finetuned_model.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ff1d060e39aca8a511486aaf14a0cc2016d9a53fa714509334395816092520e +size 1536113920 diff --git a/Phi_medQuad_finetuned_model.Q2_K.gguf b/Phi_medQuad_finetuned_model.Q2_K.gguf new file mode 100644 index 0000000..fe94701 --- /dev/null +++ b/Phi_medQuad_finetuned_model.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab5ffad0650f3675b6c4da5eece1152041f5844436b1121286032b48507c5ea8 +size 1109720320 diff --git a/Phi_medQuad_finetuned_model.Q3_K_L.gguf b/Phi_medQuad_finetuned_model.Q3_K_L.gguf new file mode 100644 index 0000000..890e178 --- /dev/null +++ b/Phi_medQuad_finetuned_model.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:912bb452cf1cc13fea7096a3597c6c125bd05af5978ee20b773263a855041cb5 +size 1575230720 diff --git a/Phi_medQuad_finetuned_model.Q3_K_M.gguf b/Phi_medQuad_finetuned_model.Q3_K_M.gguf new file mode 100644 index 0000000..8b92741 --- /dev/null +++ b/Phi_medQuad_finetuned_model.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30272d43522452f11df634a016962abb99f250b0d63b99e6b4f558176ccdebfb +size 1426136320 diff --git a/Phi_medQuad_finetuned_model.Q3_K_S.gguf b/Phi_medQuad_finetuned_model.Q3_K_S.gguf new file mode 100644 index 0000000..75c2bb8 --- /dev/null +++ b/Phi_medQuad_finetuned_model.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deba9556c3bc32827fc4b8f58b691a9955985445283fbb1164ebd9bb6ab5f87a +size 1250827520 diff --git a/Phi_medQuad_finetuned_model.Q4_K_M.gguf b/Phi_medQuad_finetuned_model.Q4_K_M.gguf new file mode 100644 index 0000000..d6041ac --- /dev/null +++ b/Phi_medQuad_finetuned_model.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf6c2eb2244c978fe18c35f788f95ef2c42b3a1cc8747372892774283b875678 +size 1737637120 diff --git a/Phi_medQuad_finetuned_model.Q4_K_S.gguf b/Phi_medQuad_finetuned_model.Q4_K_S.gguf new file mode 100644 index 0000000..bb5fc7b --- /dev/null +++ b/Phi_medQuad_finetuned_model.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63c687f1236d2b6d19c8bce3774db6dd9d1eef107d71fa8df36df909b4f204c9 +size 1618853120 diff --git a/Phi_medQuad_finetuned_model.Q5_K_M.gguf b/Phi_medQuad_finetuned_model.Q5_K_M.gguf new file mode 100644 index 0000000..56a0517 --- /dev/null +++ b/Phi_medQuad_finetuned_model.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ae2f44b54add3bcaa7020df6f49a7286e0c214d0da628d2306a64ee5f64a539 +size 2003057920 diff --git a/Phi_medQuad_finetuned_model.Q5_K_S.gguf b/Phi_medQuad_finetuned_model.Q5_K_S.gguf new file mode 100644 index 0000000..286ec2a --- /dev/null +++ b/Phi_medQuad_finetuned_model.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48e6c60bf9a3f1a8e2f3eb71abf6dda1ef28a1f8b5673a38d288b72cfea0eaa2 +size 1933425920 diff --git a/Phi_medQuad_finetuned_model.Q6_K.gguf b/Phi_medQuad_finetuned_model.Q6_K.gguf new file mode 100644 index 0000000..f25b1e7 --- /dev/null +++ b/Phi_medQuad_finetuned_model.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:442acc3a05f8ca0618ee521fda1e8f6b9fc043c14bf95d15637db19308aa2a48 +size 2285067520 diff --git a/Phi_medQuad_finetuned_model.Q8_0.gguf b/Phi_medQuad_finetuned_model.Q8_0.gguf new file mode 100644 index 0000000..adb1295 --- /dev/null +++ b/Phi_medQuad_finetuned_model.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb83881eccb71a17f359ed89da56b77c4cdb817207f30b3626bbd5c15e7bf15f +size 2958040320 diff --git a/Phi_medQuad_finetuned_model.f16.gguf b/Phi_medQuad_finetuned_model.f16.gguf new file mode 100644 index 0000000..cbd4d4a --- /dev/null +++ b/Phi_medQuad_finetuned_model.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e77c84e0560adb36c2ea0089ccf64fb0ccc5867d9e58a3c377975506658d4c99 +size 5563096320 diff --git a/README.md b/README.md new file mode 100644 index 0000000..c392ca1 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: emilykang/Phi_medQuad_finetuned_model +language: +- en +library_name: transformers +quantized_by: mradermacher +tags: [] +--- +## About + + + + + + +static quants of https://huggingface.co/emilykang/Phi_medQuad_finetuned_model + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Phi_medQuad_finetuned_model-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/Phi_medQuad_finetuned_model-GGUF/resolve/main/Phi_medQuad_finetuned_model.Q2_K.gguf) | Q2_K | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Phi_medQuad_finetuned_model-GGUF/resolve/main/Phi_medQuad_finetuned_model.Q3_K_S.gguf) | Q3_K_S | 1.4 | | +| [GGUF](https://huggingface.co/mradermacher/Phi_medQuad_finetuned_model-GGUF/resolve/main/Phi_medQuad_finetuned_model.Q3_K_M.gguf) | Q3_K_M | 1.5 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Phi_medQuad_finetuned_model-GGUF/resolve/main/Phi_medQuad_finetuned_model.IQ4_XS.gguf) | IQ4_XS | 1.6 | | +| [GGUF](https://huggingface.co/mradermacher/Phi_medQuad_finetuned_model-GGUF/resolve/main/Phi_medQuad_finetuned_model.Q3_K_L.gguf) | Q3_K_L | 1.7 | | +| [GGUF](https://huggingface.co/mradermacher/Phi_medQuad_finetuned_model-GGUF/resolve/main/Phi_medQuad_finetuned_model.Q4_K_S.gguf) | Q4_K_S | 1.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi_medQuad_finetuned_model-GGUF/resolve/main/Phi_medQuad_finetuned_model.Q4_K_M.gguf) | Q4_K_M | 1.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi_medQuad_finetuned_model-GGUF/resolve/main/Phi_medQuad_finetuned_model.Q5_K_S.gguf) | Q5_K_S | 2.0 | | +| [GGUF](https://huggingface.co/mradermacher/Phi_medQuad_finetuned_model-GGUF/resolve/main/Phi_medQuad_finetuned_model.Q5_K_M.gguf) | Q5_K_M | 2.1 | | +| [GGUF](https://huggingface.co/mradermacher/Phi_medQuad_finetuned_model-GGUF/resolve/main/Phi_medQuad_finetuned_model.Q6_K.gguf) | Q6_K | 2.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Phi_medQuad_finetuned_model-GGUF/resolve/main/Phi_medQuad_finetuned_model.Q8_0.gguf) | Q8_0 | 3.1 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Phi_medQuad_finetuned_model-GGUF/resolve/main/Phi_medQuad_finetuned_model.f16.gguf) | f16 | 5.7 | 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. + +