commit 1c3b5aff6006a4caec2b98da4b15cb348ff7e8e3 Author: ModelHub XC Date: Sat Sep 5 18:54:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Phi-Stoma-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..9a692cf --- /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-Stoma.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Phi-Stoma.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-Stoma.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Phi-Stoma.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-Stoma.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-Stoma.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-Stoma.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-Stoma.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Phi-Stoma.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Phi-Stoma.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Phi-Stoma.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Phi-Stoma.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Phi-Stoma.IQ4_XS.gguf b/Phi-Stoma.IQ4_XS.gguf new file mode 100644 index 0000000..fb87be1 --- /dev/null +++ b/Phi-Stoma.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05bbfc845514597063a3172a5689ac0b0377bf737504e3a10f8e4a4bd8c1400c +size 4250010112 diff --git a/Phi-Stoma.Q2_K.gguf b/Phi-Stoma.Q2_K.gguf new file mode 100644 index 0000000..647a2b4 --- /dev/null +++ b/Phi-Stoma.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0f1e7d9920114137085db5d9779ae430c0aba3601ec069bfd1a957a2e875352 +size 3024077312 diff --git a/Phi-Stoma.Q3_K_L.gguf b/Phi-Stoma.Q3_K_L.gguf new file mode 100644 index 0000000..113d42d --- /dev/null +++ b/Phi-Stoma.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e3e035e94482611cb6f63bb61fec51e479f6764174ed33978bc93f8a72fd8f4 +size 4393984512 diff --git a/Phi-Stoma.Q3_K_M.gguf b/Phi-Stoma.Q3_K_M.gguf new file mode 100644 index 0000000..e965a72 --- /dev/null +++ b/Phi-Stoma.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94be8d713d9bb06bb846333484564caf96c40371cc324e93c1751d8741c755ff +size 3943424512 diff --git a/Phi-Stoma.Q3_K_S.gguf b/Phi-Stoma.Q3_K_S.gguf new file mode 100644 index 0000000..fb1af55 --- /dev/null +++ b/Phi-Stoma.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa9fdf0860d1e7a74aefa0b8059a9bfe77af2868f2c6c00c0565b0adfac6c3aa +size 3420774912 diff --git a/Phi-Stoma.Q4_K_M.gguf b/Phi-Stoma.Q4_K_M.gguf new file mode 100644 index 0000000..b52c9c8 --- /dev/null +++ b/Phi-Stoma.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f79479189d33e2d8425233c619883461472ff5bea2299192964df0d010eb5249 +size 4846387712 diff --git a/Phi-Stoma.Q4_K_S.gguf b/Phi-Stoma.Q4_K_S.gguf new file mode 100644 index 0000000..2f7f0a2 --- /dev/null +++ b/Phi-Stoma.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7646396d5ce7b2df5ebcd9925ea1f984d5011ce7fa45a5f19fc33fe50d33061a +size 4483482112 diff --git a/Phi-Stoma.Q5_K_M.gguf b/Phi-Stoma.Q5_K_M.gguf new file mode 100644 index 0000000..cf312b2 --- /dev/null +++ b/Phi-Stoma.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c70c5b6dc5637b24509ec00941bf8fd566d0f499a1ddae975961041d0f11ac9 +size 5609882112 diff --git a/Phi-Stoma.Q5_K_S.gguf b/Phi-Stoma.Q5_K_S.gguf new file mode 100644 index 0000000..e63e143 --- /dev/null +++ b/Phi-Stoma.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27b48c96bdc99f173e31e09bb1c25b7c54e5229b725e0fa5412573ab8770f166 +size 5400986112 diff --git a/Phi-Stoma.Q6_K.gguf b/Phi-Stoma.Q6_K.gguf new file mode 100644 index 0000000..c907540 --- /dev/null +++ b/Phi-Stoma.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ee08c623d579cd6263aac21938702834bc298f9228e94c1078cf2bb4eacdb9 +size 6421094912 diff --git a/Phi-Stoma.Q8_0.gguf b/Phi-Stoma.Q8_0.gguf new file mode 100644 index 0000000..7deaf3b --- /dev/null +++ b/Phi-Stoma.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f781d313a4b5d3e074d3e2f68412b726bf4c794589da52a9fe0dfb7177e764a +size 8313037312 diff --git a/Phi-Stoma.f16.gguf b/Phi-Stoma.f16.gguf new file mode 100644 index 0000000..151f1c9 --- /dev/null +++ b/Phi-Stoma.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1128305eafb80fd7bbd85beffc3d943c592e60f17a39abdebcceddc7ac5f5b94 +size 15636685312 diff --git a/README.md b/README.md new file mode 100644 index 0000000..ddd987b --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +base_model: Replete-AI/Phi-Stoma +language: +- en +library_name: transformers +license: mit +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/Replete-AI/Phi-Stoma + + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/Phi-Stoma-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-Stoma-GGUF/resolve/main/Phi-Stoma.Q2_K.gguf) | Q2_K | 3.1 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-Stoma-GGUF/resolve/main/Phi-Stoma.Q3_K_S.gguf) | Q3_K_S | 3.5 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-Stoma-GGUF/resolve/main/Phi-Stoma.Q3_K_M.gguf) | Q3_K_M | 4.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-Stoma-GGUF/resolve/main/Phi-Stoma.IQ4_XS.gguf) | IQ4_XS | 4.4 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-Stoma-GGUF/resolve/main/Phi-Stoma.Q3_K_L.gguf) | Q3_K_L | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-Stoma-GGUF/resolve/main/Phi-Stoma.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi-Stoma-GGUF/resolve/main/Phi-Stoma.Q4_K_M.gguf) | Q4_K_M | 4.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Phi-Stoma-GGUF/resolve/main/Phi-Stoma.Q5_K_S.gguf) | Q5_K_S | 5.5 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-Stoma-GGUF/resolve/main/Phi-Stoma.Q5_K_M.gguf) | Q5_K_M | 5.7 | | +| [GGUF](https://huggingface.co/mradermacher/Phi-Stoma-GGUF/resolve/main/Phi-Stoma.Q6_K.gguf) | Q6_K | 6.5 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-Stoma-GGUF/resolve/main/Phi-Stoma.Q8_0.gguf) | Q8_0 | 8.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Phi-Stoma-GGUF/resolve/main/Phi-Stoma.f16.gguf) | f16 | 15.7 | 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. + +