commit 8a3627b073fbd238e0183579b8ebc9350aefd8ba Author: ModelHub XC Date: Fri Jul 17 22:13:10 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: sayhan/phi-2-super-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a3aff7e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.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-2-super.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +phi-2-super.fp16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..b76ac89 --- /dev/null +++ b/README.md @@ -0,0 +1,64 @@ +--- +license: mit +license_link: https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE +language: +- en +widget: +- text: Hello who are you? + example_title: Identity +- text: What can you do? + example_title: Capabilities +- text: Create a fastapi endpoint to retrieve the weather given a zip code. + example_title: Coding +tags: +- convAI +- conversational +pipeline_tag: text-generation +inference: false +--- + + +# Phi-2 Super (SFT + cDPO) +![image/png](https://cdn-uploads.huggingface.co/production/uploads/62ceeb27e7f6014c0e9d9268/5-LQCMrXi8FN_ewcWL47v.png) +- **Model creator:** [Anton Bacaj](https://huggingface.co/abacaj) +- **Original model:** [Phi-2 Super](https://huggingface.co/abacaj/phi-2-super) + +## Description +This repo contains GGUF format model files for [abacaj's Phi-2 Super](https://huggingface.co/abacaj/phi-2-super) + +## Quantization types +Since the model is relatively very small, I recommend the larger quantizations. + +| quantization method | bits |description | recommended | +|---------------------|------|-----------------------------------------------------|-------------| +| Q2_K | 2 |smallest, significant quality loss | ❌ | +| Q3_K_S | 3 |very small, high quality loss | ❌ | +| Q3_K_M | 3 | very small, high quality loss | ❌ | +| Q3_K_L | 3 |small, substantial quality loss | ❌ | +| Q4_0 | 4 | legacy; small, very high quality loss | ❌ | +| Q4_K_M | 4 | medium, balanced quality | ❌ | +| Q5_0 | 5 | legacy; medium, balanced quality | ❌ | +| Q5_K_S | 5 | large, low quality loss | ✅ | +| Q5_K_M | 5 | large, very low quality loss | ✅ | +| Q6_K | 6 | very large, extremely low quality loss | ❌ | +| Q8_0 | 8 | very large, extremely low quality loss | ❌ | +| FP16 | 16 | enormous, negligible quality loss | ❌ | +### Phi-2-super (SFT + cDPO) + +Base Model: [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) + +### Chat template + +The model uses the same chat template as found in Mistral instruct models: + +```python +text = "<|endoftext|>[INST] What is your favourite condiment? [/INST]" +"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!<|endoftext|> " +"[INST] Do you have mayonnaise recipes? [/INST]" +``` + +### MT-bench / heval + +![image/png](https://cdn-uploads.huggingface.co/production/uploads/62ceeb27e7f6014c0e9d9268/lnFu3x1ufdpQVysIrX4-G.png) +![image/png](https://cdn-uploads.huggingface.co/production/uploads/62ceeb27e7f6014c0e9d9268/mJfBpH8dIW7Ii2KAGI_A7.png) + \ No newline at end of file diff --git a/phi-2-super.Q2_K.gguf b/phi-2-super.Q2_K.gguf new file mode 100644 index 0000000..7cfeef2 --- /dev/null +++ b/phi-2-super.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ea04f2f720165733bc68e5916165535e33e0742b20b9800ebe09db4b895d7b5 +size 1109720160 diff --git a/phi-2-super.Q3_K_L.gguf b/phi-2-super.Q3_K_L.gguf new file mode 100644 index 0000000..60d36ef --- /dev/null +++ b/phi-2-super.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb1d9c26f02ae6a7c68f9f4aa0a4b7e142d96b67d1099ca3eb00e5606c0d5016 +size 1575230560 diff --git a/phi-2-super.Q3_K_M.gguf b/phi-2-super.Q3_K_M.gguf new file mode 100644 index 0000000..39c92da --- /dev/null +++ b/phi-2-super.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81d7e0ae03d9c7b3fb1c49165ab4e00d53f18ab55b0af97b04f0f27327a40326 +size 1432689760 diff --git a/phi-2-super.Q3_K_S.gguf b/phi-2-super.Q3_K_S.gguf new file mode 100644 index 0000000..0de0cc4 --- /dev/null +++ b/phi-2-super.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa655b9505a7a611a70ef77689ada5c94f97a56db3a6764fca98728c9141851d +size 1250827360 diff --git a/phi-2-super.Q4_0.gguf b/phi-2-super.Q4_0.gguf new file mode 100644 index 0000000..09dc8cc --- /dev/null +++ b/phi-2-super.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aae877554ec22cb6c195d17fb10f2977bc15e7ffa10da45feca6092fcd5cd987 +size 1602468960 diff --git a/phi-2-super.Q4_K_M.gguf b/phi-2-super.Q4_K_M.gguf new file mode 100644 index 0000000..67755dd --- /dev/null +++ b/phi-2-super.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a691ba06743e39b90f599e3879726534505ae6112cb77790d0d74597f8f0aa9 +size 1737636960 diff --git a/phi-2-super.Q4_K_S.gguf b/phi-2-super.Q4_K_S.gguf new file mode 100644 index 0000000..5878428 --- /dev/null +++ b/phi-2-super.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a1a02dd9daeadff34ddb77ad0b89857cdf23b54edb80cbc7e5597023a02de3a +size 1631960160 diff --git a/phi-2-super.Q5_0.gguf b/phi-2-super.Q5_0.gguf new file mode 100644 index 0000000..9b5bf18 --- /dev/null +++ b/phi-2-super.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4bd216439bbc070a475c9fcc7e863e4c12f289d062b42bbdc1df79cf76739d0 +size 1933425760 diff --git a/phi-2-super.Q5_K_M.gguf b/phi-2-super.Q5_K_M.gguf new file mode 100644 index 0000000..52cc5e3 --- /dev/null +++ b/phi-2-super.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac6cc5d70a64868cf0bd2b720d0c20489da5bf2115905a9956d544e9f2e62a19 +size 2003057760 diff --git a/phi-2-super.Q5_K_S.gguf b/phi-2-super.Q5_K_S.gguf new file mode 100644 index 0000000..eefac3a --- /dev/null +++ b/phi-2-super.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f524f0fcba30a8c4b3c12887ca7d7303043ddbdec4e43d0fb6cc0b24a985aa2c +size 1933425760 diff --git a/phi-2-super.Q6_K.gguf b/phi-2-super.Q6_K.gguf new file mode 100644 index 0000000..f1d947b --- /dev/null +++ b/phi-2-super.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ad453685505306cecb151fc673c67727733952f44de3451138ed799934cf834 +size 2285067360 diff --git a/phi-2-super.Q8_0.gguf b/phi-2-super.Q8_0.gguf new file mode 100644 index 0000000..f379eb4 --- /dev/null +++ b/phi-2-super.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8afb1ec7140a9b38684cc0c4509cffe275977489405f36c74a656f607d09b030 +size 2958040160 diff --git a/phi-2-super.fp16.gguf b/phi-2-super.fp16.gguf new file mode 100644 index 0000000..0fe0de1 --- /dev/null +++ b/phi-2-super.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b45094caadfd1447eb9e4cd0c54d5178b332e1d66872ec39fcdb0d293d4d866d +size 5563096128