初始化项目，由ModelHub XC社区提供模型

Model: second-state/Phi-4-reasoning-plus-GGUF
Source: Original Platform

.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-4-reasoning-plus-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-reasoning-plus-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-reasoning-plus-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-reasoning-plus-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-reasoning-plus-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-reasoning-plus-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-reasoning-plus-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-reasoning-plus-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-reasoning-plus-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-reasoning-plus-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-reasoning-plus-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-reasoning-plus-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-reasoning-plus-f16.gguf filter=lfs diff=lfs merge=lfs -text

Phi-4-reasoning-plus-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:311d37b97747fc5dd328b201f2de2dcdfddce340f855ce067e40f181bfad672f
+size 5547349600

Phi-4-reasoning-plus-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cec10367ddac5c14c3583450513f1c831df7f7e1eae0041da55791bb7fc99e2
+size 7930156640

Phi-4-reasoning-plus-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d21935ce1ceb24d1a3c15da13f7fa50c17c607b675edc93cc10a194e78fc372
+size 7363270240

Phi-4-reasoning-plus-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1481ea7e8196d3390fb351957073b3f31fbb739c782091e03cc3af3d3168820c
+size 6504748640

Phi-4-reasoning-plus-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cd6c155a56e649153a98bfe867d640cd7bf6642a24b4d1c4f572382a3f8d94e
+size 8383420000

Phi-4-reasoning-plus-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78517dab46626dc6a1df8b8f90ed86fec08c968975088497e3b9ab355d9d1a6a
+size 9053116000

Phi-4-reasoning-plus-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a19573bd4ff24e9f73e51599fcf0012df3e411a65c124aefc91b42ab0b8aa69
+size 8440764000

Phi-4-reasoning-plus-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:044b88e3d9dcf9ff94d36c596f29dd0a4b5f979920637db10e6a71a075593eda
+size 10151581280

Phi-4-reasoning-plus-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ddade3041d12242dced4dce51c4e2be14b526a9660b4699d08a40f2cba6c7a8
+size 10604189280

Phi-4-reasoning-plus-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b11d3b35d39be1cd6019f74add9814507cf86d5d213f1090acdb6b8df0558b1a
+size 10151581280

Phi-4-reasoning-plus-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a224319dccffa0ec90feb2432ec73692e5db77fc48f277d1b43679b48e66fbd
+size 12030252640

Phi-4-reasoning-plus-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bff5f76ce1a359606f68d5aac10102c8e90b7f066476a3f83c463c2fbfc1b37
+size 15580501600

Phi-4-reasoning-plus-f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a3b8457d9f72cafe8abf00659d64e058cd48a8bc32066e970417cc3da9edf7
+size 29323400800

README.md

@@ -0,0 +1,88 @@
+---
+license: mit
+license_link: https://huggingface.co/microsoft/Phi-4-reasoning-plus-reasoning/resolve/main/LICENSE
+language:
+- en
+base_model:
+- microsoft/Phi-4-reasoning-plus
+pipeline_tag: text-generation
+library_name: transformers
+model_creator: Microsoft
+model_name: Phi-4-reasoning-plus
+quantized_by: Second State Inc.
+---
+
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+<img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+</div>
+<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
+<!-- header end -->
+
+# Phi-4-reasoning-plus-GGUF
+
+## Original Model
+
+[microsoft/Phi-4-reasoning-plus](https://huggingface.co/microsoft/Phi-4-reasoning-plus)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: coming soon
+
+<!-- - LlamaEdge version: [v0.16.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.0) and above -->
+
+- Prompt template
+
+  - Prompt type: `phi-4-chat`
+
+  - Prompt string
+
+    ```text
+    <|im_start|>system<|im_sep|>
+    {system_message}<|im_end|>
+    <|im_start|>user<|im_sep|>
+    {user_message}<|im_end|>
+    <|im_start|>assistant<|im_sep|>
+    ```
+
+- Context size: `32000`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-4-reasoning-plus-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --prompt-template phi-4-chat \
+    --ctx-size 32000 \
+    --model-name Phi-4-reasoning-plus
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-4-reasoning-plus-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template phi-4-chat \
+    --ctx-size 32000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Phi-4-reasoning-plus-Q2_K.gguf](https://huggingface.co/second-state/Phi-4-reasoning-plus-GGUF/blob/main/Phi-4-reasoning-plus-Q2_K.gguf)     | Q2_K   | 2 | 5.55 GB| smallest, significant quality loss - not recommended for most purposes |
+| [Phi-4-reasoning-plus-Q3_K_L.gguf](https://huggingface.co/second-state/Phi-4-reasoning-plus-GGUF/blob/main/Phi-4-reasoning-plus-Q3_K_L.gguf) | Q3_K_L | 3 | 7.93 GB| small, substantial quality loss |
+| [Phi-4-reasoning-plus-Q3_K_M.gguf](https://huggingface.co/second-state/Phi-4-reasoning-plus-GGUF/blob/main/Phi-4-reasoning-plus-Q3_K_M.gguf) | Q3_K_M | 3 | 7.36 GB| very small, high quality loss |
+| [Phi-4-reasoning-plus-Q3_K_S.gguf](https://huggingface.co/second-state/Phi-4-reasoning-plus-GGUF/blob/main/Phi-4-reasoning-plus-Q3_K_S.gguf) | Q3_K_S | 3 | 6.50 GB| very small, high quality loss |
+| [Phi-4-reasoning-plus-Q4_0.gguf](https://huggingface.co/second-state/Phi-4-reasoning-plus-GGUF/blob/main/Phi-4-reasoning-plus-Q4_0.gguf)     | Q4_0   | 4 | 8.38 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Phi-4-reasoning-plus-Q4_K_M.gguf](https://huggingface.co/second-state/Phi-4-reasoning-plus-GGUF/blob/main/Phi-4-reasoning-plus-Q4_K_M.gguf) | Q4_K_M | 4 | 9.05 GB| medium, balanced quality - recommended |
+| [Phi-4-reasoning-plus-Q4_K_S.gguf](https://huggingface.co/second-state/Phi-4-reasoning-plus-GGUF/blob/main/Phi-4-reasoning-plus-Q4_K_S.gguf) | Q4_K_S | 4 | 8.44 GB| small, greater quality loss |
+| [Phi-4-reasoning-plus-Q5_0.gguf](https://huggingface.co/second-state/Phi-4-reasoning-plus-GGUF/blob/main/Phi-4-reasoning-plus-Q5_0.gguf)     | Q5_0   | 5 | 10.2 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Phi-4-reasoning-plus-Q5_K_M.gguf](https://huggingface.co/second-state/Phi-4-reasoning-plus-GGUF/blob/main/Phi-4-reasoning-plus-Q5_K_M.gguf) | Q5_K_M | 5 | 10.6 GB| large, very low quality loss - recommended |
+| [Phi-4-reasoning-plus-Q5_K_S.gguf](https://huggingface.co/second-state/Phi-4-reasoning-plus-GGUF/blob/main/Phi-4-reasoning-plus-Q5_K_S.gguf) | Q5_K_S | 5 | 10.2 GB| large, low quality loss - recommended |
+| [Phi-4-reasoning-plus-Q6_K.gguf](https://huggingface.co/second-state/Phi-4-reasoning-plus-GGUF/blob/main/Phi-4-reasoning-plus-Q6_K.gguf)     | Q6_K   | 6 | 12.0 GB| very large, extremely low quality loss |
+| [Phi-4-reasoning-plus-Q8_0.gguf](https://huggingface.co/second-state/Phi-4-reasoning-plus-GGUF/blob/main/Phi-4-reasoning-plus-Q8_0.gguf)     | Q8_0   | 8 | 15.6 GB| very large, extremely low quality loss - not recommended |
+| [Phi-4-reasoning-plus-f16.gguf](https://huggingface.co/second-state/Phi-4-reasoning-plus-GGUF/blob/main/Phi-4-reasoning-plus-f16.gguf)       | f16   | 16 | 29.3 GB|  |
+
+*Quantized with llama.cpp b5201.*

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100265,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 32768,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 32768,
+  "pad_token_id": 100349,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.1",
+  "use_cache": true,
+  "vocab_size": 100352
+}