初始化项目，由ModelHub XC社区提供模型

Model: second-state/Phi-4-mini-reasoning-GGUF Source: Original Platform
2026-06-16 17:16:24 +08:00
commit a1193d64c4
16 changed files with 307 additions and 0 deletions
--- a/.gitattributes
+++ 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-4-mini-reasoning-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Phi-4-mini-reasoning-f16.gguf filter=lfs diff=lfs merge=lfs -text
--- a/Phi-4-mini-reasoning-Q2_K.gguf
+++ b/Phi-4-mini-reasoning-Q2_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20acd09ffeca78664d760b259338a2da6a6e488ba12eff9f6a8f20d32fdcaeb5
+size 1682636032
--- a/Phi-4-mini-reasoning-Q3_K_L.gguf
+++ b/Phi-4-mini-reasoning-Q3_K_L.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ecb08bf01dd2eca699018f72e356da18114b1ee71a896c0ed1480370d33ef5b
+size 2249653504
--- a/Phi-4-mini-reasoning-Q3_K_M.gguf
+++ b/Phi-4-mini-reasoning-Q3_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5daef984c39dfcde342bcf4bb0ee96b434a86d2ae1a6102d70b49028534f94e2
+size 2117532928
--- a/Phi-4-mini-reasoning-Q3_K_S.gguf
+++ b/Phi-4-mini-reasoning-Q3_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f7efed5d9574074697d2dde2024fc6bd8b251a458bfd3eb89fd267a86f38529
+size 1897331968
--- a/Phi-4-mini-reasoning-Q4_0.gguf
+++ b/Phi-4-mini-reasoning-Q4_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394a8b52b77b622e1771a4d3ed5536d813cf486d107c35b892361c18049829a3
+size 2325150976
--- a/Phi-4-mini-reasoning-Q4_K_M.gguf
+++ b/Phi-4-mini-reasoning-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba07818d4c81a29dc755825c7eb5fc025c2b287487d59063a16260197ea7694a
+size 2491874560
--- a/Phi-4-mini-reasoning-Q4_K_S.gguf
+++ b/Phi-4-mini-reasoning-Q4_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37c00c3b3e4a82b70e449883a07a0c5966950a9cd121a55b5cee6ce08ec3c8b3
+size 2337733888
--- a/Phi-4-mini-reasoning-Q5_0.gguf
+++ b/Phi-4-mini-reasoning-Q5_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2f3a2e3dd0b4fd837f9cd57430be341b17b64525cff557b155fd0d9b5d21748
+size 2727804160
--- a/Phi-4-mini-reasoning-Q5_K_M.gguf
+++ b/Phi-4-mini-reasoning-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1095c4697ca34cd105de2fcfdc7c4acde3020d7409255091111b7b3407f267c1
+size 2848128256
--- a/Phi-4-mini-reasoning-Q5_K_S.gguf
+++ b/Phi-4-mini-reasoning-Q5_K_S.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9405cabb92a2647d2f089b34286361dae709a995b6d18f3bc328b72ad0967b0e
+size 2727804160
--- a/Phi-4-mini-reasoning-Q6_K.gguf
+++ b/Phi-4-mini-reasoning-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ff4fba6515dd1a77a8d45f4f33e598a664c8fa7f57725ea9f194a23f440442d
+size 3155623168
--- a/Phi-4-mini-reasoning-Q8_0.gguf
+++ b/Phi-4-mini-reasoning-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d709abf9ba3ab5cab68aefc52688e2cd373866afacea22bcde8883a5b760acb7
+size 4084611328
--- a/Phi-4-mini-reasoning-f16.gguf
+++ b/Phi-4-mini-reasoning-f16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:600ab28baffdc1915c00da6ffb238519f32501766c3b219047d9f6cb67f0f83d
+size 7680694528
--- a/README.md
+++ b/README.md
@@ -0,0 +1,82 @@
+---
+license: mit
+license_link: https://huggingface.co/microsoft/Phi-4-mini-instruct-reasoning/resolve/main/LICENSE
+pipeline_tag: text-generation
+library_name: transformers
+model_creator: Microsoft
+model_name: Phi-4-mini-reasoning
+quantized_by: Second State Inc.
+language:
+- en
+---
+
+<!-- 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-mini-reasoning-GGUF
+
+## Original Model
+
+[microsoft/Phi-4-mini-reasoning](https://huggingface.co/microsoft/Phi-4-mini-reasoning)
+
+## Run with LlamaEdge
+
+- LlamaEdge version: coming soon
+
+<!-- - LlamaEdge version: [v0.16.9](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.16.9) and above -->
+
+- Prompt template
+
+  - Prompt type: `phi-4-chat`
+
+  - Prompt string
+
+    ```text
+    <|system|>Insert System Message<|end|><|user|>Insert User Message<|end|><|assistant|>
+    ```
+
+- Context size: `128000`
+
+- Run as LlamaEdge service
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-4-mini-reasoning-Q5_K_M.gguf \
+    llama-api-server.wasm \
+    --prompt-template phi-4-chat \
+    --ctx-size 128000 \
+    --model-name Phi-4-mini-reasoning
+  ```
+
+- Run as LlamaEdge command app
+
+  ```bash
+  wasmedge --dir .:. --nn-preload default:GGML:AUTO:Phi-4-mini-reasoning-Q5_K_M.gguf \
+    llama-chat.wasm \
+    --prompt-template phi-4-chat \
+    --ctx-size 128000
+  ```
+
+## Quantized GGUF Models
+
+| Name | Quant method | Bits | Size | Use case |
+| ---- | ---- | ---- | ---- | ----- |
+| [Phi-4-mini-reasoning-Q2_K.gguf](https://huggingface.co/second-state/Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q2_K.gguf)     | Q2_K   | 2 | 1.68 GB| smallest, significant quality loss - not recommended for most purposes |
+| [Phi-4-mini-reasoning-Q3_K_L.gguf](https://huggingface.co/second-state/Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q3_K_L.gguf) | Q3_K_L | 3 | 2.25 GB| small, substantial quality loss |
+| [Phi-4-mini-reasoning-Q3_K_M.gguf](https://huggingface.co/second-state/Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q3_K_M.gguf) | Q3_K_M | 3 | 2.12 GB| very small, high quality loss |
+| [Phi-4-mini-reasoning-Q3_K_S.gguf](https://huggingface.co/second-state/Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q3_K_S.gguf) | Q3_K_S | 3 | 1.90 GB| very small, high quality loss |
+| [Phi-4-mini-reasoning-Q4_0.gguf](https://huggingface.co/second-state/Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q4_0.gguf)     | Q4_0   | 4 | 2.33 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
+| [Phi-4-mini-reasoning-Q4_K_M.gguf](https://huggingface.co/second-state/Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q4_K_M.gguf) | Q4_K_M | 4 | 2.49 GB| medium, balanced quality - recommended |
+| [Phi-4-mini-reasoning-Q4_K_S.gguf](https://huggingface.co/second-state/Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q4_K_S.gguf) | Q4_K_S | 4 | 2.34 GB| small, greater quality loss |
+| [Phi-4-mini-reasoning-Q5_0.gguf](https://huggingface.co/second-state/Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q5_0.gguf)     | Q5_0   | 5 | 2.73 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
+| [Phi-4-mini-reasoning-Q5_K_M.gguf](https://huggingface.co/second-state/Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q5_K_M.gguf) | Q5_K_M | 5 | 2.85 GB| large, very low quality loss - recommended |
+| [Phi-4-mini-reasoning-Q5_K_S.gguf](https://huggingface.co/second-state/Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q5_K_S.gguf) | Q5_K_S | 5 | 2.73 GB| large, low quality loss - recommended |
+| [Phi-4-mini-reasoning-Q6_K.gguf](https://huggingface.co/second-state/Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q6_K.gguf)     | Q6_K   | 6 | 3.16 GB| very large, extremely low quality loss |
+| [Phi-4-mini-reasoning-Q8_0.gguf](https://huggingface.co/second-state/Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-Q8_0.gguf)     | Q8_0   | 8 | 4.08 GB| very large, extremely low quality loss - not recommended |
+| [Phi-4-mini-reasoning-f16.gguf](https://huggingface.co/second-state/Phi-4-mini-reasoning-GGUF/blob/main/Phi-4-mini-reasoning-f16.gguf)     | f16   | 16 | 7.68 GB|  |
+
+*Quantized with llama.cpp b5201.*
--- a/config.json
+++ b/config.json
@@ -0,0 +1,138 @@
+{
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 199999,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 199999,
+  "full_attn_mod": 1,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "interpolate_factor": 1,
+  "lm_head_bias": false,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "phi3",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 199999,
+  "partial_rotary_factor": 0.75,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1,
+      1.118320672,
+      1.250641126,
+      1.398617824,
+      1.564103225,
+      1.74916897,
+      1.956131817,
+      2.187582649,
+      2.446418898,
+      2.735880826,
+      3.059592084,
+      3.421605075,
+      3.826451687,
+      4.279200023,
+      4.785517845,
+      5.351743533,
+      5.984965424,
+      6.693110555,
+      7.485043894,
+      8.370679318,
+      9.36110372,
+      10.4687158,
+      11.70738129,
+      13.09260651,
+      14.64173252,
+      16.37415215,
+      18.31155283,
+      20.47818807,
+      22.90118105,
+      25.61086418,
+      28.64115884,
+      32.03,
+      32.1,
+      32.13,
+      32.23,
+      32.6,
+      32.61,
+      32.64,
+      32.66,
+      32.7,
+      32.71,
+      32.93,
+      32.97,
+      33.28,
+      33.49,
+      33.5,
+      44.16,
+      47.77
+    ],
+    "short_factor": [
+      1,
+      1.118320672,
+      1.250641126,
+      1.398617824,
+      1.564103225,
+      1.74916897,
+      1.956131817,
+      2.187582649,
+      2.446418898,
+      2.735880826,
+      3.059592084,
+      3.421605075,
+      3.826451687,
+      4.279200023,
+      4.785517845,
+      5.351743533,
+      5.984965424,
+      6.693110555,
+      7.485043894,
+      8.370679318,
+      9.36110372,
+      10.4687158,
+      11.70738129,
+      13.09260651,
+      14.64173252,
+      16.37415215,
+      18.31155283,
+      20.47818807,
+      22.90118105,
+      25.61086418,
+      28.64115884,
+      32.03,
+      32.1,
+      32.13,
+      32.23,
+      32.6,
+      32.61,
+      32.64,
+      32.66,
+      32.7,
+      32.71,
+      32.93,
+      32.97,
+      33.28,
+      33.49,
+      33.5,
+      44.16,
+      47.77
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0",
+  "use_cache": true,
+  "vocab_size": 200064
+}