初始化项目，由ModelHub XC社区提供模型

Model: Mungert/Phi-4-mini-instruct.gguf
Source: Original Platform

.gitattributes

@@ -0,0 +1,74 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+ 
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm 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-q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-iq2_s.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-bf16.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-iq3_s.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-bf16-q8.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-iq2_xs.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-tq2_0.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-q4_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-q3_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-tq1_0.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-iq2_m.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-q8.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-q6_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-q5_k_s.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-iq3_xs.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-iq4_nl.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-f16-q8.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-iq4_xs.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-q2_k_s.guuf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-q2_k_m.gguf filter=lfs diff=lfs merge=lfs -text
+phi-4-mini.imatrix filter=lfs diff=lfs merge=lfs -text
+phi-4-mini-iq3_m.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,232 @@
+---
+license: mit
+base_model:
+- microsoft/Phi-4-mini-instruct
+pipeline_tag: text-generation
+tags:
+- Demo
+- Phi 4 Mini
+- multilingual
+- reasoning
+- code generation
+- function calling
+- chat completion
+- memory efficient
+- low latency
+- 128k context
+---
+
+# Model Summary
+ 
+Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4 model family and supports 128K token context length. The model underwent an enhancement process, incorporating both supervised fine-tuning and direct preference optimization to support precise instruction adherence and robust safety measures.
+ 
+📰 [Phi-4-mini Microsoft Blog](https://aka.ms/phi4-feb2025) <br>
+📖 [Phi-4-mini Technical Report](https://aka.ms/phi-4-multimodal/techreport) <br>
+👩‍🍳 [Phi Cookbook](https://github.com/microsoft/PhiCookBook) <br>
+🏡 [Phi Portal](https://azure.microsoft.com/en-us/products/phi) <br>
+🖥️ Try It [Azure](https://aka.ms/phi-4-mini/azure), [Huggingface](https://huggingface.co/spaces/microsoft/phi-4-mini) <br>
+ 
+**Phi-4**: 
+[[mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct) | [onnx](https://huggingface.co/microsoft/Phi-4-mini-instruct-onnx)];
+[multimodal-instruct](https://huggingface.co/microsoft/Phi-4-multimodal-instruct); [gguf](https://huggingface.co/Mungert/Phi-4-mini-instruct.gguf)
+
+## Usage
+ 
+ 
+### Chat format
+ 
+This format is used for general conversation and instructions:
+ 
+```yaml
+<|system|>Insert System Message<|end|><|user|>Insert User Message<|end|><|assistant|>
+```
+ 
+### Tool-Enabled Function-Calling Format
+
+This format is used when the user wants the model to provide function calls based on the given tools. The user should define the available tools in the system prompt, wrapped by `<|tool|>` and `<|/tool|>` tokens. The tools must be specified in JSON format using a structured JSON dump.
+
+
+```plaintext
+<|system|>
+You are a helpful assistant with some tools.
+<|tool|>
+[
+  {
+    "name": "get_weather_updates",
+    "description": "Fetches weather updates for a given city using the RapidAPI Weather API.",
+    "parameters": {
+      "city": {
+        "description": "The name of the city for which to retrieve weather information.",
+        "type": "str",
+        "default": "London"
+      }
+    }
+  }
+]
+<|/tool|>
+<|end|>
+
+<|user|>
+What is the weather like in Paris today?
+<|end|>
+
+<|assistant|>
+```
+
+
+---
+
+# <span style="color: #FF7F7F;">Unsloth Bug Fixes for Better Performance</span>
+
+***Update (March 1, 2025)***   
+
+Applying all [Unsloth](https://huggingface.co/unsloth) fixes improved inference stability.
+
+| #  | Fix | Reason for Fix |
+|----|--------------------------------------------------|------------------------------------------------|
+| 1  | Changed the padding tag                         | The old padding tag could cause training issues. |
+| 2  | Removed `{% else %}{{ eos_token }}` from chat template | Prevented extra EOS tokens that could degrade inference performance. |
+| 3  | Replaced EOS with <\|end\|>               | Avoided potential inference glitches. |
+| 4  | Changed `unk_token` from EOS to `<60>`            | Stopped unknown tokens from breaking inference. |
+
+
+# <span id="testllm" style="color: #7F7FFF;">🚀 Phi 4 Mini Function Calling Test!</span>
+
+If you have a minute, I’d really appreciate it if you could test my Phi-4-Mini-Instruct Demo at 👉 [Quantum Network Monitor](https://readyforquantum.com).  
+💬 Click the **chat icon** (bottom right of the main and dashboard pages) . Then toggle between the LLM Types Phi-4-Mini-Instruct is called TestLLM : TurboLLM -> FreeLLM -> TestLLM.  
+
+### What I'm Testing 
+I'm experimenting with **function calling** against my network monitoring service. Using small open source models. I am into the question "How small can it go and still function". 
+🟡 **TestLLM** – Runs **Phi-4-mini-instruct** using phi-4-mini-q4_0.gguf , llama.cpp on 6 threads of a Cpu VM (Should take about 15s to load. Inference speed is quite slow and it only processes one user prompt at a time—still working on scaling!). If you're curious, I'd be happy to share how it works! .  
+
+### The other Available AI Assistants
+🟢 **TurboLLM** – Uses **gpt-4o-mini** Fast! . Note: tokens are limited since OpenAI models are pricey, but you can [Login](https://readyforquantum.com) or [Download](https://readyforquantum.com/download/?utm_source=huggingface&utm_medium=referral&utm_campaign=huggingface_repo_readme) the Quantum Network Monitor agent to get more tokens, Alternatively use the TestLLM .  
+🔵 **HugLLM** – Runs **open-source Hugging Face models** Fast, Runs small models (≈8B) hence lower quality, Get 2x more tokens (subject to Hugging Face API availability)  
+
+
+
+
+# <span style="color: #7FFF7F;">Phi-4-mini-instruct GGUF Models</span>
+
+
+## **Choosing the Right Model Format**  
+
+Selecting the correct model format depends on your **hardware capabilities** and **memory constraints**.  
+
+### **BF16 (Brain Float 16) – Use if BF16 acceleration is available**  
+- A 16-bit floating-point format designed for **faster computation** while retaining good precision.  
+- Provides **similar dynamic range** as FP32 but with **lower memory usage**.  
+- Recommended if your hardware supports **BF16 acceleration** (check your device’s specs).  
+- Ideal for **high-performance inference** with **reduced memory footprint** compared to FP32.  
+
+📌 **Use BF16 if:**  
+✔ Your hardware has native **BF16 support** (e.g., newer GPUs, TPUs).  
+✔ You want **higher precision** while saving memory.  
+✔ You plan to **requantize** the model into another format.  
+
+📌 **Avoid BF16 if:**  
+❌ Your hardware does **not** support BF16 (it may fall back to FP32 and run slower).  
+❌ You need compatibility with older devices that lack BF16 optimization.  
+
+---
+
+### **F16 (Float 16) – More widely supported than BF16**  
+- A 16-bit floating-point **high precision** but with less of range of values than BF16. 
+- Works on most devices with **FP16 acceleration support** (including many GPUs and some CPUs).  
+- Slightly lower numerical precision than BF16 but generally sufficient for inference.  
+
+📌 **Use F16 if:**  
+✔ Your hardware supports **FP16** but **not BF16**.  
+✔ You need a **balance between speed, memory usage, and accuracy**.  
+✔ You are running on a **GPU** or another device optimized for FP16 computations.  
+
+📌 **Avoid F16 if:**  
+❌ Your device lacks **native FP16 support** (it may run slower than expected).  
+❌ You have memory limtations.  
+
+---
+
+### **Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference**  
+Quantization reduces model size and memory usage while maintaining as much accuracy as possible.  
+- **Lower-bit models (Q4_K)** → **Best for minimal memory usage**, may have lower precision.  
+- **Higher-bit models (Q6_K, Q8_0)** → **Better accuracy**, requires more memory.  
+
+📌 **Use Quantized Models if:**  
+✔ You are running inference on a **CPU** and need an optimized model.  
+✔ Your device has **low VRAM** and cannot load full-precision models.  
+✔ You want to reduce **memory footprint** while keeping reasonable accuracy.  
+
+📌 **Avoid Quantized Models if:**  
+❌ You need **maximum accuracy** (full-precision models are better for this).  
+❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16).  
+
+---
+
+### **Summary Table: Model Format Selection**  
+
+| Model Format  | Precision  | Memory Usage  | Device Requirements  | Best Use Case  |  
+|--------------|------------|---------------|----------------------|---------------|  
+| **BF16**     | Highest       | High      | BF16-supported GPU/CPUs  | High-speed inference with reduced memory |  
+| **F16**      | High     | High           | FP16-supported devices | GPU inference when BF16 isn’t available |  
+| **Q4_K**     | Low        | Very Low      | CPU or Low-VRAM devices | Best for memory-constrained environments |  
+| **Q6_K**     | Medium Low     | Low      | CPU with more memory | Better accuracy while still being quantized |  
+| **Q8**       | Medium       | Moderate        | CPU or GPU with enough VRAM | Best accuracy among quantized models |  
+
+
+## **Included Files & Details**  
+
+### `phi-4-mini-bf16.gguf`  
+- Model weights preserved in **BF16**.  
+- Use this if you want to **requantize** the model into a different format.  
+- Best if your device supports **BF16 acceleration**.  
+
+### `phi-4-mini-f16.gguf`  
+- Model weights stored in **F16**.  
+- Use if your device supports **FP16**, especially if BF16 is not available.  
+
+### `phi-4-mini-bf16-q8.gguf`  
+- **Output & embeddings** remain in **BF16**.  
+- All other layers quantized to **Q8_0**.  
+- Use if your device supports **BF16** and you want a quantized version.  
+
+### `phi-4-mini-f16-q8.gguf`  
+- **Output & embeddings** remain in **F16**.  
+- All other layers quantized to **Q8_0**.    
+
+### `phi-4-mini-q4_k_l.gguf`  
+- **Output & embeddings** quantized to **Q8_0**.  
+- All other layers quantized to **Q4_K**.  
+- Good for **CPU inference** with limited memory.  
+
+### `phi-4-mini-q4_k_m.gguf`  
+- Similar to Q4_K.  
+- Another option for **low-memory CPU inference**.  
+
+### `phi-4-mini-q4_k_s.gguf`  
+- Smallest **Q4_K** variant, using less memory at the cost of accuracy.  
+- Best for **very low-memory setups**.  
+
+### `phi-4-mini-q6_k_l.gguf`  
+- **Output & embeddings** quantized to **Q8_0**.  
+- All other layers quantized to **Q6_K** .  
+
+### `phi-4-mini-q6_k_m.gguf`  
+- A mid-range **Q6_K** quantized model for balanced performance .  
+- Suitable for **CPU-based inference** with **moderate memory**.  
+
+### `phi-4-mini-q8.gguf`  
+- Fully **Q8** quantized model for better accuracy.  
+- Requires **more memory** but offers higher precision.
+
+
+
+## Credits
+
+Thanks [Bartowski](https://huggingface.co/bartowski) for imartix upload. And your guidance on quantization that has enabled me to produce these gguf file.
+
+Thanks [Unsloth](https://huggingface.co/unsloth) for bug fixing many models.
+
+
+
+
+Thanks for your support! 🙌

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

phi-4-mini-bf16-q8.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d70865878dd43c49f16a1275a65390059a497a6ad94d97722acbe19af64e4045
+size 4660796064

phi-4-mini-bf16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:811da09fc2630c2cb5128c9172fb69a7c9c16a6e8df1b4882fcff9843a4306d4
+size 7680694688

phi-4-mini-f16-q8.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab6a61d50cb8d796c9b31e3ec5ddb17d41a0881154a907498304435885f82487
+size 4660796064

phi-4-mini-iq2_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:264dc9c362d5fa1e274d707addfda9d7055d9109d6f8568bcf77565f7ac0e6ba
+size 1507424928

phi-4-mini-iq2_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e88713883a1be4544387f094bc7937be5aa8c031967d08508350f29d3d76009b
+size 1419344544

phi-4-mini-iq2_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3901070d71ae92241820d27d96c94bbe6be16ec38412d1a7efcbc769831802f1
+size 1366653600

phi-4-mini-iq3_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a30357660f3eea354b4c8a5422fc14226773402253b76b6a79ddc0f680e9331
+size 2017656480

phi-4-mini-iq3_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4274314d7143596a6e2aa8401c5f23eead566853f3e302649a7325202168528
+size 1897332384

phi-4-mini-iq3_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d75696c295ef933f7f77d3f29edd027872b9d6f30e6cc453c1e60526f2483fe
+size 1840709280

phi-4-mini-iq4_nl.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ae6b40d98006d8998525796f55b82031a77c3895cb1634dd95591574749c49
+size 2325151392

phi-4-mini-iq4_xs.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fc0af3fab6254a76b9447496cf11b887361f68e475101a271c9f87fab079307
+size 2224488096

phi-4-mini-q2_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40755c670c48e35f361d51ae195326f5e3bfc798e881e81375ebbfac89fbc9d3
+size 1682636352

phi-4-mini-q2_k_s.guuf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70a5b134185fb91fe8a0e1afbb8ee0a73dc96e64c5af1c17e6dfe7ba6e8250ef
+size 1593769632

phi-4-mini-q3_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e9443091c7789d9e5e7c337919f805c82c123a4d939c9f650cd761863b9c391
+size 2117533344

phi-4-mini-q3_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cfd425bc628f47232f55ab82ec4dac59d613321308bb1098448eebcc8bd2002
+size 1897332384

phi-4-mini-q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7057985d67935b25eda8c8faf69067175969c38f524b910e3423c8527551e57c
+size 2473999008

phi-4-mini-q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30a45c474106e9774dbd2e0d4af2496b3d71066937c8fd47d78a327a0ce6db72
+size 2675325600

phi-4-mini-q4_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be9eb0e3e0334344700ebeb8c07b1576dbf67e337f1b20a5d2a4fb061f0d76eb
+size 2491874976

phi-4-mini-q4_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c58af3a619c69f8bb0c6be5682128b5ddafaf6f71e0aa1c5cd0651670cea62af
+size 2337734304

phi-4-mini-q5_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66d1d47b19dc1ec07bb757cad87eba70dac6f894fe5a90c60858af0de65d9306
+size 2848128672

phi-4-mini-q5_k_s.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e4a6ae1e76744e51337b827d9b494b09a3e971d7041cc6ff9c78f7309054623
+size 2727804576

phi-4-mini-q6_k_m.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4bf2030f3a669ed2f8ed85e718a70ecad349f6f7d561b148724f28319e5f6ba
+size 3155623584

phi-4-mini-q8.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7532d384576e9dbe39852a3f4bc397a7abca99b6bef6b7611fdc8cddf7a60f19
+size 4084611488

phi-4-mini-tq1_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:544bcbc19af0888b83be97d429961a085e2252251e7ea50752e1f4d433bd1c66
+size 1192689312

phi-4-mini-tq2_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe13881efb1e54b58eb32e9dadf722a6a7d3a124f0271acd160f088cb6b9cac
+size 1343684256

phi-4-mini.imatrix

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be45717d26324e46f8bba4bc2badd89e7005bb2d6ddb8330749208b992f8ad40
+size 2232616