commit 908f12d12b2e5415479398f39e202cf70491f2e4
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Wed Apr 22 02:44:41 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: tokenaii/Horus-1.0-4B-GGUF
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..725feff
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,44 @@
+*.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
+Horus-1.0-4B-F16.gguf filter=lfs diff=lfs merge=lfs -text
+media/main.png filter=lfs diff=lfs merge=lfs -text
+Horus-1.0-4B-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Horus-1.0-4B-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Horus-1.0-4B-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Horus-1.0-4B-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+media/1.png filter=lfs diff=lfs merge=lfs -text
+media/2.png filter=lfs diff=lfs merge=lfs -text
+media/3.png filter=lfs diff=lfs merge=lfs -text
diff --git a/Horus-1.0-4B-F16.gguf b/Horus-1.0-4B-F16.gguf
new file mode 100644
index 0000000..4e33625
--- /dev/null
+++ b/Horus-1.0-4B-F16.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7fcaf86a54ec1e7f5e9bd0bddcffda42a48e38252df42fe2e3a300a00be303d
+size 9033728832
diff --git a/Horus-1.0-4B-Q4_K_M.gguf b/Horus-1.0-4B-Q4_K_M.gguf
new file mode 100644
index 0000000..bbdfdc0
--- /dev/null
+++ b/Horus-1.0-4B-Q4_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde6de087cfd697341a57117fba72add30c340c8b1524353ef00777dbcac5a47
+size 2778282816
diff --git a/Horus-1.0-4B-Q5_K_M.gguf b/Horus-1.0-4B-Q5_K_M.gguf
new file mode 100644
index 0000000..798e78f
--- /dev/null
+++ b/Horus-1.0-4B-Q5_K_M.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:681d2d481795d6519961b785401fbc3d9583480a20734b7e7e1596a4507986fd
+size 3230186304
diff --git a/Horus-1.0-4B-Q6_K.gguf b/Horus-1.0-4B-Q6_K.gguf
new file mode 100644
index 0000000..ec0ad8d
--- /dev/null
+++ b/Horus-1.0-4B-Q6_K.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91a17404bf62aa9fb4b28ce957a8248ff453fbb561c424a9186f68312ebcdcf7
+size 3710333760
diff --git a/Horus-1.0-4B-Q8_0.gguf b/Horus-1.0-4B-Q8_0.gguf
new file mode 100644
index 0000000..198e734
--- /dev/null
+++ b/Horus-1.0-4B-Q8_0.gguf
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4087c49b01e315e60716515646d342b26a51e2bf669e8f96a644d3577dcf43a
+size 4803216192
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..62ce8f3
--- /dev/null
+++ b/README.md
@@ -0,0 +1,222 @@
+---
+license: mit
+language:
+- ar
+- en
+- fr
+- es
+- de
+- it
+- pt
+- tr
+- ur
+- hi
+tags:
+- llama
+- llm
+- text-generation
+- multilingual
+- causal-lm
+- arabic
+- gguf
+- quantized
+- horus
+- tokenai
+- neuralnode
+- tts
+- voice
+base_model: tokenaii/horus
+widget:
+  - text: "### User:\nWhat is the capital of Egypt?\n\n### Assistant:\nThe capital of Egypt is Cairo."
+  - text: "### User:\nمن هو أول رئيس لمصر؟\n\n### Assistant:\nأول رئيس لمصر بعد ثورة 1952 هو محمد نجيب."
+  - text: "### User:\nHello Horus!\n\n### Assistant:\nHello! I'm Horus, an AI assistant developed by TokenAI. How can I help you today?"
+inference: true
+---
+
+# Hours-1.0-4B-GGUF
+
+![Horus Model](media/main.png)
+
+GGUF quantized versions of Horus-1.0-4B by TokenAI.
+
+## Base Model
+
+- **Source:** [tokenaii/horus](https://huggingface.co/tokenaii/horus)
+- **Original Model:** Horus-1.0-4B (4B parameters)
+- **Developer:** [Assem Sabry](https://assem.cloud/) & TokenAI
+- **Organization:** [TokenAI](https://tokenai.cloud/)
+- **Release Date:** April 2026
+- **License:** MIT
+
+## About TokenAI
+
+**TokenAI** is an AI startup founded by [Assem Sabry](https://assem.cloud/) with headquarters in Egypt.
+
+### Mission
+
+TokenAI aims to deliver the strongest language models in the world and in the Arab world through the Horus family of models. The startup bridges the gap between cutting-edge AI capabilities and regional cultural contexts, starting with the Arab world.
+
+### The Horus Family
+
+Horus-1.0-4B marks the **first model in the Horus family line**. This is just the beginning of TokenAI's journey to create a comprehensive suite of AI models serving the Arab region.
+
+# Horus-1.0-4B-GGUF
+ 
+GGUF quantized versions of Horus-1.0-4B - A 4B parameter multilingual language model optimized for Arabic and English.
+ 
+## Model Variants & Hardware Requirements
+ 
+| Format | File Size | Min RAM (CPU) | Min VRAM (GPU) | Quality | Best For |
+|--------|-----------|---------------|----------------|---------|----------|
+| **F16** | 9.03 GB | 12 GB | 10 GB | Maximum quality | High-end GPUs (RTX 3090, A100) |
+| **Q8_0** | 4.8 GB | 6 GB | 5 GB | Near-lossless | RTX 3060 12GB, RTX 4060 |
+| **Q6_K** | 3.71 GB | 5 GB | 4 GB | Excellent | RTX 3060, RTX 4060 Laptop |
+| **Q5_K_M** | 3.23 GB | 4 GB | 3.5 GB | Very Good | GTX 1650, RTX 3050 |
+| **Q4_K_M** | 2.78 GB | 3.5 GB | 3 GB | Good | Entry-level GPUs, CPU-only |
+ 
+### Detailed Hardware Requirements
+ 
+#### F16 (FP16 - Full Precision)
+- **File**: `Horus-1.0-4B-F16.gguf` (9.03 GB)
+- **Min System RAM**: 12 GB
+- **Min VRAM**: 10 GB
+- **Recommended**: RTX 3090, RTX 4090, A100, A6000
+- **Use Case**: Maximum quality, research, fine-tuning reference
+ 
+#### Q8_0 (8-bit Quantization)
+- **File**: `Horus-1.0-4B-Q8_0.gguf` (4.8 GB)
+- **Min System RAM**: 6 GB
+- **Min VRAM**: 5 GB
+- **Recommended**: RTX 3060 12GB, RTX 4060, RTX 4070
+- **Use Case**: Near-lossless quality with half the memory
+ 
+#### Q6_K (6-bit K-Quant)
+- **File**: `Horus-1.0-4B-Q6_K.gguf` (3.71 GB)
+- **Min System RAM**: 5 GB
+- **Min VRAM**: 4 GB
+- **Recommended**: RTX 3060, RTX 4060 Laptop, GTX 1080 Ti
+- **Use Case**: Excellent quality for most applications
+ 
+#### Q5_K_M (5-bit K-Quant Medium)
+- **File**: `Horus-1.0-4B-Q5_K_M.gguf` (3.23 GB)
+- **Min System RAM**: 4 GB
+- **Min VRAM**: 3.5 GB
+- **Recommended**: GTX 1650 Super, RTX 3050, RTX 3050 Ti
+- **Use Case**: Balanced quality and performance
+ 
+#### Q4_K_M (4-bit K-Quant Medium)
+- **File**: `Horus-1.0-4B-Q4_K_M.gguf` (2.78 GB)
+- **Min System RAM**: 3.5 GB
+- **Min VRAM**: 3 GB
+- **Recommended**: GTX 1060 6GB, GTX 1650, Intel Arc A380
+- **Use Case**: Maximum compression, edge devices, CPU inference
+
+## Quick Start
+
+### Using NeuralNode (Recommended)
+
+The easiest way to use Horus GGUF models is with the NeuralNode framework:
+
+```python
+import neuralnode as nn
+
+MODEL_ID = "tokenaii/Hours-1.0-4B-GGUF/Horus-1.0-4B-Q6_K.gguf"
+DEVICE = "cpu"  # Change to "cuda" for GPU acceleration
+
+# Download and load
+model = nn.HorusModel(MODEL_ID, device=DEVICE).load()
+
+# Use immediately
+response = model.chat([{"role": "user", "content": "hi horus im emy"}])
+print(response.content)
+```
+
+### Using llama-cpp-python
+
+For direct llama.cpp integration:
+
+```python
+from llama_cpp import Llama
+
+llm = Llama(
+    model_path="Horus-1.0-4B-Q4_K_M.gguf",
+    n_ctx=4096
+)
+
+output = llm("Hello, how are you?", max_tokens=256)
+print(output['choices'][0]['text'])
+```
+
+## Voice Interface with Replica TTS
+
+Add natural voice output to your Horus GGUF model with Replica TTS:
+
+```python
+import neuralnode as nn
+
+voice_id = "replica-aria-language{en-us}"
+
+MODEL_ID = "tokenaii/Hours-1.0-4B-GGUF/Horus-1.0-4B-F16.gguf"
+DEVICE = "cuda"
+
+# Load model with Replica TTS
+model = nn.HorusModel(
+    MODEL_ID,
+    tts_engine="replica_tts",
+    voice=voice_id,
+    device=DEVICE
+).load()
+
+# Chat and get spoken response
+response = model.chat([{"role": "user", "content": "Hello!"}])
+print(response.content)
+response.play_audio()  # Plays the TTS audio
+```
+
+### Browse All Voices
+
+```python
+import neuralnode as nn
+
+voices = nn.replica_voice_list()
+for voice in voices:
+    print(voice)
+```
+
+---
+
+## Benchmark Results
+
+Below are visual comparisons of Horus-1.0-4B against leading models.
+
+### General Knowledge & Reasoning
+![General Benchmarks](media/1.png)
+
+### Arabic Language & Cultural Benchmarks
+![Arabic Benchmarks](media/2.png)
+
+### Coding & Tool Use Benchmarks
+![Coding Benchmarks](media/3.png)
+
+---
+
+## Model Capabilities
+
+- **Multilingual:** Supports 10+ languages including Arabic, English, French, Spanish, German, Italian, Portuguese, Turkish, Urdu, Hindi
+- **Identity Recognition:** Knows itself as Horus from TokenAI
+- **Reasoning:** Chain-of-thought capabilities
+- **Context Length:** Up to 4096 tokens
+- **Voice Output:** Replica TTS integration for natural speech
+
+---
+
+## Links
+
+- **Base Model:** https://huggingface.co/tokenaii/horus
+- **TokenAI Website:** https://tokenai.cloud/
+- **Developer:** https://assem.cloud/
+- **GitHub:** https://github.com/tokenaii/horus-1.0
+
+---
+
+**Note:** Quantized using llama.cpp for efficient inference. GGUF versions are optimized for local deployment with minimal resource requirements.
diff --git a/media/1.png b/media/1.png
new file mode 100644
index 0000000..5265556
--- /dev/null
+++ b/media/1.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d29a11ba3de89c559fcbe4e5f9d5ed35781a50b689de45d29d48137fc723bfb
+size 496985
diff --git a/media/2.png b/media/2.png
new file mode 100644
index 0000000..900027e
--- /dev/null
+++ b/media/2.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e7b03f61fc258b17701f9f117eea42e0b5281bf48663900250bff00ffa9908d
+size 512627
diff --git a/media/3.png b/media/3.png
new file mode 100644
index 0000000..21cb971
--- /dev/null
+++ b/media/3.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fbea089f6acb95c4aa4c1cebbf8112855b97d45b56d94aa80de0f1736778caf
+size 508459
diff --git a/media/main.png b/media/main.png
new file mode 100644
index 0000000..8763229
--- /dev/null
+++ b/media/main.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:224d94528fcf373083cafea19a00fc193ee32857a69026d3bc5d9a8d9f65c183
+size 1238177