Update README.md

README.md

@@ -1,4 +1,3 @@
-
 ---
 language:
 - zh
@@ -10,68 +9,42 @@ tags:
 - aviation
 - slm
 - mobile-ai
+- peft
 model_name: Language Dragon LoRA v1.1
-base_model: gpt2
+base_model: openai-community/gpt2
 pipeline_tag: text-generation
 library_name: peft
 ---
 
 # 🐉 Language Dragon LoRA (v1.1)
 
-> **"Powerful enough to lead. Small enough to hide."**
-
-Language Dragon is a high-precision **Small Language Model (SLM)** specialized for the aerospace industry and bilingual tasks (English & Chinese). While most models are "oceans," the Dragon is the **Changjiang**—deep, specialized, and essential for its niche.
+"Powerful enough to lead. Small enough to hide."
 
-Built on a **Microsoft Surface Pro (i5-10210U)**, it is optimized for "Edge AI" and local development where memory is at a premium.
+Language Dragon is a high-precision Small Language Model (SLM) specialized for the aerospace industry and bilingual tasks. Optimized for "Edge AI" on devices like the **Surface Pro (i5-10210U)**.
 
 ---
 
-## 🚀 The Roadmap to Blackwell Station
-We are currently destroying the "concrete wall" of hardware limitations. Every download and supporter brings us closer to the ultimate aviation training rig.
-
+## 🚀 Roadmap to the $5,000 Powerhouse (RTX 5090)
 | Goal | Reward Unlocked | Current Status |
 | :--- | :--- | :--- |
-| **50 Pilots** | Release detailed [J-20 vs. F-22] combat story sample. | **84% (42/50)** |
-| **500 Pilots** | Release "Language Dragon 7B" (Llama 3 base). | *Planned* |
-| **1,000 Pilots** | Fund the **RTX 5090**; Pre-orders open for "Pro" weights. | *The Target* |
-
----
-
-## 🛠️ Technical Specifications
-* **Base Model:** GPT-2 (124M)
-* **Adapter Type:** LoRA (Rank 16)
-* **Dataset:** TinyStories-ZH + Aviation-Expert Mix (Bilingual)
-* **Hardware Target:** Optimized for CPU inference and 4GB-8GB VRAM GPUs.
+| **50 Pilots** | Post detailed [J-20 vs. F-22] story sample. | **84% (42/50)** |
+| **500 Pilots** | Release the "Language Dragon 7B" (Llama 3 base). | *Planned* |
+| **1,000 Pilots** | Pre-orders open for the "Pro" 5090 Weights. | *Future* |
 
 ---
 
-## ⚠️ Critical Inference Settings
-Because this is a 124M parameter model, it requires specific **penalty guardrails** to prevent the "Repetition Loop" bug. Use the following parameters for the best flight experience:
+## 🧪 Test Flight (Python Sample)
+Run this directly on your CPU to see the Dragon in action:
 
 ```python
-# Recommended settings for Language Dragon:
-outputs = model.generate(
-    **inputs,
-    max_new_tokens=200, 
-    repetition_penalty=1.5,   # Prevents loops
-    no_repeat_ngram_size=3,   # Block 3-word repeats
-    temperature=0.4,          # Lower = More factual
-    top_p=0.9
-)
-#🧪 Quick Start (Test Flight)
-#Copy and paste this into your local environment to run the Dragon on your CPU:
-
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from peft import PeftModel
 
-# 1. Load the base engine
 model = AutoModelForCausalLM.from_pretrained("gpt2")
 tokenizer = AutoTokenizer.from_pretrained("gpt2")
-
-# 2. Snap on the Dragon Wings
 model = PeftModel.from_pretrained(model, "MightyDragon-Dev/language-dragon-lora")
 
-# 3. Ready for Takeoff
+# The Combat Alert Test:
 prompt = "歼-20 (Mighty Dragon) 在广东领空开启了加力燃烧室 (Afterburners)。由于 DSI 进气道的设计，它在超音速巡航时保持了极低的雷达散射截面 (RCS)。突然，预警机发出了警报"
 inputs = tokenizer(prompt, return_tensors="pt")