GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
muhammad-taqi512
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
muhammad-taqi512
Model Tree
Input Modalities
Output Modalities
Supported Functionality
muhammad-taqi512/LYRA"LYRA is designed as an autonomous, high-efficiency client-and-cloud native AI model engineered to deliver lightning-fast responses with precise ChatML structuring." — Muhammad Taqi
transformers Integration)Aap is model ko direct Muhammad Taqi's Hugging Face Repository se pull karke Python mein run kar sakte hain:
python
from fastapi import FastAPI, Requestfrom fastapi.responses import JSONResponse, HTMLResponsefrom fastapi.middleware.cors import CORSMiddlewarefrom transformers import pipeline, AutoTokenizerimport datetime app = FastAPI() # CORS enabled for local/web connectivityapp.add_middleware( CORSMiddleware, allow_origins=["*"], allow_credentials=True, allow_methods=["*"], allow_headers=["*"],) # Initialize Model (Aapka Model ID)print("⏳ Loading LYRA Core Engine...")model_id = 'muhammad-taqi512/LYRA'tokenizer = AutoTokenizer.from_pretrained(model_id)ai_pipeline = pipeline('text-generation', model=model_id, tokenizer=tokenizer)print("✅ LYRA AI Engine Active!") # Serve index.html UI at root route@app.get("/", response_class=HTMLResponse)async def serve_index(): with open("index.html", "r", encoding="utf-8") as f: return f.read() @app.post("/api/chat")async def chat_endpoint(data: dict): # Extracting parameters sent from frontend user_message = data.get("message", "") custom_rules = data.get( "custom_rules", "You are LYRA, an advanced AI created by Muhammad Taqi. You give accurate answers and clean code." ) if not user_message: return JSONResponse({"error": "Message is missing"}, status_code=400) # Constructing prompt using incoming custom rules full_prompt = f"<|im_start|>system\n{custom_rules}\n<|im_end|>\n<|im_start|>user\n{user_message}\n<|im_end|>\n<|im_start|>assistant\n" # Model Generation output = ai_pipeline( full_prompt, max_new_tokens=250, temperature=0.7, top_p=0.9, do_sample=True, pad_token_id=tokenizer.eos_token_id ) # Extract response raw_text = output[0]['generated_text'] response_text = raw_text.split("<|im_start|>assistant\n")[-1].replace("<|im_end|>", "").strip() return { "status": "success", "response": response_text }from fastapi import FastAPI, Requestfrom fastapi.responses import JSONResponse, HTMLResponsefrom fastapi.middleware.cors import CORSMiddlewarefrom transformers import pipeline, AutoTokenizerimport datetime app = FastAPI() # CORS enabled for local/web connectivityapp.add_middleware( CORSMiddleware, allow_origins=["*"], allow_credentials=True, allow_methods=["*"], allow_headers=["*"],) # Initialize Model (Aapka Model ID)print("⏳ Loading LYRA Core Engine...")model_id = 'muhammad-taqi512/LYRA'tokenizer = AutoTokenizer.from_pretrained(model_id)ai_pipeline = pipeline('text-generation', model=model_id, tokenizer=tokenizer)print("✅ LYRA AI Engine Active!") # Serve index.html UI at root route@app.get("/", response_class=HTMLResponse)async def serve_index(): with open("index.html", "r", encoding="utf-8") as f: return f.read() @app.post("/api/chat")async def chat_endpoint(data: dict): # Extracting parameters sent from frontend user_message = data.get("message", "") custom_rules = data.get( "custom_rules", "You are LYRA, an advanced AI created by Muhammad Taqi. You give accurate answers and clean code." ) if not user_message: return JSONResponse({"error": "Message is missing"}, status_code=400) # Constructing prompt using incoming custom rules full_prompt = f"<|im_start|>system\n{custom_rules}\n<|im_end|>\n<|im_start|>user\n{user_message}\n<|im_end|>\n<|im_start|>assistant\n" # Model Generation output = ai_pipeline( full_prompt, max_new_tokens=250, temperature=0.7, top_p=0.9, do_sample=True, pad_token_id=tokenizer.eos_token_id ) # Extract response raw_text = output[0]['generated_text'] response_text = raw_text.split("<|im_start|>assistant\n")[-1].replace("<|im_end|>", "").strip() return { "status": "success", "response": response_text }