GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
dheeyantra
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
dheeyantra
Model Tree
Input Modalities
Output Modalities
Supported Functionality
Dhee-NxtGen-Qwen3-Indic is a single, unified 4B-parameter multilingual large language model developed by DheeYantra in collaboration with NxtGen Cloud Technologies Pvt. Ltd.
Built on the Qwen3-4B architecture, the model is created to support assistant-style conversations, reasoning, and function-calling–compatible workflows across 14 Indian (Indic) languages within one shared model.
This single model supports the following Indic languages:
Best results are achieved when prompts are written entirely in the target language.
python
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLM # 1. Configurationmodel_name = "dheeyantra/dhee-nxtgen-qwen3-indic"device = "cuda" if torch.cuda.is_available() else "cpu" # 2. Load Model and Tokenizerprint(f"Loading model: {model_name}...")tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained( model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32) # 3. Define the Prompt# Using the ChatML format expected by Qwen-based architecturesprompt = """<|im_start|>systemYou are a helpful multilingual assistant.<|im_end|><|im_start|>userक्या आप मेरे लिए एक अपॉइंटमेंट बुक कर सकते हैं? अगर हाँ, तो कृपया मुझसे ज़रूरी जानकारी जैसे तारीख, समय और उद्देश्य पूछिए।<|im_end|><|im_start|>assistant""" # 4. Process and Generateinputs = tokenizer(prompt, return_tensors="pt").to(model.device) print("Generating response...")with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=256, temperature=0.7, top_p=0.9, do_sample=True, pad_token_id=tokenizer.eos_token_id ) # 5. Decode and Print# We only want to print the newly generated text (the assistant's reply)full_output = tokenizer.decode(outputs[0], skip_special_tokens=True)response = full_output.split("assistant")[-1].strip() print("-" * 30)print(f"Assistant: {response}")print("-" * 30)python
import torchimport jsonimport refrom transformers import AutoTokenizer, AutoModelForCausalLM # --- 1. MODEL SETUP ---model_name = "dheeyantra/dhee-nxtgen-qwen3-indic"tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained( model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32) # --- 2. TOOLS & SYSTEM PROMPT ---tools = [{ "name": "book_appointment", "description": "Book an appointment for the user.", "parameters": { "type": "object", "properties": { "date": {"type": "string", "description": "Date in YYYY-MM-DD format"}, "time": {"type": "string", "description": "Time in HH:MM (24h) format"}, "purpose": {"type": "string", "description": "The medical reason or department"} }, "required": ["date", "time", "purpose"] }}] # We provide the current date so the model can resolve "tomorrow" or "next Monday"SYSTEM_PROMPT = f"""You are a helpful AI assistant.Today's Date: 2026-01-08 (Thursday). Available Tools:{json.dumps(tools, indent=2)} Rules:1. If details (date, time, purpose) are missing, ask the user in Hindi.2. If all details are present, output ONLY a <tool_call> JSON.3. After a tool result is provided, confirm the booking to the user in Hindi.""" # --- 3. BACKEND FUNCTION ---def execute_booking(date, time, purpose): # Simulated backend logic if "10:00" in time: # Simulate a busy slot return {"status": "error", "message": "यह समय पहले से बुक है। कृपया कोई और समय चुनें।"} return {"status": "success", "id": "APP-9921", "doctor": "Dr. Verma"} # --- 4. THE INTERACTION ENGINE ---def run_conversation(user_input, history): # Add user input to history history.append({"role": "user", "content": user_input}) # Construct ChatML prompt prompt = f"<|im_start|>system\n{SYSTEM_PROMPT}<|im_end|>\n" for msg in history: prompt += f"<|im_start|>{msg['role']}\n{msg['content']}<|im_end|>\n" prompt += "<|im_start|>assistant\n" # Generate inputs = tokenizer(prompt, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.1) response = tokenizer.decode(outputs[0], skip_special_tokens=True).split("assistant")[-1].strip() # Check if the model wants to call a tool tool_match = re.search(r"<tool_call>(.*?)</tool_call>", response, re.DOTALL) if tool_match: print(f"\n[MODEL REQUESTED TOOL]: {response}") call_data = json.loads(tool_match.group(1).strip()) # Execute the function result = execute_booking(**call_data['arguments']) print(f"[TOOL RESULT]: {result}") # Feed result back to model for final response history.append({"role": "assistant", "content": response}) history.append({"role": "system", "content": f"Tool Result: {json.dumps(result)}"}) # Final confirmation generation return run_conversation("Please confirm the result to the user.", history) return response # --- 5. TEST SCENARIO ---chat_history = [] print("--- Chatbot Started (Today is 2026-01-08) ---") # Step 1: User provides partial infoquery_1 = "मेरे लिए डेंटिस्ट का अपॉइंटमेंट बुक करें।"print(f"\nUser: {query_1}")res_1 = run_conversation(query_1, chat_history)chat_history.append({"role": "assistant", "content": res_1})print(f"Assistant: {res_1}") # Step 2: User provides the restquery_2 = "कल दोपहर 2 बजे।"print(f"\nUser: {query_2}")res_2 = run_conversation(query_2, chat_history)print(f"Assistant: {res_2}")bash
pip install torch transformers vllm sentencepiecebash
vllm serve --model dheeyantra/dhee-nxtgen-qwen3-indic --host 0.0.0.0 --port 8000Released under the Apache 2.0 License.
Developed by DheeYantra in collaboration with NxtGen Cloud Technologies Pvt. Ltd.
import torchfrom transformers import AutoTokenizer, AutoModelForCausalLM # 1. Configurationmodel_name = "dheeyantra/dhee-nxtgen-qwen3-indic"device = "cuda" if torch.cuda.is_available() else "cpu" # 2. Load Model and Tokenizerprint(f"Loading model: {model_name}...")tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained( model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32) # 3. Define the Prompt# Using the ChatML format expected by Qwen-based architecturesprompt = """<|im_start|>systemYou are a helpful multilingual assistant.<|im_end|><|im_start|>userक्या आप मेरे लिए एक अपॉइंटमेंट बुक कर सकते हैं? अगर हाँ, तो कृपया मुझसे ज़रूरी जानकारी जैसे तारीख, समय और उद्देश्य पूछिए।<|im_end|><|im_start|>assistant""" # 4. Process and Generateinputs = tokenizer(prompt, return_tensors="pt").to(model.device) print("Generating response...")with torch.no_grad(): outputs = model.generate( **inputs, max_new_tokens=256, temperature=0.7, top_p=0.9, do_sample=True, pad_token_id=tokenizer.eos_token_id ) # 5. Decode and Print# We only want to print the newly generated text (the assistant's reply)full_output = tokenizer.decode(outputs[0], skip_special_tokens=True)response = full_output.split("assistant")[-1].strip() print("-" * 30)print(f"Assistant: {response}")print("-" * 30)import torchimport jsonimport refrom transformers import AutoTokenizer, AutoModelForCausalLM # --- 1. MODEL SETUP ---model_name = "dheeyantra/dhee-nxtgen-qwen3-indic"tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained( model_name, trust_remote_code=True, device_map="auto", torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32) # --- 2. TOOLS & SYSTEM PROMPT ---tools = [{ "name": "book_appointment", "description": "Book an appointment for the user.", "parameters": { "type": "object", "properties": { "date": {"type": "string", "description": "Date in YYYY-MM-DD format"}, "time": {"type": "string", "description": "Time in HH:MM (24h) format"}, "purpose": {"type": "string", "description": "The medical reason or department"} }, "required": ["date", "time", "purpose"] }}] # We provide the current date so the model can resolve "tomorrow" or "next Monday"SYSTEM_PROMPT = f"""You are a helpful AI assistant.Today's Date: 2026-01-08 (Thursday). Available Tools:{json.dumps(tools, indent=2)} Rules:1. If details (date, time, purpose) are missing, ask the user in Hindi.2. If all details are present, output ONLY a <tool_call> JSON.3. After a tool result is provided, confirm the booking to the user in Hindi.""" # --- 3. BACKEND FUNCTION ---def execute_booking(date, time, purpose): # Simulated backend logic if "10:00" in time: # Simulate a busy slot return {"status": "error", "message": "यह समय पहले से बुक है। कृपया कोई और समय चुनें।"} return {"status": "success", "id": "APP-9921", "doctor": "Dr. Verma"} # --- 4. THE INTERACTION ENGINE ---def run_conversation(user_input, history): # Add user input to history history.append({"role": "user", "content": user_input}) # Construct ChatML prompt prompt = f"<|im_start|>system\n{SYSTEM_PROMPT}<|im_end|>\n" for msg in history: prompt += f"<|im_start|>{msg['role']}\n{msg['content']}<|im_end|>\n" prompt += "<|im_start|>assistant\n" # Generate inputs = tokenizer(prompt, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.1) response = tokenizer.decode(outputs[0], skip_special_tokens=True).split("assistant")[-1].strip() # Check if the model wants to call a tool tool_match = re.search(r"<tool_call>(.*?)</tool_call>", response, re.DOTALL) if tool_match: print(f"\n[MODEL REQUESTED TOOL]: {response}") call_data = json.loads(tool_match.group(1).strip()) # Execute the function result = execute_booking(**call_data['arguments']) print(f"[TOOL RESULT]: {result}") # Feed result back to model for final response history.append({"role": "assistant", "content": response}) history.append({"role": "system", "content": f"Tool Result: {json.dumps(result)}"}) # Final confirmation generation return run_conversation("Please confirm the result to the user.", history) return response # --- 5. TEST SCENARIO ---chat_history = [] print("--- Chatbot Started (Today is 2026-01-08) ---") # Step 1: User provides partial infoquery_1 = "मेरे लिए डेंटिस्ट का अपॉइंटमेंट बुक करें।"print(f"\nUser: {query_1}")res_1 = run_conversation(query_1, chat_history)chat_history.append({"role": "assistant", "content": res_1})print(f"Assistant: {res_1}") # Step 2: User provides the restquery_2 = "कल दोपहर 2 बजे।"print(f"\nUser: {query_2}")res_2 = run_conversation(query_2, chat_history)print(f"Assistant: {res_2}")vllm serve --model dheeyantra/dhee-nxtgen-qwen3-indic --host 0.0.0.0 --port 8000