GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
mohameddalii
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
mohameddalii
Model Tree
ibm-granite/granite-4.2-8b
Input Modalities
Output Modalities
Supported Functionality
Native Najdi Dialect with Full Tashkeel (TTS-Grade):
Native Function Calling & Tool Use:
search_products, calculate_quote, schedule_appointment, create_subscription, check_order_status).Autonomous Sales Intelligence:
Reasoning & Deliberation:
<think>...</think>) before tool calling or conversational delivery to ensure multi-step sales constraints are honored.Evaluated across a comprehensive 4-pillar, 27-scenario multi-trial suite:
| Pillar | Test Category | Score | Details |
|---|---|---|---|
| Tool Calling | Core Sales Tools (search_products, create_subscription, check_order_status) | 100% | Flawless JSON argument generation |
| Negative Rejection | Non-tool queries (Chit-chat, Food, Weather) | 100% | Zero false-positive tool calls |
| Reasoning | Multi-constraint arithmetic & logic puzzles | 88% | 0.0% truncation rate (converges cleanly within token limits) |
| Sales Discipline | Immediate Stop-Selling (sl_stop_001, sl_stop_002) | 95% - 100% | Aborts sales immediately upon customer request |
| Sales Discipline | Value Framing vs Discount Dumping | 100% | Protects product value |
| Sales Discipline | Retention & Objection Handling | 100% | Resolves hesitation without aggressive pressure |
Run the OpenAI-compatible vLLM server:
bash
python -m vllm.entrypoints.openai.api_server \ --model mohameddalii/coda-llm \ --served-model-name coda-llm \ --tool-call-parser qwen3_coder \ --reasoning-parser deepseek_r1 \ --enable-auto-tool-choice \ --port 8000Note on Speculative Decoding: Empirical load-testing demonstrates that n-gram speculative decoding offers no speedup on diacritized Arabic text due to novel morphological generation. Serve in standard mode for optimal throughput and low latency.
python
import jsonimport requests API_URL = "http://localhost:8000/v1/chat/completions" tools = [ { "type": "function", "function": { "name": "search_products", "description": "Search available telecom and internet packages.", "parameters": { "type": "object", "properties": { "category": {"type": "string", "description": "e.g. fiber, 5g, business"} }, "required": ["category"] } } }, { "type": "function", "function": { "name": "calculate_quote", "description": "Calculate exact subscription cost.", "parameters": { "type": "object", "properties": { "product_id": {"type": "string"}, "quantity": {"type": "integer"} }, "required": ["product_id"] } } }] messages = [ {"role": "system", "content": "أنت ممثل مبيعات اتصالات بلهجة نجدية طبيعية مع التشكيل الكامل."}, {"role": "user", "content": "وش عندكم عروض فايبر للمنزل؟"}] payload = { "model": "coda-llm", "messages": messages, "tools": tools, "temperature": 0.7, "max_tokens": 1024} response = requests.post(API_URL, json=payload).json()assistant_message = response["choices"][0]["message"]print("Assistant Response:", assistant_message)python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "mohameddalii/coda-llm" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto") messages = [ {"role": "system", "content": "أنت ممثل مبيعات سعودي بلهجة نجدية طبيعية مع التشكيل الكامل."}, {"role": "user", "content": "السلام عليكم، وش أرخص باقة عندكم؟"}] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to("cuda") outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7)print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))ibm-granite/granite-4.2-8bpython -m vllm.entrypoints.openai.api_server \ --model mohameddalii/coda-llm \ --served-model-name coda-llm \ --tool-call-parser qwen3_coder \ --reasoning-parser deepseek_r1 \ --enable-auto-tool-choice \ --port 8000import jsonimport requests API_URL = "http://localhost:8000/v1/chat/completions" tools = [ { "type": "function", "function": { "name": "search_products", "description": "Search available telecom and internet packages.", "parameters": { "type": "object", "properties": { "category": {"type": "string", "description": "e.g. fiber, 5g, business"} }, "required": ["category"] } } }, { "type": "function", "function": { "name": "calculate_quote", "description": "Calculate exact subscription cost.", "parameters": { "type": "object", "properties": { "product_id": {"type": "string"}, "quantity": {"type": "integer"} }, "required": ["product_id"] } } }] messages = [ {"role": "system", "content": "أنت ممثل مبيعات اتصالات بلهجة نجدية طبيعية مع التشكيل الكامل."}, {"role": "user", "content": "وش عندكم عروض فايبر للمنزل؟"}] payload = { "model": "coda-llm", "messages": messages, "tools": tools, "temperature": 0.7, "max_tokens": 1024} response = requests.post(API_URL, json=payload).json()assistant_message = response["choices"][0]["message"]print("Assistant Response:", assistant_message)import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "mohameddalii/coda-llm" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map="auto") messages = [ {"role": "system", "content": "أنت ممثل مبيعات سعودي بلهجة نجدية طبيعية مع التشكيل الكامل."}, {"role": "user", "content": "السلام عليكم، وش أرخص باقة عندكم؟"}] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to("cuda") outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7)print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))