GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
TheArchitect256
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
TheArchitect256
Model Tree
unsloth/Qwen3.5-2B
Input Modalities
Output Modalities
Supported Functionality
Evaluated on a held-out set of 500 examples (not seen during training):
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "TheArchitect256/qwen3.5-2b-triage-master" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto") alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. ### Instruction:{} ### Input:{} ### Response:""" instruction = """Available tools:1. [STOCK_CHECK]: Verifies if an item is available in the warehouse inventory.2. [SHIPPING_CALC]: Calculates delivery rates and times based on postal codes. User Query: Can you tell me if we still have the RTX 4060 graphics card in our warehouse?""" prompt = alpaca_prompt.format(instruction, "")inputs = tokenizer(text=prompt, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_new_tokens=20, do_sample=False, pad_token_id=tokenizer.eos_token_id)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)) # **Note:** The model does not reliably emit an EOS token after the tool label, so `generate()` may continue producing text past the intended answer. Always truncate the output to the first `[TOOL_NAME]`-style tag rather than relying on generation length alone: import rematch = re.search(r"\[[A-Z_]+\]", response)clean_response = match.group(0) if match else response.strip()This model was trained 2x faster with Unsloth and Hugging Face's TRL library.
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer model_id = "TheArchitect256/qwen3.5-2b-triage-master" tokenizer = AutoTokenizer.from_pretrained(model_id)model = AutoModelForCausalLM.from_pretrained(model_id, dtype=torch.bfloat16, device_map="auto") alpaca_prompt = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. ### Instruction:{} ### Input:{} ### Response:""" instruction = """Available tools:1. [STOCK_CHECK]: Verifies if an item is available in the warehouse inventory.2. [SHIPPING_CALC]: Calculates delivery rates and times based on postal codes. User Query: Can you tell me if we still have the RTX 4060 graphics card in our warehouse?""" prompt = alpaca_prompt.format(instruction, "")inputs = tokenizer(text=prompt, return_tensors="pt").to(model.device) outputs = model.generate(**inputs, max_new_tokens=20, do_sample=False, pad_token_id=tokenizer.eos_token_id)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True)) # **Note:** The model does not reliably emit an EOS token after the tool label, so `generate()` may continue producing text past the intended answer. Always truncate the output to the first `[TOOL_NAME]`-style tag rather than relying on generation length alone: import rematch = re.search(r"\[[A-Z_]+\]", response)clean_response = match.group(0) if match else response.strip()