GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
alphaedge-ai
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
alphaedge-ai
Model Tree
Input Modalities
Output Modalities
Supported Functionality
| Metric | Original | Trimmed | Reduction |
|---|---|---|---|
| Vocabulary size | 151,936 tokens | 16,384 tokens | 89.22% |
| Model size | 2,031,739,904 params | 1,476,518,912 params | 27.33% |
python
from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "alphaedge-ai/Qwen3-1.7B-war-16384" # load the tokenizer and the modeltokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto") # prepare the model inputprompt = "Your prompt in Waray."messages = [ {"role": "user", "content": prompt}]text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.)model_inputs = tokenizer([text], return_tensors="pt").to(model.device) # conduct text completiongenerated_ids = model.generate( **model_inputs, max_new_tokens=32768)output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() # parsing thinking contenttry: # rindex finding 32767 (</think>) index = len(output_ids) - output_ids[::-1].index(32767)except ValueError: index = 0 thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("")content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("") print("thinking content:", thinking_content)print("content:", content)text
@misc{qwen3technicalreport, title={Qwen3 Technical Report}, author={Qwen Team}, year={2025}, eprint={2505.09388}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2505.09388}, }text
@misc{hf_blogpost_trimming, title={Introduction to Trimming}, author={Loïck BOURDOIS and Tom AARSEN and Bram VANROY and Christopher AKIKI and Woojun JUNG and Manuel ROMERO and Prithiv SAKTHI}, year={2026}, url={https://huggingface.co/blog/lbourdois/introduction-to-trimming}, }@misc{qwen3technicalreport, title={Qwen3 Technical Report}, author={Qwen Team}, year={2025}, eprint={2505.09388}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2505.09388}, }@misc{hf_blogpost_trimming, title={Introduction to Trimming}, author={Loïck BOURDOIS and Tom AARSEN and Bram VANROY and Christopher AKIKI and Woojun JUNG and Manuel ROMERO and Prithiv SAKTHI}, year={2026}, url={https://huggingface.co/blog/lbourdois/introduction-to-trimming}, }from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "alphaedge-ai/Qwen3-1.7B-war-16384" # load the tokenizer and the modeltokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained( model_name, torch_dtype="auto", device_map="auto") # prepare the model inputprompt = "Your prompt in Waray."messages = [ {"role": "user", "content": prompt}]text = tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True, enable_thinking=True # Switches between thinking and non-thinking modes. Default is True.)model_inputs = tokenizer([text], return_tensors="pt").to(model.device) # conduct text completiongenerated_ids = model.generate( **model_inputs, max_new_tokens=32768)output_ids = generated_ids[0][len(model_inputs.input_ids[0]):].tolist() # parsing thinking contenttry: # rindex finding 32767 (</think>) index = len(output_ids) - output_ids[::-1].index(32767)except ValueError: index = 0 thinking_content = tokenizer.decode(output_ids[:index], skip_special_tokens=True).strip("")content = tokenizer.decode(output_ids[index:], skip_special_tokens=True).strip("") print("thinking content:", thinking_content)print("content:", content)