Article may be outdated

This article is 8 days old. Some details may have changed since publication.

Hacker News·2 min read·hard

GLM-5.3 is now open-weight

J
jeudesprits
GLM-5.3 is now open-weight
AI Summary

The GLM-5.3 artificial intelligence model has been released as an open-weight project, allowing developers to integrate it into various applications. The model supports both English and Chinese and is compatible with standard machine learning libraries like Transformers and vLLM.

Why it matters

The release of open-weight models accelerates the democratization of advanced AI, enabling researchers and developers to build custom solutions without relying on proprietary APIs.

Dive DeeperCreate a free account to unlock

like 1.04k Follow Z.ai 19.6k Text Generation Transformers Safetensors English Chinese glm_moe_dsa conversational Eval Results fp8 arxiv: 2602.15763 License: glm-5.3 Model card Files Files and versions xet Community 5 Deploy Copy to bucket new Use this model Instructions to use zai-org/GLM-5.3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started. Libraries Transformers How to use zai-org/GLM-5.3 with Transformers:

# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="zai-org/GLM-5.3") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages) # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("zai-org/GLM-5.3") model = AutoModelForCausalLM.from_pretrained("zai-org/GLM-5.3", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) Inference Inference Providers HuggingChat Notebooks Google Colab Kaggle Local Apps Settings vLLM How to use zai-org/GLM-5.3 with vLLM:

Continue reading on Headlinne

Create a free account to read the full article.

Read full article →
technologyai

Get smarter about the news

Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.

Create free account

Already have an account? Sign in