Arxiv:2507.08297 Autotrain compatible Conversational Endpoints compatible Multilingual Qwen2 Region:us Safetensors Sharded Tensorflow
Model Card on HF 🤗: https://huggingface.co/Kwaipilot/KAT-V1-40B
KAT V1 40B Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
KAT V1 40B Parameters and Internals
| LLM Name | KAT V1 40B |
| Repository 🤗 | https://huggingface.co/Kwaipilot/KAT-V1-40B |
| Model Size | 40b |
| Required VRAM | 81.1 GB |
| Updated | 2025-10-23 |
| Maintainer | Kwaipilot |
| Model Type | qwen2 |
| Model Files | |
| Model Architecture | Qwen2ForCausalLM |
| License | other |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.46.1 |
| Tokenizer Class | Qwen2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 152064 |
| Torch Data Type | bfloat16 |
| Errors | replace |
Rank the KAT V1 40B Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 51594 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124