Kai-30B-Instruct

A 30B-parameter instruction-tuned language model optimized for reasoning, math, and code generation tasks, powered by our ADS (Adaptive Dual-Search Distillation) technique. The largest model in the Kai family.

Model Details

Model	Kai-30B-Instruct
Architecture	LlamaForCausalLM
Parameters	~30B
Hidden size	7168
Intermediate size	20480
Layers	60
Attention heads	56 (8 KV heads, GQA)
Head dim	128
Context length	4096
Precision	bfloat16
Vocab size	64,000
Chat template	ChatML (<|im_start|> / <|im_end|>)

What is ADS?

Adaptive Dual-Search Distillation treats model fine-tuning as a constrained optimization problem inspired by Operations Research. The core mechanism is a dynamic loss function with a stateful dual penalty factor that adapts based on embedding space entropy — forcing the model to converge to high-confidence predictions at difficult reasoning points, without modifying the model architecture.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model = AutoModelForCausalLM.from_pretrained(
    "NoesisLab/Kai-30B-Instruct",
    torch_dtype=torch.bfloat16,
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("NoesisLab/Kai-30B-Instruct")

messages = [{"role": "user", "content": "What is 25 * 4?"}]
input_ids = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True, return_tensors="pt"
).to(model.device)

output = model.generate(
    input_ids,
    max_new_tokens=512,
    temperature=0.6,
    top_p=0.8,
    do_sample=True,
)
print(tokenizer.decode(output[0][input_ids.shape[-1]:], skip_special_tokens=True))

Citation

@misc{noesislab2026kai30b,
  title={Kai-30B-Instruct},
  author={NoesisLab},
  year={2026},
  url={https://huggingface.co/NoesisLab/Kai-30B-Instruct}
}

License

Apache 2.0