Instructions to use NoesisLab/Kai-30B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NoesisLab/Kai-30B-Instruct with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="NoesisLab/Kai-30B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NoesisLab/Kai-30B-Instruct")
model = AutoModelForCausalLM.from_pretrained("NoesisLab/Kai-30B-Instruct", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NoesisLab/Kai-30B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NoesisLab/Kai-30B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NoesisLab/Kai-30B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NoesisLab/Kai-30B-Instruct

SGLang

How to use NoesisLab/Kai-30B-Instruct with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "NoesisLab/Kai-30B-Instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NoesisLab/Kai-30B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "NoesisLab/Kai-30B-Instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NoesisLab/Kai-30B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NoesisLab/Kai-30B-Instruct with Docker Model Runner:
```
docker model run hf.co/NoesisLab/Kai-30B-Instruct
```

OzTianlu commited on Mar 3

Commit

1228bb4

verified ·

1 Parent(s): 79921d9

Upload 2 files

Browse files

Files changed (3) hide show

.gitattributes +1 -0
README.md +11 -0
model_comparison_aaai.png +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+model_comparison_aaai.png filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -35,6 +35,17 @@ A 30B-parameter instruction-tuned language model optimized for reasoning, math,
 | **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.

 | **Vocab size** | 64,000 |
 | **Chat template** | ChatML (`<\|im_start\|>` / `<\|im_end\|>`) |
+## Benchmark Results (5-shot, acc_norm)
+| Benchmark | Kai-30B-Instruct | Llama-3 70B | Qwen2.5 32B | Yi-34B | Llama-3 8B | Mistral 7B | Llama-2 7B |
+|-----------|:---:|:---:|:---:|:---:|:---:|:---:|:---:|
+| **ARC-C** | 64.0 | 83.0 | 70.5 | 65.3 | 60.1 | 55.5 | 53.0 |
+| **HellaSwag** | 74.4 | 89.0 | 85.2 | 83.1 | 78.6 | 81.3 | 78.6 |
+| **PIQA** | 84.8 | 85.0 | 84.1 | 82.5 | 79.8 | 82.1 | 78.1 |
+| **Winogrande** | **86.4** | 83.0 | 78.2 | 76.4 | 73.0 | 74.0 | 69.1 |
+![Benchmark Comparison](model_comparison_aaai.png)
 ## 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.

model_comparison_aaai.png ADDED Viewed

Git LFS Details

SHA256: d38ebf4ed0e75e9cd3ee80cee4c989c233025d7ff77664e3f5a794e31a2182ac
Pointer size: 131 Bytes
Size of remote file: 147 kB