Instructions to use NoesisLab/Kai-3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NoesisLab/Kai-3B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="NoesisLab/Kai-3B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NoesisLab/Kai-3B-Instruct")
model = AutoModelForCausalLM.from_pretrained("NoesisLab/Kai-3B-Instruct")
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

vLLM

How to use NoesisLab/Kai-3B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NoesisLab/Kai-3B-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-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NoesisLab/Kai-3B-Instruct

SGLang

How to use NoesisLab/Kai-3B-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-3B-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-3B-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-3B-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-3B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NoesisLab/Kai-3B-Instruct with Docker Model Runner:
```
docker model run hf.co/NoesisLab/Kai-3B-Instruct
```

OzTianlu commited on Feb 27

Commit

eede50b

verified ·

1 Parent(s): 800f1ab

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

README.md +1 -1
model-00001-of-00002.safetensors +1 -1
model-00002-of-00002.safetensors +1 -1

README.md CHANGED Viewed

@@ -102,7 +102,7 @@ A 3B-parameter instruction-tuned language model optimized for reasoning, math, a
 ## 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.
 ## Benchmark Results

 ## What is ADS?
+**Adaptive Dual-Search Distillation (自适应对偶搜索蒸馏)** 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.
 ## Benchmark Results

model-00001-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e98ab017eab910e19466dfa5ce298e1720470c563efb1efc686b314239257a34
 size 4966315264

 version https://git-lfs.github.com/spec/v1
+oid sha256:e5a15717e85d23851ded51752efb28ce8296403925f91d01005bfff4c587b308
 size 4966315264

model-00002-of-00002.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abc6d445d8b0a2bf107b4502636b27da5c023ce89d41ca4399eb6ace288efe86
 size 1183919744

 version https://git-lfs.github.com/spec/v1
+oid sha256:30034dea2d5a297abd0648af528b0c1755e8aaa7085d63965dfa5e0ca3759976
 size 1183919744