Instructions to use alea-institute/kl3m-006-170m-checkpoint-33000 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alea-institute/kl3m-006-170m-checkpoint-33000 with Transformers:

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

pipe = pipeline("text-generation", model="alea-institute/kl3m-006-170m-checkpoint-33000")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alea-institute/kl3m-006-170m-checkpoint-33000")
model = AutoModelForCausalLM.from_pretrained("alea-institute/kl3m-006-170m-checkpoint-33000", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alea-institute/kl3m-006-170m-checkpoint-33000 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alea-institute/kl3m-006-170m-checkpoint-33000"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alea-institute/kl3m-006-170m-checkpoint-33000",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/alea-institute/kl3m-006-170m-checkpoint-33000

SGLang

How to use alea-institute/kl3m-006-170m-checkpoint-33000 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 "alea-institute/kl3m-006-170m-checkpoint-33000" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alea-institute/kl3m-006-170m-checkpoint-33000",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "alea-institute/kl3m-006-170m-checkpoint-33000" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alea-institute/kl3m-006-170m-checkpoint-33000",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use alea-institute/kl3m-006-170m-checkpoint-33000 with Docker Model Runner:
```
docker model run hf.co/alea-institute/kl3m-006-170m-checkpoint-33000
```

KL3M 170M, 6th Gen Model, 33K Checkpoint

A 170M parameter language model trained on legal agreements using the Muon optimizer with spectral clamping.

Model Details

Architecture: Llama-based with Grouped Query Attention (GQA)
Parameters: 181.7M (170M non-embedding)
Training Steps: 33,000
Sequence Length: 4,096 tokens
Precision: BF16
Optimizer: Muon with spectral regularization (max condition: 2000)

Model Architecture

Hidden Size: 576
Layers: 30
Attention Heads: 9 (3 KV heads with GQA)
Intermediate Size: 1536
Vocabulary: 131,072 tokens

Training Configuration

Dataset: Legal agreements (EDGAR filings)
Optimizer: Muon with momentum 0.95
Muon Learning Rate: 8e-5 (depth-scaled)
Auxiliary Learning Rate: 4e-5
Batch Size: 1 per device (effective 4 with gradient accumulation)
Gradient Accumulation Steps: 4
Warmup Steps: 10,000
LR Scheduler: Cosine with warmup
Weight Decay: Muon 1e-5, Auxiliary 0.001
Spectral Clamping: Enabled (max condition 2000, sigma floor 6e-4, every 10 steps)
Mixed Precision: BF16
Gradient Checkpointing: Enabled
Additional Regularization:
- Entropy bonus weight: 0.001 (target: 6.5 bits)
- Activation norm weight: 0.001
- Loss chunk tokens: 1024

Spectral Health (Step 33K)

Attention Layers: Median condition number 237.75 ✓ EXCELLENT
MLP Layers: Median condition number 4.58 ✓ EXCELLENT
Max Attention Condition: 2208.16 (at spectral clamp ceiling)

Generation Quality

Generates coherent, fluent legal text with no repetition issues. Best for legal/contractual content.

Usage

from transformers import pipeline

# Create text generation pipeline
generator = pipeline(
    "text-generation",
    model="alea-institute/kl3m-006-170m-checkpoint-33000",
    torch_dtype="auto",
    device_map="auto"
)

# Generate text
outputs = generator(
    "This Agreement is entered into as of",
    max_new_tokens=100,
    temperature=0.7,
    top_p=0.95,
    repetition_penalty=1.15
)

print(outputs[0]['generated_text'])

Citation

For technical details, see the paper: https://arxiv.org/abs/2504.07854

@misc{kl3m2025,
  title={KL3M: Knowledge-Guided Language Model Training},
  author={Alea Institute},
  year={2025},
  url={https://arxiv.org/abs/2504.07854},
  note={Trained with Muon optimizer and spectral clamping}
}

License

Apache 2.0

Downloads last month: 20

Safetensors

Model size

0.2B params

Tensor type

BF16

Paper for alea-institute/kl3m-006-170m-checkpoint-33000

The KL3M Data Project: Copyright-Clean Training Resources for Large Language Models

Paper • 2504.07854 • Published Apr 10, 2025