Text Generation
Transformers
English
code
coding
code-generation
distillation
gpt2-xl
causal-lm
qwen
How to use from
SGLangUse 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 "waveforce-ai/Aura-1-Coding" \
--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": "waveforce-ai/Aura-1-Coding",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'Quick Links
Aura-1-Coding (Standalone FP16)
Aura-1-Coding is a lightweight, distilled causal language model designed for Python code generation and algorithmic problem solving. It adapts GPT-2 XL (1.5B parameters) through live on-policy knowledge distillation from Qwen2.5-3B-Instruct, fusing modern reasoning and coding patterns into a compact, standalone footprint.
This repository hosts the fully merged standalone FP16 weights (safetensors). No PEFT or bitsandbytes runtime dependencies are required for deployment.
Model Details
- Architecture: Causal Transformer (Decoder-Only)
- Base Model:
gpt2-xl(1.5B parameters) - Teacher Model:
Qwen/Qwen2.5-3B-Instruct - Distillation Method: Live On-Policy Sequence Distillation via QLoRA (NF4) merged into FP16
- Precision: Float16 (
torch.float16) - Context Window: Up to 1024 tokens (optimized for prompts/solutions $\le 512$ tokens)
- Primary Domain: Python algorithms, data structures, and utility functions
Prompt Format
Aura-1-Coding is trained on structured prompt-solution pairs. For optimal performance, structure your input as follows:
Problem: <Your description or programming question task>
Solution:
Model tree for waveforce-ai/Aura-1-Coding
Base model
openai-community/gpt2-xl
Install from pip and serve model
# Install SGLang from pip: pip install sglang# Start the SGLang server: python3 -m sglang.launch_server \ --model-path "waveforce-ai/Aura-1-Coding" \ --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": "waveforce-ai/Aura-1-Coding", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'