Text Generation
Transformers
English
code
coding
code-generation
distillation
gpt2-xl
causal-lm
qwen
Instructions to use waveforce-ai/Aura-1-Coding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use waveforce-ai/Aura-1-Coding with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="waveforce-ai/Aura-1-Coding")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("waveforce-ai/Aura-1-Coding", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use waveforce-ai/Aura-1-Coding with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "waveforce-ai/Aura-1-Coding" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/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 }'Use Docker
docker model run hf.co/waveforce-ai/Aura-1-Coding
- SGLang
How to use waveforce-ai/Aura-1-Coding 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 "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 }'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 "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 }' - Docker Model Runner
How to use waveforce-ai/Aura-1-Coding with Docker Model Runner:
docker model run hf.co/waveforce-ai/Aura-1-Coding
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,17 +1,10 @@
|
|
| 1 |
---
|
| 2 |
license: llama3.1
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
-
Name: text
|
| 9 |
-
Date of Birth: date_picker
|
| 10 |
-
Primary Intent:
|
| 11 |
-
type: select
|
| 12 |
-
options:
|
| 13 |
-
- "Personal Use"
|
| 14 |
-
- "Business Use"
|
| 15 |
---
|
| 16 |
|
| 17 |
# Aura-1-Coding (Standalone 4-Bit Variant)
|
|
@@ -20,19 +13,9 @@ Aura-1-Coding is an ultra-fast, standalone code generation model optimized using
|
|
| 20 |
|
| 21 |
---
|
| 22 |
|
| 23 |
-
## 🔒 Terms and Conditions (Gated Agreement)
|
| 24 |
-
|
| 25 |
-
By requesting access to, downloading, or interacting with the weights of **Aura-1-Coding**, you explicitly bind yourself to the following team directives:
|
| 26 |
-
|
| 27 |
-
1. **Anti-Tampering & Guardrails:** You are strictly prohibited from modifying, fine-tuning for malicious use, or executing adversarial prompt injections ("jailbreaks") to force the model into coding harmful, illegal, or destructive payloads.
|
| 28 |
-
2. **Data Collection Policy:** To ensure alignment, system stability, and project integrity, waveforce-ai reserves the right to collect metadata, execution parameters, and request telemetry passing through the infrastructure.
|
| 29 |
-
3. **Usage Boundaries:** Requests submitted under *Personal Use* are restricted to non-commercial research and local development environments. *Business Use* tier allocations must comply with corporate liability parameters.
|
| 30 |
-
|
| 31 |
-
---
|
| 32 |
-
|
| 33 |
## ⚡ Performance Footprint & Specifications
|
| 34 |
|
| 35 |
-
|
| 36 |
|
| 37 |
| Metric / Component | Configuration Specification |
|
| 38 |
| :--- | :--- |
|
|
|
|
| 1 |
---
|
| 2 |
license: llama3.1
|
| 3 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
| 4 |
+
tags:
|
| 5 |
+
- code
|
| 6 |
+
- text-generation
|
| 7 |
+
- distilled
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
# Aura-1-Coding (Standalone 4-Bit Variant)
|
|
|
|
| 13 |
|
| 14 |
---
|
| 15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
## ⚡ Performance Footprint & Specifications
|
| 17 |
|
| 18 |
+
The primary execution architecture operates under the following hardware parameters:
|
| 19 |
|
| 20 |
| Metric / Component | Configuration Specification |
|
| 21 |
| :--- | :--- |
|