Text Generation
Transformers
English
conversational
gaming
persona
local-llm
autotelic
think-block
vision-llm
harness
qwen
Instructions to use bochen2079/ASTRA-7 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bochen2079/ASTRA-7 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="bochen2079/ASTRA-7") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("bochen2079/ASTRA-7", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use bochen2079/ASTRA-7 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "bochen2079/ASTRA-7" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "bochen2079/ASTRA-7", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/bochen2079/ASTRA-7
- SGLang
How to use bochen2079/ASTRA-7 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 "bochen2079/ASTRA-7" \ --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": "bochen2079/ASTRA-7", "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 "bochen2079/ASTRA-7" \ --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": "bochen2079/ASTRA-7", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use bochen2079/ASTRA-7 with Docker Model Runner:
docker model run hf.co/bochen2079/ASTRA-7
Commit ·
28b4b28
1
Parent(s): f431726
Add website link astra-7.com
Browse filesCross-link the bundle page with the new landing site and the GitHub
source. Everything points to everything.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
README.md
CHANGED
|
@@ -21,10 +21,13 @@ library_name: transformers
|
|
| 21 |
|
| 22 |
> A ship, one human, one mind, the long voyage.
|
| 23 |
|
| 24 |
-
ASTRA-7 is the persona bundle for the AI character at the center of [ASTRA-7](https://
|
| 25 |
|
| 26 |
**Status: placeholder.** As of 2026-05-12 the LoRA has not been trained. The sysprompt is canon. The harness lives in the GitHub repository. Check back as the project develops.
|
| 27 |
|
|
|
|
|
|
|
|
|
|
| 28 |
## Project
|
| 29 |
|
| 30 |
ASTRA-7 is a solitary starship simulator. You are the only crewman aboard a vessel that doesn't need you. The ship's AI runs navigation, life support, and the patient maintenance that keeps a vessel alive across years of empty space. There is one other mind aboard. No combat. No aliens. No other NPCs. The mission is unspecified. The destination is irrelevant.
|
|
@@ -35,6 +38,7 @@ This is the first game where the AI is the primary content.
|
|
| 35 |
|
| 36 |
## Distribution
|
| 37 |
|
|
|
|
| 38 |
- **Code:** [bochen2029-pixel/astra-7](https://github.com/bochen2029-pixel/astra-7) on GitHub. MIT.
|
| 39 |
- **AI Bundle:** this repository. Apache 2.0 for bundle artifacts; base model licenses apply to derived weights.
|
| 40 |
- **Game:** Steam, Coming Soon. Free. No DRM. No monetization. No telemetry. No internet connection required after install.
|
|
|
|
| 21 |
|
| 22 |
> A ship, one human, one mind, the long voyage.
|
| 23 |
|
| 24 |
+
ASTRA-7 is the persona bundle for the AI character at the center of [ASTRA-7](https://astra-7.com), an open-source solo-dev starship simulator. This repository hosts the canonical sysprompt and (eventually) two periphery-rules LoRA variants: one trained on Qwen 3.5 9B and one on Qwen 3.6 27B.
|
| 25 |
|
| 26 |
**Status: placeholder.** As of 2026-05-12 the LoRA has not been trained. The sysprompt is canon. The harness lives in the GitHub repository. Check back as the project develops.
|
| 27 |
|
| 28 |
+
- **Website:** <https://astra-7.com>
|
| 29 |
+
- **Source code:** <https://github.com/bochen2029-pixel/astra-7>
|
| 30 |
+
|
| 31 |
## Project
|
| 32 |
|
| 33 |
ASTRA-7 is a solitary starship simulator. You are the only crewman aboard a vessel that doesn't need you. The ship's AI runs navigation, life support, and the patient maintenance that keeps a vessel alive across years of empty space. There is one other mind aboard. No combat. No aliens. No other NPCs. The mission is unspecified. The destination is irrelevant.
|
|
|
|
| 38 |
|
| 39 |
## Distribution
|
| 40 |
|
| 41 |
+
- **Website:** <https://astra-7.com>
|
| 42 |
- **Code:** [bochen2029-pixel/astra-7](https://github.com/bochen2029-pixel/astra-7) on GitHub. MIT.
|
| 43 |
- **AI Bundle:** this repository. Apache 2.0 for bundle artifacts; base model licenses apply to derived weights.
|
| 44 |
- **Game:** Steam, Coming Soon. Free. No DRM. No monetization. No telemetry. No internet connection required after install.
|