Instructions to use cosmicoptima/computer-9a with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cosmicoptima/computer-9a with Transformers:

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

pipe = pipeline("text-generation", model="cosmicoptima/computer-9a")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cosmicoptima/computer-9a")
model = AutoModelForCausalLM.from_pretrained("cosmicoptima/computer-9a", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cosmicoptima/computer-9a with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cosmicoptima/computer-9a"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cosmicoptima/computer-9a",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cosmicoptima/computer-9a

SGLang

How to use cosmicoptima/computer-9a 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 "cosmicoptima/computer-9a" \
    --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": "cosmicoptima/computer-9a",
		"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 "cosmicoptima/computer-9a" \
        --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": "cosmicoptima/computer-9a",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cosmicoptima/computer-9a with Docker Model Runner:
```
docker model run hf.co/cosmicoptima/computer-9a
```

Computer-9a

Computer-9a is the step-60 policy from an online terminal reinforcement-learning experiment. It is a full-weight bfloat16 causal language model exported from the exact retained FSDP checkpoint used for evaluation.

The training environment presented a bash tool through textual <tool name="bash">...</tool> calls and returned textual <tool_result name="bash">...</tool_result> observations. The model was optimized on automatically verified terminal tasks while regularizing against a conversational parent policy.

Prompt format

The experiment used an explicit transcript header and role markers:

**User:** ...

**Model C:** ...

**Environment:** <tool_result name="bash">...</tool_result>

Tool execution is not built into the weights. Applications must parse tool calls, execute them in an appropriately isolated sandbox, append the tool result, and generate the next model turn.

Safety and limitations

This is a research checkpoint. It can emit shell commands and should only be connected to a strongly isolated, least-privilege environment. It may make destructive requests, hallucinate command effects, contradict visible tool traces, or fail exact multi-stage tasks. Do not give it credentials, unrestricted network access, or access to valuable files.

The model often produces terse answers. Its terminal-task performance and fixed-probe performance are noisy, and this checkpoint should not be interpreted as a generally reliable computer-use agent.

Checkpoint identity

Training step: 60
Export dtype: bfloat16
Source checkpoint: retained-checkpoint-60
Export format: sharded safetensors

Downloads last month: -

Safetensors

Model size

71B params

Tensor type

BF16