mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-27 01:11:40 +00:00
5438b64e32
- Introduced `run_browser_tasks.sh` for executing browser-focused data generation tasks with specific guidelines for automation. - Added `run_eval_glm4.7_newterm.sh` for evaluating terminal tasks using the GLM 4.7 model, including logging and configuration for terminal environments. - Created `run_eval_terminal.sh` for terminal-only evaluations with Modal sandboxes, ensuring proper logging and environment setup. - Developed `run_mixed_tasks.sh` for running mixed browser and terminal tasks, integrating capabilities for both environments. - Implemented `run_terminal_tasks.sh` for terminal-focused data generation, with detailed instructions for task execution and logging. - All scripts include timestamped logging for better tracking of task execution and outputs.
34 lines
1.7 KiB
Bash
Executable file
34 lines
1.7 KiB
Bash
Executable file
#!/bin/bash
|
|
|
|
# Terminal-focused data generation run
|
|
# Uses nous-terminal-tasks.jsonl (597 tasks)
|
|
# Distribution: terminal 97%, web 15%, browser 10%, vision 8%, image_gen 3%
|
|
|
|
# Create logs directory if it doesn't exist
|
|
mkdir -p logs
|
|
|
|
# Generate log filename with timestamp
|
|
LOG_FILE="logs/terminal_tasks_$(date +%Y%m%d_%H%M%S).log"
|
|
|
|
echo "📝 Logging output to: $LOG_FILE"
|
|
echo "💻 Running terminal-focused tasks with terminal_tasks distribution"
|
|
|
|
# Set terminal environment (Modal sandboxes recommended for safety)
|
|
export TERMINAL_ENV=modal
|
|
export TERMINAL_MODAL_IMAGE=nikolaik/python-nodejs:python3.11-nodejs20
|
|
export TERMINAL_TIMEOUT=300
|
|
|
|
python batch_runner.py \
|
|
--dataset_file="nous-terminal-tasks.jsonl" \
|
|
--batch_size=20 \
|
|
--run_name="terminal_tasks" \
|
|
--distribution="terminal_tasks" \
|
|
--model="z-ai/glm-4.7" \
|
|
--base_url="https://openrouter.ai/api/v1" \
|
|
--providers_allowed="gmicloud,siliconflow,atlas-cloud,z-ai,novita" \
|
|
--num_workers=40 \
|
|
--max_turns=60 \
|
|
--ephemeral_system_prompt="You have access to a terminal tool for executing commands and completing coding, system administration, and computing tasks. Use the terminal to write code, run scripts, install packages (use --break-system-packages with pip if needed), manipulate files, and verify your work. Always test and validate code you create. Do not use interactive tools like vim, nano, or python REPL. If git output is large, pipe to cat. When web search is available, use it to look up documentation, APIs, or best practices. If browser tools are available, use them for web interactions that require page manipulation. Do not use the terminal to communicate with the user - only your final response will be shown to them." \
|
|
2>&1 | tee "$LOG_FILE"
|
|
|
|
echo "✅ Log saved to: $LOG_FILE"
|