2026-02-07 09:17:16 +00:00
|
|
|
# SWE Environment -- Default Configuration
|
|
|
|
|
#
|
|
|
|
|
# SWE-bench style tasks with Modal sandboxes for cloud isolation.
|
|
|
|
|
# Uses terminal + file + web toolsets.
|
|
|
|
|
#
|
|
|
|
|
# Usage:
|
2026-02-10 19:39:05 +00:00
|
|
|
# python environments/hermes_swe_env/hermes_swe_env.py serve \
|
|
|
|
|
# --config environments/hermes_swe_env/default.yaml
|
2026-02-07 09:17:16 +00:00
|
|
|
|
|
|
|
|
env:
|
|
|
|
|
enabled_toolsets: ["terminal", "file", "web"]
|
|
|
|
|
max_agent_turns: 30
|
|
|
|
|
max_token_length: 4096
|
|
|
|
|
group_size: 4
|
|
|
|
|
terminal_backend: "modal"
|
|
|
|
|
tool_call_parser: "hermes"
|
|
|
|
|
tokenizer_name: "NousResearch/DeepHermes-3-Llama-3-3B-Preview"
|
|
|
|
|
dataset_name: "bigcode/humanevalpack"
|
|
|
|
|
dataset_split: "test"
|
|
|
|
|
prompt_field: "prompt"
|
|
|
|
|
steps_per_eval: 50
|
|
|
|
|
total_steps: 500
|
|
|
|
|
use_wandb: true
|
|
|
|
|
wandb_name: "hermes-swe"
|
|
|
|
|
system_prompt: >
|
|
|
|
|
You are a skilled software engineer. You have access to a terminal,
|
|
|
|
|
file tools, and web search. Use these tools to complete the coding task.
|
|
|
|
|
Write clean, working code and verify it runs correctly before finishing.
|
|
|
|
|
|
|
|
|
|
openai:
|
|
|
|
|
base_url: "http://localhost:8000/v1"
|
|
|
|
|
model_name: "NousResearch/DeepHermes-3-Llama-3-3B-Preview"
|
|
|
|
|
server_type: "openai"
|
|
|
|
|
api_key: ""
|
