Move BLEUBERI environment to community folder

- Moved environments/bleuberi to environments/community/bleuberi
      - Updated .gitmodules to reflect new submodule path
      - Fixed pre-commit formatting issues
      - Cleaned up test output files

environments/bleuberi/configs/default.yaml

@@ -1,41 +0,0 @@
-env:
-  wandb_name: bleuberi
-  group_size: 4
-  max_token_length: 2048
-  max_num_workers_per_node: 8
-  steps_per_eval: 100
-  total_steps: 1000
-  include_messages: true
-
-  # Dataset configuration
-  dataset_name: "allenai/tulu-3-sft-mixture"
-  dataset_split: "train"
-  selection_mode: "hard"
-  num_examples: 5000
-  cache_dir: null
-  streaming: false
-  shuffle: true
-
-  # Reward configuration
-  reward_funcs:
-    - "bleu"
-  ref_models:
-    - "gold"  # Use ground truth as reference
-
-  # System prompt configuration
-  system_prompt: "You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem. After your thinking, make sure to clearly provide your final answer inside <answer></answer> tags."
-
-  # Seeds and evaluation
-  seed: 42
-  eval_seed: 123
-  num_eval_samples_per_task: 5
-  eval_limit_ratio: 0.1
-  reasoning: true
-
-openai:
-  base_url: "http://localhost:8000/v1"
-  model: "Llama-3.1-8B-Instruct"
-  api_key: "PLACEHOLDER"
-  temperature: 0.7
-  max_tokens: 1024
-  top_p: 0.95