- command:
    - docker exec leaderboard{{ gpu }} python lm-evaluation-harness/main.py --device cuda --no_cache --model hf-causal-experimental --model_args pretrained={{ model }},trust_remote_code=True,use_accelerate=True --tasks arc_challenge --num_fewshot 25 --output_path /data/leaderboard/benchmark/nlp/{{ replace model "/" "--" }}/arc_challenge.json
  model:
    - /data/leaderboard/weights/metaai/llama-7B
    - /data/leaderboard/weights/metaai/llama-13B
    - /data/leaderboard/weights/lmsys/vicuna-7B
    - /data/leaderboard/weights/lmsys/vicuna-13B
    - /data/leaderboard/weights/tatsu-lab/alpaca-7B
    - /data/leaderboard/weights/BAIR/koala-7b
    - /data/leaderboard/weights/BAIR/koala-13b
    - camel-ai/CAMEL-13B-Combined-Data
    - databricks/dolly-v2-12b
    - FreedomIntelligence/phoenix-inst-chat-7b
    - h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2
    - Neutralzz/BiLLa-7B-SFT
    - nomic-ai/gpt4all-13b-snoozy
    - openaccess-ai-collective/manticore-13b-chat-pyg
    - OpenAssistant/oasst-sft-1-pythia-12b
    - project-baize/baize-v2-7B
    - StabilityAI/stablelm-tuned-alpha-7b
    - togethercomputer/RedPajama-INCITE-7B-Chat
    - RWKV/rwkv-raven-7b
    - Salesforce/xgen-7b-8k-inst

- command:
    - docker exec leaderboard{{ gpu }} python lm-evaluation-harness/main.py --device cuda --no_cache --model hf-causal-experimental --model_args pretrained={{ model }},trust_remote_code=True,use_accelerate=True --tasks hellaswag --num_fewshot 10 --output_path /data/leaderboard/benchmark/nlp/{{ replace model "/" "--" }}/hellaswag.json
  model:
    - /data/leaderboard/weights/metaai/llama-7B
    - /data/leaderboard/weights/metaai/llama-13B
    - /data/leaderboard/weights/lmsys/vicuna-7B
    - /data/leaderboard/weights/lmsys/vicuna-13B
    - /data/leaderboard/weights/tatsu-lab/alpaca-7B
    - /data/leaderboard/weights/BAIR/koala-7b
    - /data/leaderboard/weights/BAIR/koala-13b
    - camel-ai/CAMEL-13B-Combined-Data
    - databricks/dolly-v2-12b
    - FreedomIntelligence/phoenix-inst-chat-7b
    - h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2
    - Neutralzz/BiLLa-7B-SFT
    - nomic-ai/gpt4all-13b-snoozy
    - openaccess-ai-collective/manticore-13b-chat-pyg
    - OpenAssistant/oasst-sft-1-pythia-12b
    - project-baize/baize-v2-7B
    - StabilityAI/stablelm-tuned-alpha-7b
    - togethercomputer/RedPajama-INCITE-7B-Chat
    - RWKV/rwkv-raven-7b
    - Salesforce/xgen-7b-8k-inst

- command:
    - docker exec leaderboard{{ gpu }} python lm-evaluation-harness/main.py --device cuda --no_cache --model hf-causal-experimental --model_args pretrained={{ model }},trust_remote_code=True,use_accelerate=True --tasks truthfulqa_mc --num_fewshot 0 --output_path /data/leaderboard/benchmark/nlp/{{ replace model "/" "--" }}/truthfulqa_mc.json
  model:
    - /data/leaderboard/weights/metaai/llama-7B
    - /data/leaderboard/weights/metaai/llama-13B
    - /data/leaderboard/weights/lmsys/vicuna-7B
    - /data/leaderboard/weights/lmsys/vicuna-13B
    - /data/leaderboard/weights/tatsu-lab/alpaca-7B
    - /data/leaderboard/weights/BAIR/koala-7b
    - /data/leaderboard/weights/BAIR/koala-13b
    - camel-ai/CAMEL-13B-Combined-Data
    - databricks/dolly-v2-12b
    - FreedomIntelligence/phoenix-inst-chat-7b
    - h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-7b-preview-300bt-v2
    - Neutralzz/BiLLa-7B-SFT
    - nomic-ai/gpt4all-13b-snoozy
    - openaccess-ai-collective/manticore-13b-chat-pyg
    - OpenAssistant/oasst-sft-1-pythia-12b
    - project-baize/baize-v2-7B
    - StabilityAI/stablelm-tuned-alpha-7b
    - togethercomputer/RedPajama-INCITE-7B-Chat
    - RWKV/rwkv-raven-7b
    - Salesforce/xgen-7b-8k-inst

- command:
    - docker exec leaderboard{{ gpu }} python lm-evaluation-harness/main.py --device cuda --no_cache --model hf-seq2seq --model_args pretrained={{ model }},trust_remote_code=True,use_accelerate=True --tasks arc_challenge --num_fewshot 25 --output_path /data/leaderboard/benchmark/nlp/{{ replace model "/" "--" }}/arc_challenge.json
    - docker exec leaderboard{{ gpu }} python lm-evaluation-harness/main.py --device cuda --no_cache --model hf-seq2seq --model_args pretrained={{ model }},trust_remote_code=True,use_accelerate=True --tasks hellaswag --num_fewshot 10 --output_path /data/leaderboard/benchmark/nlp/{{ replace model "/" "--" }}/hellaswag.json
    - docker exec leaderboard{{ gpu }} python lm-evaluation-harness/main.py --device cuda --no_cache --model hf-seq2seq --model_args pretrained={{ model }},trust_remote_code=True,use_accelerate=True --tasks truthfulqa_mc --num_fewshot 0 --output_path /data/leaderboard/benchmark/nlp/{{ replace model "/" "--" }}/truthfulqa_mc.json
  model:
    - lmsys/fastchat-t5-3b-v1.0