├── .gitignore ├── LICENSE ├── README.md ├── data_utils.py ├── eval_template.md ├── eval_utils.py ├── evaluate.py ├── fastchat_conversation.py ├── instruct_template.md ├── merge_json.py ├── model_outputs ├── Llama-2-7b-chat-hf.json ├── Mixtral-8x7B-Instruct-v0.1.json ├── Pallas-0.5.json ├── TurnOpt.json ├── Yi-34b-chat.json ├── Yi-6b-chat.json ├── gpt-3.5-turbo.json ├── gpt-4-0613.json ├── gpt-4-1106-preview.json ├── tulu-2-dpo-70b.json ├── vicuna-13b-v1.5.json └── zephyr-7b-beta.json ├── requirements.txt ├── scripts ├── Llama-2-7b-chat-hf.sh ├── Mixtral-8x7B-Instruct-v0.1.sh ├── Pallas-0.5.sh ├── Yi-34b-chat.sh ├── Yi-6b-chat.sh ├── all_gpt_eval.sh ├── gpt-3.5-turbo.sh ├── gpt-4-0613.sh ├── gpt-4-1106-preview.sh ├── tulu-2-dpo-70b.sh ├── vicuna-13b-v1.5.sh └── zephyr-7b-beta.sh ├── show_cases.py ├── show_table.py └── vllm_infer.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/README.md -------------------------------------------------------------------------------- /data_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/data_utils.py -------------------------------------------------------------------------------- /eval_template.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/eval_template.md -------------------------------------------------------------------------------- /eval_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/eval_utils.py -------------------------------------------------------------------------------- /evaluate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/evaluate.py -------------------------------------------------------------------------------- /fastchat_conversation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/fastchat_conversation.py -------------------------------------------------------------------------------- /instruct_template.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/instruct_template.md -------------------------------------------------------------------------------- /merge_json.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/merge_json.py -------------------------------------------------------------------------------- /model_outputs/Llama-2-7b-chat-hf.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/model_outputs/Llama-2-7b-chat-hf.json -------------------------------------------------------------------------------- /model_outputs/Mixtral-8x7B-Instruct-v0.1.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/model_outputs/Mixtral-8x7B-Instruct-v0.1.json -------------------------------------------------------------------------------- /model_outputs/Pallas-0.5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/model_outputs/Pallas-0.5.json -------------------------------------------------------------------------------- /model_outputs/TurnOpt.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/model_outputs/TurnOpt.json -------------------------------------------------------------------------------- /model_outputs/Yi-34b-chat.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/model_outputs/Yi-34b-chat.json -------------------------------------------------------------------------------- /model_outputs/Yi-6b-chat.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/model_outputs/Yi-6b-chat.json -------------------------------------------------------------------------------- /model_outputs/gpt-3.5-turbo.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/model_outputs/gpt-3.5-turbo.json -------------------------------------------------------------------------------- /model_outputs/gpt-4-0613.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/model_outputs/gpt-4-0613.json -------------------------------------------------------------------------------- /model_outputs/gpt-4-1106-preview.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/model_outputs/gpt-4-1106-preview.json -------------------------------------------------------------------------------- /model_outputs/tulu-2-dpo-70b.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/model_outputs/tulu-2-dpo-70b.json -------------------------------------------------------------------------------- /model_outputs/vicuna-13b-v1.5.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/model_outputs/vicuna-13b-v1.5.json -------------------------------------------------------------------------------- /model_outputs/zephyr-7b-beta.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/model_outputs/zephyr-7b-beta.json -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/requirements.txt -------------------------------------------------------------------------------- /scripts/Llama-2-7b-chat-hf.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/scripts/Llama-2-7b-chat-hf.sh -------------------------------------------------------------------------------- /scripts/Mixtral-8x7B-Instruct-v0.1.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/scripts/Mixtral-8x7B-Instruct-v0.1.sh -------------------------------------------------------------------------------- /scripts/Pallas-0.5.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/scripts/Pallas-0.5.sh -------------------------------------------------------------------------------- /scripts/Yi-34b-chat.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/scripts/Yi-34b-chat.sh -------------------------------------------------------------------------------- /scripts/Yi-6b-chat.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/scripts/Yi-6b-chat.sh -------------------------------------------------------------------------------- /scripts/all_gpt_eval.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/scripts/all_gpt_eval.sh -------------------------------------------------------------------------------- /scripts/gpt-3.5-turbo.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/scripts/gpt-3.5-turbo.sh -------------------------------------------------------------------------------- /scripts/gpt-4-0613.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/scripts/gpt-4-0613.sh -------------------------------------------------------------------------------- /scripts/gpt-4-1106-preview.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/scripts/gpt-4-1106-preview.sh -------------------------------------------------------------------------------- /scripts/tulu-2-dpo-70b.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/scripts/tulu-2-dpo-70b.sh -------------------------------------------------------------------------------- /scripts/vicuna-13b-v1.5.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/scripts/vicuna-13b-v1.5.sh -------------------------------------------------------------------------------- /scripts/zephyr-7b-beta.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/scripts/zephyr-7b-beta.sh -------------------------------------------------------------------------------- /show_cases.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/show_cases.py -------------------------------------------------------------------------------- /show_table.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/show_table.py -------------------------------------------------------------------------------- /vllm_infer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/allenai/CommonGen-Eval/HEAD/vllm_infer.py --------------------------------------------------------------------------------