├── README.md ├── eval_gsm8k_few_shot.py ├── eval_gsm8k_zero_shot.py ├── eval_results ├── few_shot │ ├── Llama-2-7b-hf_results.json │ ├── Mistral-7B-v0.1_maj1@8_temp0.2_results.json │ ├── Mistral-7B-v0.1_maj1@8_temp0.4_results.json │ └── Mistral-7B-v0.1_results.json └── zero_shot │ ├── Mistral-7B-v0.1_cot_results.json │ └── Mistral-7B-v0.1_results.json └── utils.py /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianlwang/eval_gsm8k/HEAD/README.md -------------------------------------------------------------------------------- /eval_gsm8k_few_shot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianlwang/eval_gsm8k/HEAD/eval_gsm8k_few_shot.py -------------------------------------------------------------------------------- /eval_gsm8k_zero_shot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianlwang/eval_gsm8k/HEAD/eval_gsm8k_zero_shot.py -------------------------------------------------------------------------------- /eval_results/few_shot/Llama-2-7b-hf_results.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianlwang/eval_gsm8k/HEAD/eval_results/few_shot/Llama-2-7b-hf_results.json -------------------------------------------------------------------------------- /eval_results/few_shot/Mistral-7B-v0.1_maj1@8_temp0.2_results.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianlwang/eval_gsm8k/HEAD/eval_results/few_shot/Mistral-7B-v0.1_maj1@8_temp0.2_results.json -------------------------------------------------------------------------------- /eval_results/few_shot/Mistral-7B-v0.1_maj1@8_temp0.4_results.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianlwang/eval_gsm8k/HEAD/eval_results/few_shot/Mistral-7B-v0.1_maj1@8_temp0.4_results.json -------------------------------------------------------------------------------- /eval_results/few_shot/Mistral-7B-v0.1_results.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianlwang/eval_gsm8k/HEAD/eval_results/few_shot/Mistral-7B-v0.1_results.json -------------------------------------------------------------------------------- /eval_results/zero_shot/Mistral-7B-v0.1_cot_results.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianlwang/eval_gsm8k/HEAD/eval_results/zero_shot/Mistral-7B-v0.1_cot_results.json -------------------------------------------------------------------------------- /eval_results/zero_shot/Mistral-7B-v0.1_results.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianlwang/eval_gsm8k/HEAD/eval_results/zero_shot/Mistral-7B-v0.1_results.json -------------------------------------------------------------------------------- /utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianlwang/eval_gsm8k/HEAD/utils.py --------------------------------------------------------------------------------