Spaces:
Running
Running
File size: 4,615 Bytes
862fdcc dcc2472 862fdcc b08a0ac 862fdcc dcc2472 862fdcc b08a0ac 862fdcc dcc2472 862fdcc b08a0ac 4fc7206 dcc2472 b559f9a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 |
- 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
- 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
- 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
- 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
|