├── .gitignore ├── Dockerfile ├── LICENSE ├── README.md ├── assets ├── .gitignore ├── 01-ai │ ├── Yi-34B-Chat-4bits │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ └── Yi-6B-Chat │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── CohereForAI │ ├── c4ai-command-r-plus │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ └── c4ai-command-r-plus_gguf-iq2m-hf │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── Deepreneur │ └── blue-lizard │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── Fugaku-LLM │ ├── Fugaku-LLM-13B-instruct-gpt4o │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ └── Fugaku-LLM-13B-instruct │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── NTQAI │ └── chatntq-ja-7b-v1.0 │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── NexusFlow │ └── Starling-LM-7B-beta │ │ ├── dataset.jsonl │ │ ├── preds.jsonl │ │ └── tmp.jsonl ├── OrionStarAI │ └── Orion-14B-Chat │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── SakanaAI │ ├── EvoLLM-JP-A-v1-7B-gguf-q4km-hf │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── EvoLLM-JP-A-v1-7B │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── EvoLLM-JP-A-v1-7B_do_sample │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── EvoLLM-JP-v1-10B │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── EvoLLM-JP-v1-10B_do_sample │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── EvoLLM-JP-v1-7B-gguf-q4km-hf │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── EvoLLM-JP-v1-7B │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ └── EvoLLM-JP-v1-7B_do_sample │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── TFMC │ ├── Japanese-Starling-ChatV-7B-bfloat16 │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ └── Japanese-Starling-ChatV-7B │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── Weyaxi │ └── OpenHermes-2.5-neural-chat-7b-v3-1-7B │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── Xwin-LM │ ├── Xwin-LM-13B-V0.1-gguf-q4km-hf │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── Xwin-LM-13B-V0.1 │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── Xwin-LM-70B-V0.1 │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── Xwin-LM-7B-V0.1-gguf-q4km-hf │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ └── Xwin-LM-7B-V0.1 │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── aixsatoshi │ ├── Llama-3-youko-8b-instruct-chatvector │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── Mixtral-8x7B-ja-Lora-sft-ChatbotArenaJAcalm2-claude │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ └── Mixtral-8x7B-ja-Lora-sft-ChatbotArenaJAcalm2-elyza │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── apple │ └── OpenELM-3B-Instruct │ │ ├── dataset.jsonl │ │ ├── preds.jsonl │ │ └── preds_orig.jsonl ├── augmxnt │ └── shisa-7b-v1 │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── biomistral │ └── biomistral-7b │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── cyberagent │ ├── calm2-7b-chat-gguf-q4km-hf │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── calm2-7b-chat │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ └── calm2-7b-chat_cmdr+ │ │ ├── dataset.jsonl │ │ ├── preds.jsonl │ │ ├── result_take1.jsonl │ │ ├── result_take2.jsonl │ │ └── result_take3.jsonl ├── deepseek-ai │ ├── deepseek-llm-67b-chat-GGUF_TheBloke │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ └── deepseek-llm-7b-chat │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── elyza │ ├── ELYZA-japanese-Llama-2-13b-instruct-gguf-q4km-hf │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── ELYZA-japanese-Llama-2-13b-instruct │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── ELYZA-japanese-Llama-2-7b-instruct-gguf-q4km-hf │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ └── ELYZA-japanese-Llama-2-7b-instruct │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── elyza_tasks_100 │ └── dataset.jsonl ├── karakuri-ai │ ├── karakuri-lm-70b-chat-v0.1-gguf-q4km-hf │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── karakuri-lm-70b-chat-v0.1-gguf-q4km-hf_cmdr+ │ │ ├── dataset.jsonl │ │ ├── preds.jsonl │ │ ├── result_take1.jsonl │ │ ├── result_take2.jsonl │ │ └── result_take3.jsonl │ └── karakuri-lm-8x7b-chat-v0.1-gguf-iq3xxs-hf │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── llm-jp │ ├── llm-jp-13b-instruct-full-dolly-oasst-v1.0 │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ └── llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0 │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── meta-llama │ ├── Meta-Llama-3-70B-Instruct-gguf-q4km │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ └── Meta-Llama-3-8B-Instruct │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── meta-math │ └── MetaMath-Mistral-7B │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── microsoft │ ├── Phi-3-medium-128k-instruct │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── Phi-3-mini-128k-instruct-en │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── Phi-3-mini-128k-instruct │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── Phi-3-small-128k-instruct │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ └── Phi-3-small-128k-instruct_gpt-4o │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── nssv │ ├── 20240423_biomistral_stableLM-instruct-gamma-7b_0.5 │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── 20240423_biomistral_stableLM-instruct-gamma-7b_1.0 │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── 20240423_metamath_stableLM-instruct-gamma-7b_0.5_prompt-ja │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── 20240423_metamath_stableLM-instruct-gamma-7b_1.0_prompt-ja │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── 20240501_llama2_qlora │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── 20240507_swallow-7b-instruct-v0.1_meditron_0.5 │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── 20240507_swallow-7b-instruct-v0.1_meditron_1.0 │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── japanese-stablelm-instruct-beta-7b_dpo_distilabel-intel-orca │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── japanese-stablelm-instruct-beta-7b_dpo_hh-rlhf │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ └── tfmc-biomistral_1.0-7B │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── openchat │ ├── openchat-3.5-0106 │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ └── openchat-3.5-1210 │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── prompt_eval.txt ├── prompt_eval_cohere.txt ├── rinna │ ├── llama-3-youko-8b │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── youri-7b-chat-gguf-q4km-hf │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ └── youri-7b-chat │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── stabilityai │ ├── japanese-stablelm-base-beta-70b-GGUF_TheBloke │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── japanese-stablelm-instruct-beta-7b-gguf-q4km-hf │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── japanese-stablelm-instruct-beta-7b-gpt3.5 │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ ├── japanese-stablelm-instruct-beta-7b │ │ ├── dataset.jsonl │ │ └── preds.jsonl │ └── japanese-stablelm-instruct-gamma-7b │ │ ├── dataset.jsonl │ │ └── preds.jsonl ├── test │ ├── dataset.jsonl │ └── preds.jsonl └── tokyotech-llm │ ├── Swallow-13b-instruct-gguf-q4km-hf │ ├── dataset.jsonl │ └── preds.jsonl │ ├── Swallow-13b-instruct │ ├── dataset.jsonl │ └── preds.jsonl │ ├── Swallow-70b-instruct │ ├── dataset.jsonl │ ├── preds.jsonl │ ├── raw.txt │ └── raw_to_jsonl.py │ ├── Swallow-7b-instruct-gguf-q4km-hf │ ├── dataset.jsonl │ └── preds.jsonl │ ├── Swallow-7b-instruct-v0.1 │ ├── dataset.jsonl │ └── preds.jsonl │ ├── Swallow-7b-instruct │ ├── dataset.jsonl │ └── preds.jsonl │ ├── Swallow-7b-instruct_cmdr+ │ ├── dataset.jsonl │ ├── preds.jsonl │ ├── result_take1.jsonl │ ├── result_take2.jsonl │ └── result_take3.jsonl │ ├── Swallow-7b-plus-hf │ ├── dataset.jsonl │ └── preds.jsonl │ ├── Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude-sys │ ├── dataset.jsonl │ └── preds.jsonl │ ├── Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude-sysml │ ├── dataset.jsonl │ └── preds.jsonl │ ├── Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude-v2 │ └── preds.jsonl │ ├── Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude │ ├── dataset.jsonl │ └── preds.jsonl │ ├── Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-elyza │ ├── dataset.jsonl │ └── preds.jsonl │ ├── Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-mixtral │ ├── dataset.jsonl │ └── preds.jsonl │ └── Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-vanilla │ ├── dataset.jsonl │ └── preds.jsonl ├── compose.yml ├── notebooks ├── ELYZA_tasks_100_inference_01_ai_Yi_34B_Chat_4bits.ipynb ├── ELYZA_tasks_100_inference_01_ai_Yi_6B_Chat.ipynb ├── ELYZA_tasks_100_inference_Weyaxi_OpenHermes_2_5_neural_chat_7b_v3_1_7B.ipynb ├── ELYZA_tasks_100_inference_Xwin_LM_Xwin_LM_13B_V0_1.ipynb ├── ELYZA_tasks_100_inference_Xwin_LM_Xwin_LM_70B_V0_1.ipynb ├── ELYZA_tasks_100_inference_Xwin_LM_Xwin_LM_7B_V0_1.ipynb ├── ELYZA_tasks_100_inference_augmxnt_shisa_7b_v1.ipynb ├── ELYZA_tasks_100_inference_cyberagent_calm2_7b_chat.ipynb ├── ELYZA_tasks_100_inference_deepseek_ai_deepseek_llm_7b_chat.ipynb ├── ELYZA_tasks_100_inference_deepseek_deepseek_llm_67b_chat_GGUF_TheBloke.ipynb ├── ELYZA_tasks_100_inference_elyza_ELYZA_japanese_Llama_2_7b_instruct.ipynb ├── ELYZA_tasks_100_inference_llm_jp_llm_jp_13b_instruct_full_dolly_oasst_v1_0.ipynb ├── ELYZA_tasks_100_inference_openchat_openchat_3_5_1210.ipynb ├── ELYZA_tasks_100_inference_rinna_youri_7b_chat.ipynb ├── ELYZA_tasks_100_inference_stabilityai_japanese_stablelm_instruct_beta_70b.ipynb ├── ELYZA_tasks_100_inference_stabilityai_japanese_stablelm_instruct_beta_7b.ipynb ├── ELYZA_tasks_100_inference_tokyotech_llm_Swallow_13b_instruct_hf.ipynb ├── ELYZA_tasks_100_inference_tokyotech_llm_Swallow_70B_Instruct_GGUF_.ipynb └── ELYZA_tasks_100_inference_tokyotech_llm_Swallow_7b_instruct_hf.ipynb ├── requirements.txt ├── secrets └── .gitkeep ├── src ├── download_elyza.py ├── judges │ ├── cohere │ │ └── command_r_plus │ │ │ ├── cmdr_plus_judge.py │ │ │ └── sequential_process.py │ └── openai │ │ └── gpt_4 │ │ ├── batch_retrieve.py │ │ ├── batch_submit.py │ │ ├── openai_judge.py │ │ └── sequential_process.py ├── lib │ ├── client_cohere.py │ ├── client_openai.py │ └── common.py └── main.py └── tools └── copy_jsonl_to_google_spreadsheet.js /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/.gitignore -------------------------------------------------------------------------------- /Dockerfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/Dockerfile -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/README.md -------------------------------------------------------------------------------- /assets/.gitignore: -------------------------------------------------------------------------------- 1 | result.jsonl 2 | -------------------------------------------------------------------------------- /assets/01-ai/Yi-34B-Chat-4bits/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/01-ai/Yi-34B-Chat-4bits/dataset.jsonl -------------------------------------------------------------------------------- /assets/01-ai/Yi-34B-Chat-4bits/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/01-ai/Yi-34B-Chat-4bits/preds.jsonl -------------------------------------------------------------------------------- /assets/01-ai/Yi-6B-Chat/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/01-ai/Yi-6B-Chat/dataset.jsonl -------------------------------------------------------------------------------- /assets/01-ai/Yi-6B-Chat/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/01-ai/Yi-6B-Chat/preds.jsonl -------------------------------------------------------------------------------- /assets/CohereForAI/c4ai-command-r-plus/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/CohereForAI/c4ai-command-r-plus/dataset.jsonl -------------------------------------------------------------------------------- /assets/CohereForAI/c4ai-command-r-plus/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/CohereForAI/c4ai-command-r-plus/preds.jsonl -------------------------------------------------------------------------------- /assets/CohereForAI/c4ai-command-r-plus_gguf-iq2m-hf/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/CohereForAI/c4ai-command-r-plus_gguf-iq2m-hf/dataset.jsonl -------------------------------------------------------------------------------- /assets/CohereForAI/c4ai-command-r-plus_gguf-iq2m-hf/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/CohereForAI/c4ai-command-r-plus_gguf-iq2m-hf/preds.jsonl -------------------------------------------------------------------------------- /assets/Deepreneur/blue-lizard/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Deepreneur/blue-lizard/dataset.jsonl -------------------------------------------------------------------------------- /assets/Deepreneur/blue-lizard/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Deepreneur/blue-lizard/preds.jsonl -------------------------------------------------------------------------------- /assets/Fugaku-LLM/Fugaku-LLM-13B-instruct-gpt4o/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Fugaku-LLM/Fugaku-LLM-13B-instruct-gpt4o/dataset.jsonl -------------------------------------------------------------------------------- /assets/Fugaku-LLM/Fugaku-LLM-13B-instruct-gpt4o/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Fugaku-LLM/Fugaku-LLM-13B-instruct-gpt4o/preds.jsonl -------------------------------------------------------------------------------- /assets/Fugaku-LLM/Fugaku-LLM-13B-instruct/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Fugaku-LLM/Fugaku-LLM-13B-instruct/dataset.jsonl -------------------------------------------------------------------------------- /assets/Fugaku-LLM/Fugaku-LLM-13B-instruct/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Fugaku-LLM/Fugaku-LLM-13B-instruct/preds.jsonl -------------------------------------------------------------------------------- /assets/NTQAI/chatntq-ja-7b-v1.0/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/NTQAI/chatntq-ja-7b-v1.0/dataset.jsonl -------------------------------------------------------------------------------- /assets/NTQAI/chatntq-ja-7b-v1.0/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/NTQAI/chatntq-ja-7b-v1.0/preds.jsonl -------------------------------------------------------------------------------- /assets/NexusFlow/Starling-LM-7B-beta/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/NexusFlow/Starling-LM-7B-beta/dataset.jsonl -------------------------------------------------------------------------------- /assets/NexusFlow/Starling-LM-7B-beta/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/NexusFlow/Starling-LM-7B-beta/preds.jsonl -------------------------------------------------------------------------------- /assets/NexusFlow/Starling-LM-7B-beta/tmp.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/NexusFlow/Starling-LM-7B-beta/tmp.jsonl -------------------------------------------------------------------------------- /assets/OrionStarAI/Orion-14B-Chat/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/OrionStarAI/Orion-14B-Chat/dataset.jsonl -------------------------------------------------------------------------------- /assets/OrionStarAI/Orion-14B-Chat/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/OrionStarAI/Orion-14B-Chat/preds.jsonl -------------------------------------------------------------------------------- /assets/SakanaAI/EvoLLM-JP-A-v1-7B-gguf-q4km-hf/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/SakanaAI/EvoLLM-JP-A-v1-7B-gguf-q4km-hf/dataset.jsonl -------------------------------------------------------------------------------- /assets/SakanaAI/EvoLLM-JP-A-v1-7B-gguf-q4km-hf/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/SakanaAI/EvoLLM-JP-A-v1-7B-gguf-q4km-hf/preds.jsonl -------------------------------------------------------------------------------- /assets/SakanaAI/EvoLLM-JP-A-v1-7B/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/SakanaAI/EvoLLM-JP-A-v1-7B/dataset.jsonl -------------------------------------------------------------------------------- /assets/SakanaAI/EvoLLM-JP-A-v1-7B/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/SakanaAI/EvoLLM-JP-A-v1-7B/preds.jsonl -------------------------------------------------------------------------------- /assets/SakanaAI/EvoLLM-JP-A-v1-7B_do_sample/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/SakanaAI/EvoLLM-JP-A-v1-7B_do_sample/dataset.jsonl -------------------------------------------------------------------------------- /assets/SakanaAI/EvoLLM-JP-A-v1-7B_do_sample/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/SakanaAI/EvoLLM-JP-A-v1-7B_do_sample/preds.jsonl -------------------------------------------------------------------------------- /assets/SakanaAI/EvoLLM-JP-v1-10B/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/SakanaAI/EvoLLM-JP-v1-10B/dataset.jsonl -------------------------------------------------------------------------------- /assets/SakanaAI/EvoLLM-JP-v1-10B/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/SakanaAI/EvoLLM-JP-v1-10B/preds.jsonl -------------------------------------------------------------------------------- /assets/SakanaAI/EvoLLM-JP-v1-10B_do_sample/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/SakanaAI/EvoLLM-JP-v1-10B_do_sample/dataset.jsonl -------------------------------------------------------------------------------- /assets/SakanaAI/EvoLLM-JP-v1-10B_do_sample/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/SakanaAI/EvoLLM-JP-v1-10B_do_sample/preds.jsonl -------------------------------------------------------------------------------- /assets/SakanaAI/EvoLLM-JP-v1-7B-gguf-q4km-hf/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/SakanaAI/EvoLLM-JP-v1-7B-gguf-q4km-hf/dataset.jsonl -------------------------------------------------------------------------------- /assets/SakanaAI/EvoLLM-JP-v1-7B-gguf-q4km-hf/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/SakanaAI/EvoLLM-JP-v1-7B-gguf-q4km-hf/preds.jsonl -------------------------------------------------------------------------------- /assets/SakanaAI/EvoLLM-JP-v1-7B/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/SakanaAI/EvoLLM-JP-v1-7B/dataset.jsonl -------------------------------------------------------------------------------- /assets/SakanaAI/EvoLLM-JP-v1-7B/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/SakanaAI/EvoLLM-JP-v1-7B/preds.jsonl -------------------------------------------------------------------------------- /assets/SakanaAI/EvoLLM-JP-v1-7B_do_sample/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/SakanaAI/EvoLLM-JP-v1-7B_do_sample/dataset.jsonl -------------------------------------------------------------------------------- /assets/SakanaAI/EvoLLM-JP-v1-7B_do_sample/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/SakanaAI/EvoLLM-JP-v1-7B_do_sample/preds.jsonl -------------------------------------------------------------------------------- /assets/TFMC/Japanese-Starling-ChatV-7B-bfloat16/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/TFMC/Japanese-Starling-ChatV-7B-bfloat16/dataset.jsonl -------------------------------------------------------------------------------- /assets/TFMC/Japanese-Starling-ChatV-7B-bfloat16/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/TFMC/Japanese-Starling-ChatV-7B-bfloat16/preds.jsonl -------------------------------------------------------------------------------- /assets/TFMC/Japanese-Starling-ChatV-7B/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/TFMC/Japanese-Starling-ChatV-7B/dataset.jsonl -------------------------------------------------------------------------------- /assets/TFMC/Japanese-Starling-ChatV-7B/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/TFMC/Japanese-Starling-ChatV-7B/preds.jsonl -------------------------------------------------------------------------------- /assets/Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-1-7B/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-1-7B/dataset.jsonl -------------------------------------------------------------------------------- /assets/Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-1-7B/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Weyaxi/OpenHermes-2.5-neural-chat-7b-v3-1-7B/preds.jsonl -------------------------------------------------------------------------------- /assets/Xwin-LM/Xwin-LM-13B-V0.1-gguf-q4km-hf/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Xwin-LM/Xwin-LM-13B-V0.1-gguf-q4km-hf/dataset.jsonl -------------------------------------------------------------------------------- /assets/Xwin-LM/Xwin-LM-13B-V0.1-gguf-q4km-hf/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Xwin-LM/Xwin-LM-13B-V0.1-gguf-q4km-hf/preds.jsonl -------------------------------------------------------------------------------- /assets/Xwin-LM/Xwin-LM-13B-V0.1/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Xwin-LM/Xwin-LM-13B-V0.1/dataset.jsonl -------------------------------------------------------------------------------- /assets/Xwin-LM/Xwin-LM-13B-V0.1/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Xwin-LM/Xwin-LM-13B-V0.1/preds.jsonl -------------------------------------------------------------------------------- /assets/Xwin-LM/Xwin-LM-70B-V0.1/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Xwin-LM/Xwin-LM-70B-V0.1/dataset.jsonl -------------------------------------------------------------------------------- /assets/Xwin-LM/Xwin-LM-70B-V0.1/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Xwin-LM/Xwin-LM-70B-V0.1/preds.jsonl -------------------------------------------------------------------------------- /assets/Xwin-LM/Xwin-LM-7B-V0.1-gguf-q4km-hf/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Xwin-LM/Xwin-LM-7B-V0.1-gguf-q4km-hf/dataset.jsonl -------------------------------------------------------------------------------- /assets/Xwin-LM/Xwin-LM-7B-V0.1-gguf-q4km-hf/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Xwin-LM/Xwin-LM-7B-V0.1-gguf-q4km-hf/preds.jsonl -------------------------------------------------------------------------------- /assets/Xwin-LM/Xwin-LM-7B-V0.1/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Xwin-LM/Xwin-LM-7B-V0.1/dataset.jsonl -------------------------------------------------------------------------------- /assets/Xwin-LM/Xwin-LM-7B-V0.1/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/Xwin-LM/Xwin-LM-7B-V0.1/preds.jsonl -------------------------------------------------------------------------------- /assets/aixsatoshi/Llama-3-youko-8b-instruct-chatvector/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/aixsatoshi/Llama-3-youko-8b-instruct-chatvector/dataset.jsonl -------------------------------------------------------------------------------- /assets/aixsatoshi/Llama-3-youko-8b-instruct-chatvector/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/aixsatoshi/Llama-3-youko-8b-instruct-chatvector/preds.jsonl -------------------------------------------------------------------------------- /assets/aixsatoshi/Mixtral-8x7B-ja-Lora-sft-ChatbotArenaJAcalm2-claude/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/aixsatoshi/Mixtral-8x7B-ja-Lora-sft-ChatbotArenaJAcalm2-claude/dataset.jsonl -------------------------------------------------------------------------------- /assets/aixsatoshi/Mixtral-8x7B-ja-Lora-sft-ChatbotArenaJAcalm2-claude/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/aixsatoshi/Mixtral-8x7B-ja-Lora-sft-ChatbotArenaJAcalm2-claude/preds.jsonl -------------------------------------------------------------------------------- /assets/aixsatoshi/Mixtral-8x7B-ja-Lora-sft-ChatbotArenaJAcalm2-elyza/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/aixsatoshi/Mixtral-8x7B-ja-Lora-sft-ChatbotArenaJAcalm2-elyza/dataset.jsonl -------------------------------------------------------------------------------- /assets/aixsatoshi/Mixtral-8x7B-ja-Lora-sft-ChatbotArenaJAcalm2-elyza/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/aixsatoshi/Mixtral-8x7B-ja-Lora-sft-ChatbotArenaJAcalm2-elyza/preds.jsonl -------------------------------------------------------------------------------- /assets/apple/OpenELM-3B-Instruct/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/apple/OpenELM-3B-Instruct/dataset.jsonl -------------------------------------------------------------------------------- /assets/apple/OpenELM-3B-Instruct/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/apple/OpenELM-3B-Instruct/preds.jsonl -------------------------------------------------------------------------------- /assets/apple/OpenELM-3B-Instruct/preds_orig.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/apple/OpenELM-3B-Instruct/preds_orig.jsonl -------------------------------------------------------------------------------- /assets/augmxnt/shisa-7b-v1/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/augmxnt/shisa-7b-v1/dataset.jsonl -------------------------------------------------------------------------------- /assets/augmxnt/shisa-7b-v1/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/augmxnt/shisa-7b-v1/preds.jsonl -------------------------------------------------------------------------------- /assets/biomistral/biomistral-7b/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/biomistral/biomistral-7b/dataset.jsonl -------------------------------------------------------------------------------- /assets/biomistral/biomistral-7b/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/biomistral/biomistral-7b/preds.jsonl -------------------------------------------------------------------------------- /assets/cyberagent/calm2-7b-chat-gguf-q4km-hf/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/cyberagent/calm2-7b-chat-gguf-q4km-hf/dataset.jsonl -------------------------------------------------------------------------------- /assets/cyberagent/calm2-7b-chat-gguf-q4km-hf/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/cyberagent/calm2-7b-chat-gguf-q4km-hf/preds.jsonl -------------------------------------------------------------------------------- /assets/cyberagent/calm2-7b-chat/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/cyberagent/calm2-7b-chat/dataset.jsonl -------------------------------------------------------------------------------- /assets/cyberagent/calm2-7b-chat/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/cyberagent/calm2-7b-chat/preds.jsonl -------------------------------------------------------------------------------- /assets/cyberagent/calm2-7b-chat_cmdr+/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/cyberagent/calm2-7b-chat_cmdr+/dataset.jsonl -------------------------------------------------------------------------------- /assets/cyberagent/calm2-7b-chat_cmdr+/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/cyberagent/calm2-7b-chat_cmdr+/preds.jsonl -------------------------------------------------------------------------------- /assets/cyberagent/calm2-7b-chat_cmdr+/result_take1.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/cyberagent/calm2-7b-chat_cmdr+/result_take1.jsonl -------------------------------------------------------------------------------- /assets/cyberagent/calm2-7b-chat_cmdr+/result_take2.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/cyberagent/calm2-7b-chat_cmdr+/result_take2.jsonl -------------------------------------------------------------------------------- /assets/cyberagent/calm2-7b-chat_cmdr+/result_take3.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/cyberagent/calm2-7b-chat_cmdr+/result_take3.jsonl -------------------------------------------------------------------------------- /assets/deepseek-ai/deepseek-llm-67b-chat-GGUF_TheBloke/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/deepseek-ai/deepseek-llm-67b-chat-GGUF_TheBloke/dataset.jsonl -------------------------------------------------------------------------------- /assets/deepseek-ai/deepseek-llm-67b-chat-GGUF_TheBloke/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/deepseek-ai/deepseek-llm-67b-chat-GGUF_TheBloke/preds.jsonl -------------------------------------------------------------------------------- /assets/deepseek-ai/deepseek-llm-7b-chat/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/deepseek-ai/deepseek-llm-7b-chat/dataset.jsonl -------------------------------------------------------------------------------- /assets/deepseek-ai/deepseek-llm-7b-chat/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/deepseek-ai/deepseek-llm-7b-chat/preds.jsonl -------------------------------------------------------------------------------- /assets/elyza/ELYZA-japanese-Llama-2-13b-instruct-gguf-q4km-hf/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/elyza/ELYZA-japanese-Llama-2-13b-instruct-gguf-q4km-hf/dataset.jsonl -------------------------------------------------------------------------------- /assets/elyza/ELYZA-japanese-Llama-2-13b-instruct-gguf-q4km-hf/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/elyza/ELYZA-japanese-Llama-2-13b-instruct-gguf-q4km-hf/preds.jsonl -------------------------------------------------------------------------------- /assets/elyza/ELYZA-japanese-Llama-2-13b-instruct/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/elyza/ELYZA-japanese-Llama-2-13b-instruct/dataset.jsonl -------------------------------------------------------------------------------- /assets/elyza/ELYZA-japanese-Llama-2-13b-instruct/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/elyza/ELYZA-japanese-Llama-2-13b-instruct/preds.jsonl -------------------------------------------------------------------------------- /assets/elyza/ELYZA-japanese-Llama-2-7b-instruct-gguf-q4km-hf/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/elyza/ELYZA-japanese-Llama-2-7b-instruct-gguf-q4km-hf/dataset.jsonl -------------------------------------------------------------------------------- /assets/elyza/ELYZA-japanese-Llama-2-7b-instruct-gguf-q4km-hf/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/elyza/ELYZA-japanese-Llama-2-7b-instruct-gguf-q4km-hf/preds.jsonl -------------------------------------------------------------------------------- /assets/elyza/ELYZA-japanese-Llama-2-7b-instruct/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/elyza/ELYZA-japanese-Llama-2-7b-instruct/dataset.jsonl -------------------------------------------------------------------------------- /assets/elyza/ELYZA-japanese-Llama-2-7b-instruct/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/elyza/ELYZA-japanese-Llama-2-7b-instruct/preds.jsonl -------------------------------------------------------------------------------- /assets/elyza_tasks_100/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/elyza_tasks_100/dataset.jsonl -------------------------------------------------------------------------------- /assets/karakuri-ai/karakuri-lm-70b-chat-v0.1-gguf-q4km-hf/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/karakuri-ai/karakuri-lm-70b-chat-v0.1-gguf-q4km-hf/dataset.jsonl -------------------------------------------------------------------------------- /assets/karakuri-ai/karakuri-lm-70b-chat-v0.1-gguf-q4km-hf/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/karakuri-ai/karakuri-lm-70b-chat-v0.1-gguf-q4km-hf/preds.jsonl -------------------------------------------------------------------------------- /assets/karakuri-ai/karakuri-lm-70b-chat-v0.1-gguf-q4km-hf_cmdr+/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/karakuri-ai/karakuri-lm-70b-chat-v0.1-gguf-q4km-hf_cmdr+/dataset.jsonl -------------------------------------------------------------------------------- /assets/karakuri-ai/karakuri-lm-70b-chat-v0.1-gguf-q4km-hf_cmdr+/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/karakuri-ai/karakuri-lm-70b-chat-v0.1-gguf-q4km-hf_cmdr+/preds.jsonl -------------------------------------------------------------------------------- /assets/karakuri-ai/karakuri-lm-70b-chat-v0.1-gguf-q4km-hf_cmdr+/result_take1.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/karakuri-ai/karakuri-lm-70b-chat-v0.1-gguf-q4km-hf_cmdr+/result_take1.jsonl -------------------------------------------------------------------------------- /assets/karakuri-ai/karakuri-lm-70b-chat-v0.1-gguf-q4km-hf_cmdr+/result_take2.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/karakuri-ai/karakuri-lm-70b-chat-v0.1-gguf-q4km-hf_cmdr+/result_take2.jsonl -------------------------------------------------------------------------------- /assets/karakuri-ai/karakuri-lm-70b-chat-v0.1-gguf-q4km-hf_cmdr+/result_take3.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/karakuri-ai/karakuri-lm-70b-chat-v0.1-gguf-q4km-hf_cmdr+/result_take3.jsonl -------------------------------------------------------------------------------- /assets/karakuri-ai/karakuri-lm-8x7b-chat-v0.1-gguf-iq3xxs-hf/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/karakuri-ai/karakuri-lm-8x7b-chat-v0.1-gguf-iq3xxs-hf/dataset.jsonl -------------------------------------------------------------------------------- /assets/karakuri-ai/karakuri-lm-8x7b-chat-v0.1-gguf-iq3xxs-hf/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/karakuri-ai/karakuri-lm-8x7b-chat-v0.1-gguf-iq3xxs-hf/preds.jsonl -------------------------------------------------------------------------------- /assets/llm-jp/llm-jp-13b-instruct-full-dolly-oasst-v1.0/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/llm-jp/llm-jp-13b-instruct-full-dolly-oasst-v1.0/dataset.jsonl -------------------------------------------------------------------------------- /assets/llm-jp/llm-jp-13b-instruct-full-dolly-oasst-v1.0/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/llm-jp/llm-jp-13b-instruct-full-dolly-oasst-v1.0/preds.jsonl -------------------------------------------------------------------------------- /assets/llm-jp/llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/llm-jp/llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0/dataset.jsonl -------------------------------------------------------------------------------- /assets/llm-jp/llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/llm-jp/llm-jp-13b-instruct-full-jaster-dolly-oasst-v1.0/preds.jsonl -------------------------------------------------------------------------------- /assets/meta-llama/Meta-Llama-3-70B-Instruct-gguf-q4km/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/meta-llama/Meta-Llama-3-70B-Instruct-gguf-q4km/dataset.jsonl -------------------------------------------------------------------------------- /assets/meta-llama/Meta-Llama-3-70B-Instruct-gguf-q4km/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/meta-llama/Meta-Llama-3-70B-Instruct-gguf-q4km/preds.jsonl -------------------------------------------------------------------------------- /assets/meta-llama/Meta-Llama-3-8B-Instruct/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/meta-llama/Meta-Llama-3-8B-Instruct/dataset.jsonl -------------------------------------------------------------------------------- /assets/meta-llama/Meta-Llama-3-8B-Instruct/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/meta-llama/Meta-Llama-3-8B-Instruct/preds.jsonl -------------------------------------------------------------------------------- /assets/meta-math/MetaMath-Mistral-7B/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/meta-math/MetaMath-Mistral-7B/dataset.jsonl -------------------------------------------------------------------------------- /assets/meta-math/MetaMath-Mistral-7B/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/meta-math/MetaMath-Mistral-7B/preds.jsonl -------------------------------------------------------------------------------- /assets/microsoft/Phi-3-medium-128k-instruct/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/microsoft/Phi-3-medium-128k-instruct/dataset.jsonl -------------------------------------------------------------------------------- /assets/microsoft/Phi-3-medium-128k-instruct/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/microsoft/Phi-3-medium-128k-instruct/preds.jsonl -------------------------------------------------------------------------------- /assets/microsoft/Phi-3-mini-128k-instruct-en/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/microsoft/Phi-3-mini-128k-instruct-en/dataset.jsonl -------------------------------------------------------------------------------- /assets/microsoft/Phi-3-mini-128k-instruct-en/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/microsoft/Phi-3-mini-128k-instruct-en/preds.jsonl -------------------------------------------------------------------------------- /assets/microsoft/Phi-3-mini-128k-instruct/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/microsoft/Phi-3-mini-128k-instruct/dataset.jsonl -------------------------------------------------------------------------------- /assets/microsoft/Phi-3-mini-128k-instruct/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/microsoft/Phi-3-mini-128k-instruct/preds.jsonl -------------------------------------------------------------------------------- /assets/microsoft/Phi-3-small-128k-instruct/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/microsoft/Phi-3-small-128k-instruct/dataset.jsonl -------------------------------------------------------------------------------- /assets/microsoft/Phi-3-small-128k-instruct/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/microsoft/Phi-3-small-128k-instruct/preds.jsonl -------------------------------------------------------------------------------- /assets/microsoft/Phi-3-small-128k-instruct_gpt-4o/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/microsoft/Phi-3-small-128k-instruct_gpt-4o/dataset.jsonl -------------------------------------------------------------------------------- /assets/microsoft/Phi-3-small-128k-instruct_gpt-4o/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/microsoft/Phi-3-small-128k-instruct_gpt-4o/preds.jsonl -------------------------------------------------------------------------------- /assets/nssv/20240423_biomistral_stableLM-instruct-gamma-7b_0.5/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/20240423_biomistral_stableLM-instruct-gamma-7b_0.5/dataset.jsonl -------------------------------------------------------------------------------- /assets/nssv/20240423_biomistral_stableLM-instruct-gamma-7b_0.5/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/20240423_biomistral_stableLM-instruct-gamma-7b_0.5/preds.jsonl -------------------------------------------------------------------------------- /assets/nssv/20240423_biomistral_stableLM-instruct-gamma-7b_1.0/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/20240423_biomistral_stableLM-instruct-gamma-7b_1.0/dataset.jsonl -------------------------------------------------------------------------------- /assets/nssv/20240423_biomistral_stableLM-instruct-gamma-7b_1.0/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/20240423_biomistral_stableLM-instruct-gamma-7b_1.0/preds.jsonl -------------------------------------------------------------------------------- /assets/nssv/20240423_metamath_stableLM-instruct-gamma-7b_0.5_prompt-ja/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/20240423_metamath_stableLM-instruct-gamma-7b_0.5_prompt-ja/dataset.jsonl -------------------------------------------------------------------------------- /assets/nssv/20240423_metamath_stableLM-instruct-gamma-7b_0.5_prompt-ja/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/20240423_metamath_stableLM-instruct-gamma-7b_0.5_prompt-ja/preds.jsonl -------------------------------------------------------------------------------- /assets/nssv/20240423_metamath_stableLM-instruct-gamma-7b_1.0_prompt-ja/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/20240423_metamath_stableLM-instruct-gamma-7b_1.0_prompt-ja/dataset.jsonl -------------------------------------------------------------------------------- /assets/nssv/20240423_metamath_stableLM-instruct-gamma-7b_1.0_prompt-ja/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/20240423_metamath_stableLM-instruct-gamma-7b_1.0_prompt-ja/preds.jsonl -------------------------------------------------------------------------------- /assets/nssv/20240501_llama2_qlora/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/20240501_llama2_qlora/dataset.jsonl -------------------------------------------------------------------------------- /assets/nssv/20240501_llama2_qlora/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/20240501_llama2_qlora/preds.jsonl -------------------------------------------------------------------------------- /assets/nssv/20240507_swallow-7b-instruct-v0.1_meditron_0.5/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/20240507_swallow-7b-instruct-v0.1_meditron_0.5/dataset.jsonl -------------------------------------------------------------------------------- /assets/nssv/20240507_swallow-7b-instruct-v0.1_meditron_0.5/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/20240507_swallow-7b-instruct-v0.1_meditron_0.5/preds.jsonl -------------------------------------------------------------------------------- /assets/nssv/20240507_swallow-7b-instruct-v0.1_meditron_1.0/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/20240507_swallow-7b-instruct-v0.1_meditron_1.0/dataset.jsonl -------------------------------------------------------------------------------- /assets/nssv/20240507_swallow-7b-instruct-v0.1_meditron_1.0/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/20240507_swallow-7b-instruct-v0.1_meditron_1.0/preds.jsonl -------------------------------------------------------------------------------- /assets/nssv/japanese-stablelm-instruct-beta-7b_dpo_distilabel-intel-orca/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/japanese-stablelm-instruct-beta-7b_dpo_distilabel-intel-orca/dataset.jsonl -------------------------------------------------------------------------------- /assets/nssv/japanese-stablelm-instruct-beta-7b_dpo_distilabel-intel-orca/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/japanese-stablelm-instruct-beta-7b_dpo_distilabel-intel-orca/preds.jsonl -------------------------------------------------------------------------------- /assets/nssv/japanese-stablelm-instruct-beta-7b_dpo_hh-rlhf/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/japanese-stablelm-instruct-beta-7b_dpo_hh-rlhf/dataset.jsonl -------------------------------------------------------------------------------- /assets/nssv/japanese-stablelm-instruct-beta-7b_dpo_hh-rlhf/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/japanese-stablelm-instruct-beta-7b_dpo_hh-rlhf/preds.jsonl -------------------------------------------------------------------------------- /assets/nssv/tfmc-biomistral_1.0-7B/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/tfmc-biomistral_1.0-7B/dataset.jsonl -------------------------------------------------------------------------------- /assets/nssv/tfmc-biomistral_1.0-7B/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/nssv/tfmc-biomistral_1.0-7B/preds.jsonl -------------------------------------------------------------------------------- /assets/openchat/openchat-3.5-0106/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/openchat/openchat-3.5-0106/dataset.jsonl -------------------------------------------------------------------------------- /assets/openchat/openchat-3.5-0106/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/openchat/openchat-3.5-0106/preds.jsonl -------------------------------------------------------------------------------- /assets/openchat/openchat-3.5-1210/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/openchat/openchat-3.5-1210/dataset.jsonl -------------------------------------------------------------------------------- /assets/openchat/openchat-3.5-1210/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/openchat/openchat-3.5-1210/preds.jsonl -------------------------------------------------------------------------------- /assets/prompt_eval.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/prompt_eval.txt -------------------------------------------------------------------------------- /assets/prompt_eval_cohere.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/prompt_eval_cohere.txt -------------------------------------------------------------------------------- /assets/rinna/llama-3-youko-8b/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/rinna/llama-3-youko-8b/dataset.jsonl -------------------------------------------------------------------------------- /assets/rinna/llama-3-youko-8b/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/rinna/llama-3-youko-8b/preds.jsonl -------------------------------------------------------------------------------- /assets/rinna/youri-7b-chat-gguf-q4km-hf/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/rinna/youri-7b-chat-gguf-q4km-hf/dataset.jsonl -------------------------------------------------------------------------------- /assets/rinna/youri-7b-chat-gguf-q4km-hf/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/rinna/youri-7b-chat-gguf-q4km-hf/preds.jsonl -------------------------------------------------------------------------------- /assets/rinna/youri-7b-chat/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/rinna/youri-7b-chat/dataset.jsonl -------------------------------------------------------------------------------- /assets/rinna/youri-7b-chat/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/rinna/youri-7b-chat/preds.jsonl -------------------------------------------------------------------------------- /assets/stabilityai/japanese-stablelm-base-beta-70b-GGUF_TheBloke/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/stabilityai/japanese-stablelm-base-beta-70b-GGUF_TheBloke/dataset.jsonl -------------------------------------------------------------------------------- /assets/stabilityai/japanese-stablelm-base-beta-70b-GGUF_TheBloke/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/stabilityai/japanese-stablelm-base-beta-70b-GGUF_TheBloke/preds.jsonl -------------------------------------------------------------------------------- /assets/stabilityai/japanese-stablelm-instruct-beta-7b-gguf-q4km-hf/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/stabilityai/japanese-stablelm-instruct-beta-7b-gguf-q4km-hf/dataset.jsonl -------------------------------------------------------------------------------- /assets/stabilityai/japanese-stablelm-instruct-beta-7b-gguf-q4km-hf/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/stabilityai/japanese-stablelm-instruct-beta-7b-gguf-q4km-hf/preds.jsonl -------------------------------------------------------------------------------- /assets/stabilityai/japanese-stablelm-instruct-beta-7b-gpt3.5/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/stabilityai/japanese-stablelm-instruct-beta-7b-gpt3.5/dataset.jsonl -------------------------------------------------------------------------------- /assets/stabilityai/japanese-stablelm-instruct-beta-7b-gpt3.5/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/stabilityai/japanese-stablelm-instruct-beta-7b-gpt3.5/preds.jsonl -------------------------------------------------------------------------------- /assets/stabilityai/japanese-stablelm-instruct-beta-7b/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/stabilityai/japanese-stablelm-instruct-beta-7b/dataset.jsonl -------------------------------------------------------------------------------- /assets/stabilityai/japanese-stablelm-instruct-beta-7b/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/stabilityai/japanese-stablelm-instruct-beta-7b/preds.jsonl -------------------------------------------------------------------------------- /assets/stabilityai/japanese-stablelm-instruct-gamma-7b/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/stabilityai/japanese-stablelm-instruct-gamma-7b/dataset.jsonl -------------------------------------------------------------------------------- /assets/stabilityai/japanese-stablelm-instruct-gamma-7b/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/stabilityai/japanese-stablelm-instruct-gamma-7b/preds.jsonl -------------------------------------------------------------------------------- /assets/test/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/test/dataset.jsonl -------------------------------------------------------------------------------- /assets/test/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/test/preds.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-13b-instruct-gguf-q4km-hf/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-13b-instruct-gguf-q4km-hf/dataset.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-13b-instruct-gguf-q4km-hf/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-13b-instruct-gguf-q4km-hf/preds.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-13b-instruct/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-13b-instruct/dataset.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-13b-instruct/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-13b-instruct/preds.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-70b-instruct/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-70b-instruct/dataset.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-70b-instruct/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-70b-instruct/preds.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-70b-instruct/raw.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-70b-instruct/raw.txt -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-70b-instruct/raw_to_jsonl.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-70b-instruct/raw_to_jsonl.py -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-7b-instruct-gguf-q4km-hf/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-7b-instruct-gguf-q4km-hf/dataset.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-7b-instruct-gguf-q4km-hf/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-7b-instruct-gguf-q4km-hf/preds.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-7b-instruct-v0.1/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-7b-instruct-v0.1/dataset.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-7b-instruct-v0.1/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-7b-instruct-v0.1/preds.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-7b-instruct/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-7b-instruct/dataset.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-7b-instruct/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-7b-instruct/preds.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-7b-instruct_cmdr+/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-7b-instruct_cmdr+/dataset.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-7b-instruct_cmdr+/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-7b-instruct_cmdr+/preds.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-7b-instruct_cmdr+/result_take1.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-7b-instruct_cmdr+/result_take1.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-7b-instruct_cmdr+/result_take2.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-7b-instruct_cmdr+/result_take2.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-7b-instruct_cmdr+/result_take3.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-7b-instruct_cmdr+/result_take3.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-7b-plus-hf/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-7b-plus-hf/dataset.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-7b-plus-hf/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-7b-plus-hf/preds.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude-sys/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude-sys/dataset.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude-sys/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude-sys/preds.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude-sysml/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude-sysml/dataset.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude-sysml/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude-sysml/preds.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude-v2/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude-v2/preds.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude/dataset.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-claude/preds.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-elyza/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-elyza/dataset.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-elyza/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-elyza/preds.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-mixtral/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-mixtral/dataset.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-mixtral/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-mixtral/preds.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-vanilla/dataset.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-vanilla/dataset.jsonl -------------------------------------------------------------------------------- /assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-vanilla/preds.jsonl: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/assets/tokyotech-llm/Swallow-MX-8x7b-NVE-v0.1-gguf-q4km-hf-vanilla/preds.jsonl -------------------------------------------------------------------------------- /compose.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/compose.yml -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_01_ai_Yi_34B_Chat_4bits.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_01_ai_Yi_34B_Chat_4bits.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_01_ai_Yi_6B_Chat.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_01_ai_Yi_6B_Chat.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_Weyaxi_OpenHermes_2_5_neural_chat_7b_v3_1_7B.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_Weyaxi_OpenHermes_2_5_neural_chat_7b_v3_1_7B.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_Xwin_LM_Xwin_LM_13B_V0_1.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_Xwin_LM_Xwin_LM_13B_V0_1.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_Xwin_LM_Xwin_LM_70B_V0_1.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_Xwin_LM_Xwin_LM_70B_V0_1.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_Xwin_LM_Xwin_LM_7B_V0_1.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_Xwin_LM_Xwin_LM_7B_V0_1.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_augmxnt_shisa_7b_v1.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_augmxnt_shisa_7b_v1.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_cyberagent_calm2_7b_chat.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_cyberagent_calm2_7b_chat.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_deepseek_ai_deepseek_llm_7b_chat.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_deepseek_ai_deepseek_llm_7b_chat.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_deepseek_deepseek_llm_67b_chat_GGUF_TheBloke.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_deepseek_deepseek_llm_67b_chat_GGUF_TheBloke.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_elyza_ELYZA_japanese_Llama_2_7b_instruct.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_elyza_ELYZA_japanese_Llama_2_7b_instruct.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_llm_jp_llm_jp_13b_instruct_full_dolly_oasst_v1_0.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_llm_jp_llm_jp_13b_instruct_full_dolly_oasst_v1_0.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_openchat_openchat_3_5_1210.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_openchat_openchat_3_5_1210.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_rinna_youri_7b_chat.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_rinna_youri_7b_chat.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_stabilityai_japanese_stablelm_instruct_beta_70b.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_stabilityai_japanese_stablelm_instruct_beta_70b.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_stabilityai_japanese_stablelm_instruct_beta_7b.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_stabilityai_japanese_stablelm_instruct_beta_7b.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_tokyotech_llm_Swallow_13b_instruct_hf.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_tokyotech_llm_Swallow_13b_instruct_hf.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_tokyotech_llm_Swallow_70B_Instruct_GGUF_.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_tokyotech_llm_Swallow_70B_Instruct_GGUF_.ipynb -------------------------------------------------------------------------------- /notebooks/ELYZA_tasks_100_inference_tokyotech_llm_Swallow_7b_instruct_hf.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/notebooks/ELYZA_tasks_100_inference_tokyotech_llm_Swallow_7b_instruct_hf.ipynb -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/requirements.txt -------------------------------------------------------------------------------- /secrets/.gitkeep: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /src/download_elyza.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/src/download_elyza.py -------------------------------------------------------------------------------- /src/judges/cohere/command_r_plus/cmdr_plus_judge.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/src/judges/cohere/command_r_plus/cmdr_plus_judge.py -------------------------------------------------------------------------------- /src/judges/cohere/command_r_plus/sequential_process.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/src/judges/cohere/command_r_plus/sequential_process.py -------------------------------------------------------------------------------- /src/judges/openai/gpt_4/batch_retrieve.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/src/judges/openai/gpt_4/batch_retrieve.py -------------------------------------------------------------------------------- /src/judges/openai/gpt_4/batch_submit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/src/judges/openai/gpt_4/batch_submit.py -------------------------------------------------------------------------------- /src/judges/openai/gpt_4/openai_judge.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/src/judges/openai/gpt_4/openai_judge.py -------------------------------------------------------------------------------- /src/judges/openai/gpt_4/sequential_process.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/src/judges/openai/gpt_4/sequential_process.py -------------------------------------------------------------------------------- /src/lib/client_cohere.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/src/lib/client_cohere.py -------------------------------------------------------------------------------- /src/lib/client_openai.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/src/lib/client_openai.py -------------------------------------------------------------------------------- /src/lib/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/src/lib/common.py -------------------------------------------------------------------------------- /src/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/src/main.py -------------------------------------------------------------------------------- /tools/copy_jsonl_to_google_spreadsheet.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Northern-System-Service/gpt4-autoeval/HEAD/tools/copy_jsonl_to_google_spreadsheet.js --------------------------------------------------------------------------------