mt_bench_human_judgments
by lmsys (organization)
This dataset contains 3.3K expert-level pairwise human preferences for model responses generated by 6 models in response to 80 MT-bench questions. The 6 models are GPT-4, GPT-3.5, Claud-v1, Vicuna-13B, Alpaca-13B, and LLaMA-13B. The annotators are mostly graduate students with… (excerpt from the dataset card on Hugging Face)
Dataset facts
- Hub id
- lmsys/mt_bench_human_judgments
- Likes
- 150
- Downloads (last 30 days)
- 4,312
- Tasks
- Question answering
- Modality
- tabular, text
- Size
- 1K to 10K examples
- License
- CC BY 4.0 (cc-by-4.0)
- Access
- Open download
- Author
- lmsys · Organization
- Languages
- en
- Created
- Jul 4, 2023
- Last modified
- Jul 20, 2023
More datasets from lmsys
Rank 19: lmsys/lmsys-chat-1m
LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset This dataset contains one million real-world conversations with 25 state-of-the-art LLMs. It is collecte…
1,050 likes4,702 downloads in the last 30 daysNo license givenGated
Rank 88: lmsys/chatbot_arena_conversations
This dataset contains 33K cleaned conversations with pairwise human preferences. It is collected from 13K unique IP addresses on the Chatbot Arena from April to June 202…
500 likes1,747 downloads in the last 30 daysCCGated
Rank 323: lmsys/toxic-chat
[01/31/2024] We update the OpenAI Moderation API results for ToxicChat (0124) based on their updated moderation model on on Jan 25, 2024.[01/28/2024] We release an offic…
209 likes11,972 downloads in the last 30 daysText classificationCC BY-NC 4.0