Unverified50% confidenceFactExact time
The study evaluated the token-probability scoring method using Llama 3.1 8B and 70B models on three datasets: TOEFL9, Write and Improve 2024, and BULATS-L1.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedGPTQ（2022年）和AWQ（2023年）能将70B参数的LLM量化到INT4精度，困惑度损失不到1%62% similarUnverifiedOn probabilistic prediction metrics, the framework achieves a marginal negative log-likelihood (NLL) of 0.66380 and a continuous ranked probability score (CRPS) of 0.27301.61% similarUnverifiedd1 supports three question types: Boolean, Choice, and Score, with answers accompanied by probabilities.60% similarUnverifiedThe test used the minimax_h3_fl2va_int8_convrot model.60% similarUnverifiedDASA's experiments were validated on 6 models from the Llama and Qwen model families, covering parameter scales from 1B to 32B.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1066037API
curl https://kongchang.com/api/v1/knowledge/claims/1066037MCP
get_claim(id=1066037)