TASLM 1B (token)

Reported on 4 benchmarks across 1 task

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical4 results

Language ModellingonSALMon
Gender Consistency
70.5
best: 88.5 (pGSLM)
Language ModellingonSALMon
Room Consistency
61
best: 62.5 (LAST 1.3B)
Language ModellingonSALMon
Sentiment Consistency
59
best: 73.5 (Spirit-LM (Expr.))
Language ModellingonSALMon
Speaker Consistency
68
best: 83 (pGSLM)