Microsoft’s 1.3 Billion Model Outperforms Llama 2
Read Time:24 Second
Microsoft Research has done it once again. After outperforming Meta’s LLaMa with phi-1 in July, the researchers have now introduced phi-1.5, a cutting-edge language model of 1.3 billion parameters that outperforms Llama 2’s 7 billion parameters model on several benchmarks. Microsoft has decided to open source the model. The phi-1.5 model, comprising a staggering 1.3 […]
The post Microsoft’s 1.3 Billion Model Outperforms Llama 2 appeared first on Startup Reporter.
Happy
0
0 %
Sad
0
0 %
Excited
0
0 %
Sleepy
0
0 %
Angry
0
0 %
Surprise
0
0 %
More Stories
UP Census Enumeration Begins May 7 In Two Phases; Final Population Data To Be Based On March 1, 2027 Midnight
Lucknow: Census enumeration in Uttar Pradesh will begin from May 7, marking the start of a massive two-phase exercise aimed...
Navi Mumbai: CIDCO’s 12.5 Per Cent Land Scheme Nears Completion With 98.44 Pc Allotment Done
Navi Mumbai, May 2: CIDCO’s long-pending 12.5% land distribution scheme for project-affected farmers in Panvel, Uran and Navi Mumbai has...
WATCH: Punjab Kings Fielder Shashank Singh Drops Easy Catch During Practice Session; VIDEO Viral
Mohali, May 2: Punjab Kings fielder Shashank Singh has become the face of dropped catches in the Indian Premier League...
Guardrails for the Frontier: How AI Safety is Actually Being Built
In January 2026, Dario Amodei wrote a 20,000 word essay that made waves across the internet. The CEO of Anthropic,...
‘Shahid Smriti Van’ Validated as Key Pollution Mitigator in National Study
Surat (Gujarat) [India], May 2: Renowned environmentalist Viral Desai’s ‘Shahid Smriti Van’ has received national recognition for its ecological impact...
No fuel price hike despite global crisis: Puri
Surat | Gujarat —– In a powerful message amid global uncertainty, Union Petroleum Minister Hardeep Singh Puri declared that India...
Average Rating