Snorlax/poca-SoccerTwos
Reinforcement Learning
•
Updated
•
32
Shangzhi Zhang
Snorlax
AI & ML interests
None yet
Recent Activity
updated
a model
15 days ago
Snorlax/poca-SoccerTwos
updated
a model
18 days ago
Snorlax/a2c-PandaReachDense-v3
updated
a model
24 days ago
Snorlax/ppo-Pyramids
Organizations
Snorlax's activity
updated
a
model
15 days ago
updated
a
model
18 days ago
updated
3
models
24 days ago
updated
2
models
25 days ago
updated
2
models
30 days ago
liked
a
Space
about 1 month ago
updated
2
models
about 1 month ago
liked
a
Space
4 months ago
liked
a
model
4 months ago
upvoted
an
article
5 months ago
Article
SmolLM - blazingly fast and remarkably powerful
•
292
liked
a
Space
7 months ago
Potential bug when batch inferencing with left padding.
1
#26 opened 7 months ago
by
Snorlax
liked
a
dataset
7 months ago
reacted to
georgewritescode's
post with 👍
7 months ago
Post
1017
Visualization of GPT-4o breaking away from the quality & speed trade-off curve the LLMs have followed thus far ✂️
Key GPT-4o takeaways
‣ GPT-4o not only offers the highest quality, it also sits amongst the fastest LLMs
‣ For those with speed/latency-sensitive use cases, where previously Claude 3 Haiku or Mixtral 8x7b were leaders, GPT-4o is now a compelling option (though significantly more expensive)
‣ Previously Groq was the only provider to break from the curve using its own LPU chips. OpenAI has done it on Nvidia hardware (one can imagine the potential for GPT-4o on Groq)
👉 How did they do it? Will follow up with more analysis on this but potential approaches include a very large but sparse MoE model (similar to Snowflake's Arctic) and improvements in data quality (likely to have driven much of Llama 3's impressive quality relative to parameter count)
Notes: Throughput represents the median across providers over the last 14 days of measurements (8x per day)
Data is present on our HF leaderboard: ArtificialAnalysis/LLM-Performance-Leaderboard and graphs present on our website
Key GPT-4o takeaways
‣ GPT-4o not only offers the highest quality, it also sits amongst the fastest LLMs
‣ For those with speed/latency-sensitive use cases, where previously Claude 3 Haiku or Mixtral 8x7b were leaders, GPT-4o is now a compelling option (though significantly more expensive)
‣ Previously Groq was the only provider to break from the curve using its own LPU chips. OpenAI has done it on Nvidia hardware (one can imagine the potential for GPT-4o on Groq)
👉 How did they do it? Will follow up with more analysis on this but potential approaches include a very large but sparse MoE model (similar to Snowflake's Arctic) and improvements in data quality (likely to have driven much of Llama 3's impressive quality relative to parameter count)
Notes: Throughput represents the median across providers over the last 14 days of measurements (8x per day)
Data is present on our HF leaderboard: ArtificialAnalysis/LLM-Performance-Leaderboard and graphs present on our website
- 1 reply
updated
a
collection
10 months ago