What Matters in Transformers? Not All Attention is Needed
Paper
•
2406.15786
•
Published
•
30
•
3
Eni Grand
Enigrand
AI & ML interests
None yet
Recent Activity
liked
a model
about 4 hours ago
Qwen/Qwen2.5-32B-Instruct
liked
a model
about 13 hours ago
deepseek-ai/DeepSeek-R1-Zero
liked
a model
about 13 hours ago
deepseek-ai/DeepSeek-R1
Organizations
Enigrand's activity
Qwen2.5-32B merge eval error
2
#1078 opened 15 days ago
by
ehristoforu
commented
a
paper
4 months ago
If you find Independent third-party evaluation results about this model, please share here.
7
#42 opened 5 months ago
by
Enigrand
Hi, can you deal with the bot spamming the community section of mattshumer/ref_70_e3 and
6
#16 opened 5 months ago
by
Enigrand
🚩 Report
17
#6 opened 5 months ago
by
gileneo
Reflection-Llama-3.1-70B was sonnet 3.5.
6
#5 opened 5 months ago
by
Enigrand
mattshumer/ref_70_e3 and mattshumer/Reflection-Llama-3.1-70B-ep2-working are the SAME.
2
#10 opened 5 months ago
by
Enigrand
Third party evaluation on this so-called "LLM".
3
#7 opened 5 months ago
by
Enigrand
Reflection-Llama-3.1-70B was claude 3, chatgpt4o and what?
1
#48 opened 5 months ago
by
Enigrand
🚩 Report: Spam
1
#49 opened 5 months ago
by
Enigrand
[Question] 2B or 5B?
2
#1 opened 5 months ago
by
Enigrand
Is this demo up to date?
#2 opened 6 months ago
by
Enigrand
[MODELS] Discussion
585
#372 opened 12 months ago
by
victor
How to FP8 inference
2
#5 opened 7 months ago
by
alfredplpl
Question: Will open LLM leadboard add some explicit coding benchmark?
1
#797 opened 7 months ago
by
Enigrand
About the number of training tokens
1
#1 opened 8 months ago
by
Enigrand
Questions about the context length
2
#4 opened 8 months ago
by
Enigrand