Qwen2.5 Technical Report
Paper
ā¢
2412.15115
ā¢
Published
ā¢
304
Rajdeep Borgohain
rbgo
AI & ML interests
Solving language barriers.
Recent Activity
upvoted
a
paper
3 days ago
Qwen2.5 Technical Report
liked
a dataset
5 days ago
NTU-NLP-sg/xCodeEval
upvoted
a
collection
7 days ago
Qwen2.5
Organizations
rbgo's activity
upvoted
a
paper
3 days ago
liked
a
dataset
5 days ago
upvoted
a
collection
7 days ago
liked
a
Space
9 days ago
upvoted
2
collections
11 days ago
upvoted
a
collection
12 days ago
updated
a
collection
17 days ago
liked
a
Space
17 days ago
liked
a
model
20 days ago
reacted to
m-ric's
post with š
about 1 month ago
Post
786
š Meta teams use a fine-tuned Llama model to fix production issues in seconds
One of Meta's engineering teams shared how they use a fine-tuned small Llama (Llama-2-7B, so not even a very recent model) to identify the root cause of production issues with 42% accuracy.
š¤ 42%, is that not too low?
ā”ļø Usually, whenever there's an issue in production, engineers dive into recent code changes to find the offending commit. At Meta's scale (thousands of daily changes), this is like finding a needle in a haystack.
š” So when the LLM-based suggestion is right, it cuts incident resolution time from hours to seconds!
How did they do it?
š Two-step approach:
ā£ Heuristics (code ownership, directory structure, runtime graphs) reduce thousands of potential changes to a manageable set
ā£ Fine-tuned Llama 2 7B ranks the most likely culprits
š Training pipeline:
ā£ Continued pre-training on Meta's internal docs and wikis
ā£ Supervised fine-tuning on past incident investigations
ā£ Training data mimicked real-world constraints (2-20 potential changes per incident)
š® Now future developments await:
ā£ Language models could handle more of the incident response workflow (runbooks, mitigation, post-mortems)
ā£ Improvements in model reasoning should boost accuracy further
Read it in full š https://www.tryparity.com/blog/how-meta-uses-llms-to-improve-incident-response
One of Meta's engineering teams shared how they use a fine-tuned small Llama (Llama-2-7B, so not even a very recent model) to identify the root cause of production issues with 42% accuracy.
š¤ 42%, is that not too low?
ā”ļø Usually, whenever there's an issue in production, engineers dive into recent code changes to find the offending commit. At Meta's scale (thousands of daily changes), this is like finding a needle in a haystack.
š” So when the LLM-based suggestion is right, it cuts incident resolution time from hours to seconds!
How did they do it?
š Two-step approach:
ā£ Heuristics (code ownership, directory structure, runtime graphs) reduce thousands of potential changes to a manageable set
ā£ Fine-tuned Llama 2 7B ranks the most likely culprits
š Training pipeline:
ā£ Continued pre-training on Meta's internal docs and wikis
ā£ Supervised fine-tuning on past incident investigations
ā£ Training data mimicked real-world constraints (2-20 potential changes per incident)
š® Now future developments await:
ā£ Language models could handle more of the incident response workflow (runbooks, mitigation, post-mortems)
ā£ Improvements in model reasoning should boost accuracy further
Read it in full š https://www.tryparity.com/blog/how-meta-uses-llms-to-improve-incident-response
updated
a
dataset
about 1 month ago
liked
a
Space
about 2 months ago
reacted to
abhishek's
post with š
2 months ago
updated
a
Space
3 months ago
liked
a
Space
3 months ago
updated
a
collection
3 months ago
upvoted
2
papers
3 months ago
updated
a
collection
3 months ago