Mackin7/my-distiset-5d7059ee
Viewer
ā¢
Updated
ā¢
10
ā¢
22
MATTHEW EYESAN
Mackin7
Ā·
AI & ML interests
Visions models
Language Models
ML Algorithms and Solutions
Security and Data frameworks
Recent Activity
updated
a dataset
14 days ago
Mackin7/my-distiset-5d7059ee
published
a dataset
14 days ago
Mackin7/my-distiset-5d7059ee
updated
a collection
23 days ago
FaceBChat_10
Organizations
None yet
Mackin7's activity
updated
a
dataset
14 days ago
published
a
dataset
14 days ago
updated
a
collection
23 days ago
[bot] Conversion to Parquet
#1 opened about 1 month ago
by
parquet-converter
updated
a
dataset
about 1 month ago
liked
a
Space
about 1 month ago
reacted to
fdaudens's
post with š„
4 months ago
Post
3316
A big day for multimodal models!
Llama 3.2 is out with a major update: it can now process images.
Key highlights:
ā¢ 11B and 90B vision models
ā¢ Small 1B and 3B text models for mobile devices
Eval results already on the leaderboard: open-llm-leaderboard/open_llm_leaderboard
Collection: meta-llama/llama-32-66f448ffc8c32f949b04c8cf
Llama 3.2 is out with a major update: it can now process images.
Key highlights:
ā¢ 11B and 90B vision models
ā¢ Small 1B and 3B text models for mobile devices
Eval results already on the leaderboard: open-llm-leaderboard/open_llm_leaderboard
Collection: meta-llama/llama-32-66f448ffc8c32f949b04c8cf
- 1 reply
reacted to
clem's
post with š„
5 months ago
Post
4135
Just crossed 200,000 free public AI datasets shared by the community on Hugging Face! Text, image, video, audio, time-series & many more... Thanks everyone!
http://hf.co/datasets
http://hf.co/datasets
reacted to
codelion's
post with ā¤ļø
5 months ago
Post
2048
We recently worked with OpenAI to fine-tune gpt-4o and built the SOTA model for the
patched-codes/static-analysis-eval benchmark. All the code and data
patched-codes/synth-vuln-fixes on how we did it is available on their GitHub - https://github.com/openai/build-hours/tree/main/5-4o_fine_tuning.
Here are some tips based on our experience:
ā Establish baseline with "conditioning" / prompting
ā Task-specific datasets are ideal for PEFT; hard to beat gpt-4o on "broad" tasks
ā Add your best system prompt to each example
ā Ensure training data distribution is similar to inference data
ā Shorten instructions with concise prompts; may require more examples.
ā Define clear evaluation metrics (seriously, please eval!)
You can see more details on the benchmark and process here - https://www.patched.codes/blog/the-static-analysis-evaluation-benchmark-measuring-llm-performance-in-fixing-software-vulnerabilities
Here are some tips based on our experience:
ā Establish baseline with "conditioning" / prompting
ā Task-specific datasets are ideal for PEFT; hard to beat gpt-4o on "broad" tasks
ā Add your best system prompt to each example
ā Ensure training data distribution is similar to inference data
ā Shorten instructions with concise prompts; may require more examples.
ā Define clear evaluation metrics (seriously, please eval!)
You can see more details on the benchmark and process here - https://www.patched.codes/blog/the-static-analysis-evaluation-benchmark-measuring-llm-performance-in-fixing-software-vulnerabilities
updated
a
collection
5 months ago
liked
a
model
5 months ago
updated
a
collection
5 months ago
updated
a
Space
7 months ago
updated
a
collection
7 months ago
updated
a
collection
8 months ago