Distributed SFT with trl and DeepSpeed Part 1: Starting Locally
•
1
Junlin Zhou
jlzhou
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
5 days ago
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep
Thinking
upvoted
a
paper
6 days ago
Better & Faster Large Language Models via Multi-token Prediction
upvoted
a
paper
6 days ago
Training Large Language Models to Reason in a Continuous Latent Space
Articles
Organizations
jlzhou's activity
upvoted
a
paper
5 days ago
upvoted
3
papers
6 days ago
Better & Faster Large Language Models via Multi-token Prediction
Paper
•
2404.19737
•
Published
•
75
Training Large Language Models to Reason in a Continuous Latent Space
Paper
•
2412.06769
•
Published
•
76
Enhancing Training Efficiency Using Packing with Flash Attention
Paper
•
2407.09105
•
Published
•
15
published
an
article
8 days ago
Article
Distributed SFT with trl and DeepSpeed Part 1: Starting Locally
By
•
•
1
upvoted
an
article
8 days ago
Article
Fine-tune Llama 3 with ORPO
By
•
•
233
upvoted
an
article
9 days ago
Article
Efficient LLM Pretraining: Packed Sequences and Masked Attention
By
•
•
14
updated
a
model
10 days ago
published
a
model
10 days ago
upvoted
an
article
10 days ago
Article
The Large Language Model Course
By
•
•
83
liked
a
model
10 days ago
使用load_dataset加载dataset_7M, 但是返回报错KeyError: 'tags'
6
#28 opened 24 days ago
by
Melantha246
upvoted
2
articles
15 days ago
Article
LLM Comparison/Test: Llama 3 Instruct 70B + 8B HF/GGUF/EXL2 (20 versions tested and compared!)
By
•
•
61Article
Let's talk about LLM evaluation
By
•
•
148
upvoted
an
article
16 days ago
Article
Efficient Deep Learning: A Comprehensive Overview of Optimization Techniques 👐 📚
By
•
•
48
liked
a
model
22 days ago
updated
a
collection
24 days ago
updated
a
dataset
24 days ago
updated
a
collection
24 days ago
updated
a
dataset
24 days ago