Article
SmolVLM2: Bringing Video Understanding to Every Device
•
172
Serdar ÇAĞLAR
serdarcaglar
AI & ML interests
None yet
Recent Activity
upvoted
an
article
2 days ago
SmolVLM2: Bringing Video Understanding to Every Device
new activity
about 2 months ago
aimped/nlp-health-translation-base-en-tr:Adding `safetensors` variant of this model
new activity
about 2 months ago
serdarcaglar/roberta-base-turkish-scientific-cased:Adding `safetensors` variant of this model
Organizations
serdarcaglar's activity
upvoted
an
article
2 days ago
Adding `safetensors` variant of this model
#1 opened about 2 months ago
by
SFconvertbot
Adding `safetensors` variant of this model
#3 opened about 2 months ago
by
SFconvertbot
Any plan to change licensing to MIT or Apache 2.0?
3
#10 opened 2 months ago
by
KadirErturk
Technical questions
2
#7 opened 3 months ago
by
alien79
updated
a
model
3 months ago
Update README.md
#95 opened 3 months ago
by
serdarcaglar
Onnx quantized version
3
#2 opened 3 months ago
by
ysdede
updated
a
model
3 months ago
The Inference Code is not working properly
3
#1 opened 4 months ago
by
serdarcaglar
updated
a
model
4 months ago
liked
a
model
4 months ago
updated
a
collection
5 months ago
upvoted
an
article
6 months ago
Article
Building a Vision Mixture-of-Expert Model from several fine-tuned Phi-3-Vision Models
By
•
•
6
updated
a
model
6 months ago
authored
a
paper
7 months ago
upvoted
a
paper
7 months ago
commented
a
paper
7 months ago
reacted to
thomwolf's
post with 🔥
8 months ago
Post
5210
A Little guide to building Large Language Models in 2024
This is a post-recording of a 75min lecture I gave two weeks ago on how to train a LLM from scratch in 2024. I tried to keep it short and comprehensive – focusing on concepts that are crucial for training good LLM but often hidden in tech reports.
In the lecture, I introduce the students to all the important concepts/tools/techniques for training good performance LLM:
* finding, preparing and evaluating web scale data
* understanding model parallelism and efficient training
* fine-tuning/aligning models
* fast inference
There is of course many things and details missing and that I should have added to it, don't hesitate to tell me you're most frustrating omission and I'll add it in a future part. In particular I think I'll add more focus on how to filter topics well and extensively and maybe more practical anecdotes and details.
Now that I recorded it I've been thinking this could be part 1 of a two-parts series with a 2nd fully hands-on video on how to run all these steps with some libraries and recipes we've released recently at HF around LLM training (and could be easily adapted to your other framework anyway):
*
*
*
Here is the link to watch the lecture on Youtube: https://www.youtube.com/watch?v=2-SPH9hIKT8
And here is the link to the Google slides: https://docs.google.com/presentation/d/1IkzESdOwdmwvPxIELYJi8--K3EZ98_cL6c5ZcLKSyVg/edit#slide=id.p
Enjoy and happy to hear feedback on it and what to add, correct, extend in a second part.
This is a post-recording of a 75min lecture I gave two weeks ago on how to train a LLM from scratch in 2024. I tried to keep it short and comprehensive – focusing on concepts that are crucial for training good LLM but often hidden in tech reports.
In the lecture, I introduce the students to all the important concepts/tools/techniques for training good performance LLM:
* finding, preparing and evaluating web scale data
* understanding model parallelism and efficient training
* fine-tuning/aligning models
* fast inference
There is of course many things and details missing and that I should have added to it, don't hesitate to tell me you're most frustrating omission and I'll add it in a future part. In particular I think I'll add more focus on how to filter topics well and extensively and maybe more practical anecdotes and details.
Now that I recorded it I've been thinking this could be part 1 of a two-parts series with a 2nd fully hands-on video on how to run all these steps with some libraries and recipes we've released recently at HF around LLM training (and could be easily adapted to your other framework anyway):
*
datatrove for all things web-scale data preparation: https://github.com/huggingface/datatrove*
nanotron for lightweight 4D parallelism LLM training: https://github.com/huggingface/nanotron*
lighteval for in-training fast parallel LLM evaluations: https://github.com/huggingface/lightevalHere is the link to watch the lecture on Youtube: https://www.youtube.com/watch?v=2-SPH9hIKT8
And here is the link to the Google slides: https://docs.google.com/presentation/d/1IkzESdOwdmwvPxIELYJi8--K3EZ98_cL6c5ZcLKSyVg/edit#slide=id.p
Enjoy and happy to hear feedback on it and what to add, correct, extend in a second part.
- 2 replies