Adrian Chan
gravity7
·
AI & ML interests
GenAI for UX and CX
Recent Activity
reacted
to
tegridydev's
post
with 👍
about 1 month ago
WTF is Fine-Tuning? (intro4devs)
Fine-tuning your LLM is like min-maxing your ARPG hero so you can push high-level dungeons and get the most out of your build/gear... Makes sense, right? 😃
Here's a cheat sheet for devs (but open to anyone!)
---
TL;DR
- Full Fine-Tuning: Max performance, high resource needs, best reliability.
- PEFT: Efficient, cost-effective, mainstream, enhanced by AutoML.
- Instruction Fine-Tuning: Ideal for command-following AI, often combined with RLHF and CoT.
- RAFT: Best for fact-grounded models with dynamic retrieval.
- RLHF: Produces ethical, high-quality conversational AI, but expensive.
Choose wisely and match your approach to your task, budget, and deployment constraints.
I just posted the full extended article here
if you want to continue reading >>>
https://huggingface.co/blog/tegridydev/fine-tuning-dev-intro-2025
reacted
to
Kseniase's
post
with 👍
about 1 month ago
8 New Applications of Test-Time Scaling
We've noticed a huge interest in test-time scaling (TTS), so we decided to explore this concept further. Test-time compute (TTC) refers to the amount of computational power used by an AI model when generating a response. Many researchers are now focused on scaling TTC, as it enables slow, deep "thinking" and step-by-step reasoning, which improves overall models' performance.
Here are 8 fresh studies on test-time scaling:
1. https://huggingface.co/papers/2502.05171
Introduces an LM that scales TTC by reasoning in latent space instead of generating more tokens with no special training. Here, a recurrent block to processes information iteratively.
2. https://huggingface.co/papers/2502.04728
Shows how TTS is applied to enhance model's Planning Domain Definition Language (PDDL) reasoning capabilities, which can be used to generate a symbolic world model.
3. https://huggingface.co/papers/2502.06703
Analyzes optimal TTS strategies and shows how small models can outperform much larger ones.
4. https://huggingface.co/papers/2502.04128
Shows how TTS improves expressiveness, timbre consistency and accuracy in speech synthesis with Llasa framework. It also dives into benefits of scaling train-time compute.
5. https://huggingface.co/papers/2502.07154
Suggests a modified training loss for better reasoning of LLMs when scaling TTC.
6. https://huggingface.co/papers/2502.05078
Unifies the strengths of chain, tree, and graph paradigms into one framework that expands reasoning only on necessary subproblems.
7. https://huggingface.co/papers/2502.01839
Explores scaling trends of self-verification and how to improve its capabilities with TTC.
8. https://huggingface.co/papers/2501.14723
Explores how scaling serial compute (iterations) and parallel compute (trajectories), can improve accuracy in real-world software engineering issues.
Also, explore our article about TTS for more -> https://huggingface.co/blog/Kseniase/testtimecompute
Organizations
None yet
