Merging in a Bottle: Differentiable Adaptive Merging (DAM) and the Path from Averaging to Automation
Paper
•
2410.08371
•
Published
•
1
Merge Crew
AI & ML interests
Merging models
Recent Activity
merge-crew's activity
mlabonne
authored
a
paper
about 1 month ago
SyedAbdul
authored
a
paper
2 months ago
KennethEnevoldsen
authored
4
papers
4 months ago
Encoder vs Decoder: Comparative Analysis of Encoder and Decoder Language Models on Multilingual NLU Tasks
Paper
•
2406.13469
•
Published
DaCy: A Unified Framework for Danish NLP
Paper
•
2107.05295
•
Published
Danish Foundation Models
Paper
•
2311.07264
•
Published
$S^3$ -- Semantic Signal Separation
Paper
•
2406.09556
•
Published
saattrupdan
authored
a
paper
5 months ago
Post
17287
Large models are surprisingly bad storytellers.
I asked 8 LLMs to "Tell me a bedtime story about bears and waffles."
Claude 3.5 Sonnet and GPT-4o gave me the worst stories: no conflict, no moral, zero creativity.
In contrast, smaller models were quite creative and wrote stories involving talking waffle trees and bears ostracized for their love of waffles.
Here you can see a comparison between Claude 3.5 Sonnet and NeuralDaredevil-8B-abliterated. They both start with a family of bears but quickly diverge in terms of personality, conflict, etc.
I mapped it to the hero's journey to have some kind of framework. Prompt engineering can definitely help here, but it's still disappointing that the larger models don't create better stories right off the bat.
Do you know why smaller models outperform the frontier models here?
I asked 8 LLMs to "Tell me a bedtime story about bears and waffles."
Claude 3.5 Sonnet and GPT-4o gave me the worst stories: no conflict, no moral, zero creativity.
In contrast, smaller models were quite creative and wrote stories involving talking waffle trees and bears ostracized for their love of waffles.
Here you can see a comparison between Claude 3.5 Sonnet and NeuralDaredevil-8B-abliterated. They both start with a family of bears but quickly diverge in terms of personality, conflict, etc.
I mapped it to the hero's journey to have some kind of framework. Prompt engineering can definitely help here, but it's still disappointing that the larger models don't create better stories right off the bat.
Do you know why smaller models outperform the frontier models here?
- 44 replies
buzzcraft
authored
2
papers
6 months ago
KennethEnevoldsen
authored
3
papers
7 months ago
Augmenty: A Python Library for Structured Text Augmentation
Paper
•
2312.05520
•
Published
DANSK and DaCy 2.6.0: Domain Generalization of Danish Named Entity Recognition
Paper
•
2402.18209
•
Published
•
1
The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding
Paper
•
2406.02396
•
Published
Post
17849
✂️ Uncensor any LLM with abliteration
I wrote an article about abliteration and how NeuralDaredevil-8B was created. Beyond removing alignment, I believe it's an interesting technique with a lot of potential. It's basically fine-tuning without retraining.
In this article, we see how it works, implement it in Google Colab, and heal the abliterated model to recover the performance drop due to this technique. The final model is an uncensored and high-quality model with the highest MMLU score on the Open LLM Leaderboard (8B category).
https://huggingface.co/blog/mlabonne/abliteration
I wrote an article about abliteration and how NeuralDaredevil-8B was created. Beyond removing alignment, I believe it's an interesting technique with a lot of potential. It's basically fine-tuning without retraining.
In this article, we see how it works, implement it in Google Colab, and heal the abliterated model to recover the performance drop due to this technique. The final model is an uncensored and high-quality model with the highest MMLU score on the Open LLM Leaderboard (8B category).
https://huggingface.co/blog/mlabonne/abliteration
-
- 26 replies
birgermoell
authored
4
papers
7 months ago
Evaluating Large Language Models with Human Feedback: Establishing a Swedish Benchmark
Paper
•
2405.14006
•
Published
You don't understand me!: Comparing ASR results for L1 and L2 speakers of Swedish
Paper
•
2405.13379
•
Published
A Framework for Integrating Gesture Generation Models into Interactive Conversational Agents
Paper
•
2102.12302
•
Published
Comparing the Efficacy of GPT-4 and Chat-GPT in Mental Health Care: A Blind Assessment of Large Language Models for Psychological Support
Paper
•
2405.09300
•
Published
birgermoell
authored
a
paper
8 months ago
shivammehta25
authored
a
paper
8 months ago