Dahoas QDSyntheticData issues

Dahoas / QDSyntheticData

13 stars 16 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Reinforced Self-Training (ReST) for Language Modeling

#372 Shashi456 opened 5 months ago
2
Entropy Controllable Direct Preference Optimization

#371 Dahoas opened 5 months ago
0
On the Limits of Language Generation: Trade-Offs Between Hallucination and Mode Collapse

#370 Dahoas opened 5 months ago
0
Adaptive Data Optimization: Dynamic Sample Selection with Scaling Laws

#369 Shashi456 opened 5 months ago
0
Information-Theoretic Distillation for Reference-less Summarization

#368 Shashi456 opened 5 months ago
0
Mission Impossible Language Models

#367 Dahoas opened 5 months ago
1
Create 2410.04715_Rule-based_Data_Selection.md

#366 lauraaisling opened 6 months ago
0
Entropic Distribution Matching in Supervised Fine-tuning of LLMs: Less Overfitting and Better Diversity

#365 Dahoas closed 6 months ago
0
Diversity-Rewarded CFG Distillation

#364 Dahoas opened 6 months ago
2
Rule-based Data Selection for Large Language Models

#363 Dahoas opened 6 months ago
0
$\textbf{Only-IF}$:Revealing the Decisive Effect of Instruction Diversity on Generalization

#362 Dahoas opened 6 months ago
2
Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models

#361 Dahoas opened 6 months ago
3
On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey

#360 Dahoas opened 6 months ago
1
Improving Pretraining Data Using Perplexity Correlations

#359 kanishkg opened 7 months ago
0
RL with KL penalties is better viewed as Bayesian inference

#358 Dahoas opened 7 months ago
0
QDC mermaid diagrams

#357 baberabb opened 8 months ago
0
Create 2404.14219_phi3

#356 lauraaisling opened 8 months ago
0
phi3 paper (for completeness of phi series)

#355 lauraaisling opened 8 months ago
0
phi1

#354 lauraaisling opened 8 months ago
0
Create phi_2.md

#353 lauraaisling opened 8 months ago
0
2408.03314 paper summary added

#352 ShayekhBinIslam opened 8 months ago
0
Create 2309.05463_phi1.5.md

#351 lauraaisling opened 8 months ago
0
Create 2306.11644_phi1.md

#350 lauraaisling closed 8 months ago
0
Llama 3.1 paper

#349 Dahoas opened 8 months ago
0
Orca: Progressive learning from complex explanation traces of gpt- 4

#348 Dahoas opened 8 months ago
0
Read some easy to hard papers to better understand complexity

#347 Dahoas opened 8 months ago
0
Make list of key papers

#346 Dahoas opened 8 months ago
0
Pre-training case study

#345 Dahoas opened 8 months ago
1
case study for code

#344 Dahoas opened 8 months ago
0
Case study for reasoning/math

#343 Dahoas opened 8 months ago
0
Add domain specific section for RLHF/Instruction tuning

#342 Dahoas opened 8 months ago
0
Make table of contents diagram

#341 Dahoas opened 8 months ago
0
Read phi and add to paper

#340 Dahoas opened 8 months ago
1
Adding diagrams for quality, diversity, complexity taxonomy

#339 Dahoas opened 8 months ago
0
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

#338 Dahoas opened 8 months ago
1
Self-Taught Evaluators

#337 Dahoas opened 8 months ago
0
Create Meta-Rewarding_2407.19594.md

#336 lauraaisling closed 8 months ago
0
Meta-Rewarding Language Models

#335 lauraaisling opened 8 months ago
0
Closes #301

#334 srishti-git1110 closed 8 months ago
0
docs: fix/add broken links

#333 nlile opened 9 months ago
0
Polish final draft

#332 Dahoas opened 9 months ago
1
Solicit feedback

#331 Dahoas opened 9 months ago
1
Genetic Instruct: Scaling up Synthetic Generation of Coding Instructions for Large Language Models

#330 mmhamdy opened 9 months ago
1
Add summary for RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold

#329 mmhamdy closed 9 months ago
0
ead paper summary

#328 veratr86 closed 9 months ago
0
Rethinking and Refining the Distinct Metric

#327 veratr86 opened 9 months ago
1
Create 2305.10601_Tree_of_thought.md

#326 lauraaisling closed 9 months ago
0
Add summary for Simple synthetic data reduces sycophancy in large language models

#325 mmhamdy closed 9 months ago
0
Simple synthetic data reduces sycophancy in large language models

#324 mmhamdy closed 9 months ago
0
adding evo prompt summary

#323 veratr86 closed 9 months ago
0