Parmanu @ LCS2 IIT Delhi
Popular repositories Loading
-
peft
peft PublicForked from huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Python
-
mpdistil
mpdistil PublicMPDistil is a teacher-student collaborative knowledge distillation framework that enables compact student models to outperform larger teacher models through meta-learning and curriculum learning. B…
Python
-
TransJect
TransJect PublicSource Code of TransJect: Manifold-Preserving Transformer with Enforced Injectivity. Based on the EMNLP 2023 paper **Manifold-Preserving Transformers are Effective for Short-Long Range Encoding**
Python
-
efficient_pruners
efficient_pruners PublicToolkit implementing efficient compression methods for compressing LLMs. Implements PruneNet - ICLR 2025 paper: **You only prune once: Designing calibration-free model compression with policy learn…
Python
-
llm-distil
llm-distil PublicToolkit implementing knowledge distillation techniques for LLMs with efficient fine-tuning. Based on ACL 2025 paper: **On the Generalization vs Fidelity Paradox in Knowledge Distillation**
Python
Repositories
- peft Public Forked from huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
parmanu-lcs2/peft’s past year of commit activity - mpdistil Public
MPDistil is a teacher-student collaborative knowledge distillation framework that enables compact student models to outperform larger teacher models through meta-learning and curriculum learning. Based on the ICLR 2024 paper: **A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge Distillation**
parmanu-lcs2/mpdistil’s past year of commit activity - llm-distil Public
Toolkit implementing knowledge distillation techniques for LLMs with efficient fine-tuning. Based on ACL 2025 paper: **On the Generalization vs Fidelity Paradox in Knowledge Distillation**
parmanu-lcs2/llm-distil’s past year of commit activity - efficient_pruners Public
Toolkit implementing efficient compression methods for compressing LLMs. Implements PruneNet - ICLR 2025 paper: **You only prune once: Designing calibration-free model compression with policy learning**
parmanu-lcs2/efficient_pruners’s past year of commit activity - TransJect Public
Source Code of TransJect: Manifold-Preserving Transformer with Enforced Injectivity. Based on the EMNLP 2023 paper **Manifold-Preserving Transformers are Effective for Short-Long Range Encoding**
parmanu-lcs2/TransJect’s past year of commit activity
Top languages
Loading…
Most used topics
Loading…