-
Na0s/Llama-3.2-3B-Instruct-Medical-Chatbot-LoRA-FT
Text Generation • 3B • Updated • 3 -
Na0s/Llama-3.2-3B-Medical-Chatbot-LoRA-FT
Text Generation • 3B • Updated • 3 -
meta-llama/Llama-3.2-3B-Instruct
Text Generation • 3B • Updated • 2.21M • • 1.98k -
meta-llama/Llama-3.2-3B
Text Generation • 3B • Updated • 723k • 696
Ali Janati
Na0s
AI & ML interests
NLP, Speech Recognition, Computer Vision, Time Series Forecasting.
Organizations
-
Na0s/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0
Text Generation • 7B • Updated • 2 • 3 -
Na0s/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-2.0
Text Generation • 7B • Updated • 4 • 1 -
Na0s/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-1.0
Text Generation • 7B • Updated • 3 -
Na0s/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT
Text Generation • 7B • Updated • 3
Pruned experts from Mixtral-8x7B-Instruct-v0.1 with respect to the paper "A Provably Effective Method for Pruning Experts in Fine-tuned Sparse MoEs"
-
mistralai/Mixtral-8x7B-Instruct-v0.1
47B • Updated • 490k • 4.64k -
Na0s/Mixtral-8x7B-Instruct-v0.1-LoRA-on-Gates
Text Generation • 47B • Updated • 5 • 1 -
Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-LoRA
Text Generation • 47B • Updated • 6 -
Na0s/Mixtral-8x7B-v0.1-instruct-pruned-random-1-experts
Text Generation • 41B • Updated • 8
-
Na0s/Llama-3.2-3B-Instruct-Medical-Chatbot-LoRA-FT
Text Generation • 3B • Updated • 3 -
Na0s/Llama-3.2-3B-Medical-Chatbot-LoRA-FT
Text Generation • 3B • Updated • 3 -
meta-llama/Llama-3.2-3B-Instruct
Text Generation • 3B • Updated • 2.21M • • 1.98k -
meta-llama/Llama-3.2-3B
Text Generation • 3B • Updated • 723k • 696
Fine-tuning foundation Llama-3.2-3B-Instruct on medical Q&A using differential attention (In progress). Paper: https://arxiv.org/pdf/2410.05258
-
Na0s/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-3.0
Text Generation • 7B • Updated • 2 • 3 -
Na0s/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-2.0
Text Generation • 7B • Updated • 4 • 1 -
Na0s/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT-1.0
Text Generation • 7B • Updated • 3 -
Na0s/Llama-3.1-8B-Pruned-4-Layers_LoRA-PEFT
Text Generation • 7B • Updated • 3
Fine-tuned Whisper Large v3 on Doctor/ Patient consultations.
Pruned experts from Mixtral-8x7B-Instruct-v0.1 with respect to the paper "A Provably Effective Method for Pruning Experts in Fine-tuned Sparse MoEs"
-
mistralai/Mixtral-8x7B-Instruct-v0.1
47B • Updated • 490k • 4.64k -
Na0s/Mixtral-8x7B-Instruct-v0.1-LoRA-on-Gates
Text Generation • 47B • Updated • 5 • 1 -
Na0s/Mixtral-8x7B-Instruct-v0.1-exhaustive-LoRA
Text Generation • 47B • Updated • 6 -
Na0s/Mixtral-8x7B-v0.1-instruct-pruned-random-1-experts
Text Generation • 41B • Updated • 8