Zaid Ahmad Awan

zaidawan

AI & ML interests

None yet

Recent Activity

updated a model 17 days ago

zaidawan/unsloth_Meta-Llama-3.1-8B-Instruct-bnb-4bit_Adapter

replied to smangrul's post 17 days ago

🚨 New Release of 🤗PEFT! 1. New methods for merging LoRA weights. Refer this HF Post for more details: https://huggingface.co/posts/smangrul/850816632583824 2. AWQ and AQLM support for LoRA. You can now: - Train adapters on top of 2-bit quantized models with AQLM - Train adapters on top of powerful AWQ quantized models Note for inference you can't merge the LoRA weights into the base model! 3. DoRA support: Enabling DoRA is as easy as adding `use_dora=True` to your `LoraConfig`. Find out more about this method here: https://arxiv.org/abs/2402.09353 4. Improved documentation, particularly docs regarding PEFT LoRA+DeepSpeed and PEFT LoRA+FSDP! 📄 Check out the docs at https://huggingface.co/docs/peft/index. 5. Full Release Notes: https://github.com/huggingface/peft/releases/tag/v0.9.0

new activity 17 days ago

hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4:Finetuning AWQ model

View all activity

Organizations

None yet

zaidawan's activity

updated a model 17 days ago

zaidawan/unsloth_Meta-Llama-3.1-8B-Instruct-bnb-4bit_Adapter

Updated 17 days ago

replied to smangrul's post 17 days ago

are we suppose to train LORA Adapter using AWQ base model ?
or if LORA is trained using bnb int 4 or fp16 base model can i use that adapater with AWQ model without losing much in terms of performance and accuracy

New activity in hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4 17 days ago

Finetuning AWQ model

#17 opened 17 days ago by

zaidawan

updated a dataset 20 days ago

zaidawan/synthetic_agents

Viewer • Updated 19 days ago • 27.2k • 14

updated a model 20 days ago

zaidawan/unsloth_test_llama3_8B_finetuned_adapter

Updated 20 days ago