Faster fine-tuning using TRL & Unsloth
•
38
Daniel Han-Chen
danielhanchen
AI & ML interests
None yet
Recent Activity
updated
a Space
1 day ago
unsloth/README
updated
a model
2 days ago
unsloth/gemma-2-9b-bnb-4bit
updated
a model
2 days ago
unsloth/Phi-3.5-mini-instruct-bnb-4bit
Articles
Organizations
Posts
3
Post
1022
Vision finetuning is in 🦥Unsloth! You can now finetune Llama 3.2, Qwen2 VL, Pixtral and all Llava variants up to 2x faster and with up to 70% less VRAM usage! Colab to finetune Llama 3.2: https://colab.research.google.com/drive/1j0N4XTY1zXXy7mPAhOC1_gMYZ2F2EBlk?usp=sharing
Post
3608
Yay we got 500K+ monthly HF downloads on our Unsloth HF repo! :) Super appreciate everyone in the OSS community - and thanks for using Unsloth!!
models
105
danielhanchen/finetune_llama_vision
Updated
danielhanchen/Qwen2.5-Coder-3B-Instruct-Q2_K-GGUF
Text Generation
•
Updated
•
25
danielhanchen/Qwen2.5-Coder-1.5B-bnb-4bit
Text Generation
•
Updated
•
8
danielhanchen/gemma2_test
Updated
•
16
danielhanchen/llama-3.2-lora
Updated
danielhanchen/lora_model_new
Updated
danielhanchen/EAGLE-llama2-chat-7B
Updated
danielhanchen/lora_test_vHHHHHH
Updated
danielhanchen/lora_test_v999
Updated
danielhanchen/lora_test_v2
Updated