Faster fine-tuning using TRL & Unsloth
•
43
Daniel Han-Chen
danielhanchen
AI & ML interests
None yet
Recent Activity
new activity
8 days ago
unsloth/Llama-3.3-70B-Instruct:Big thanks for these "without original" uploads!
updated
a model
9 days ago
danielhanchen/lora
updated
a model
10 days ago
danielhanchen/combined_saving_new
Articles
Organizations
Posts
4
Post
1406
I uploaded GGUFs, 4bit bitsandbytes and full 16bit precision weights for Llama 3.3 70B Instruct are here:
unsloth/llama-33-all-versions-67535d7d994794b9d7cf5e9f
You can also finetune Llama 3.3 70B in under 48GB of VRAM with Unsloth!
GGUFs: unsloth/Llama-3.3-70B-Instruct-GGUF
BnB 4bit: unsloth/Llama-3.3-70B-Instruct-bnb-4bit
16bit: unsloth/Llama-3.3-70B-Instruct
You can also finetune Llama 3.3 70B in under 48GB of VRAM with Unsloth!
GGUFs: unsloth/Llama-3.3-70B-Instruct-GGUF
BnB 4bit: unsloth/Llama-3.3-70B-Instruct-bnb-4bit
16bit: unsloth/Llama-3.3-70B-Instruct
Post
1335
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
models
108
danielhanchen/lora
Image-Text-to-Text
•
Updated
danielhanchen/combined_saving_new
Updated
danielhanchen/lora_upload
Image-Text-to-Text
•
Updated
•
4
danielhanchen/unsloth_finetune_ocr
Image-Text-to-Text
•
Updated
•
14
danielhanchen/finetune_llama_vision
Updated
danielhanchen/Qwen2.5-Coder-3B-Instruct-Q2_K-GGUF
Text Generation
•
Updated
•
5
danielhanchen/Qwen2.5-Coder-1.5B-bnb-4bit
Text Generation
•
Updated
•
12
danielhanchen/gemma2_test
Updated
•
20
danielhanchen/llama-3.2-lora
Updated
danielhanchen/lora_model_new
Updated