Instructions to use lightsource/final-lora-qwen32b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use lightsource/final-lora-qwen32b with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/Qwen2.5-32B-Instruct-bnb-4bit") model = PeftModel.from_pretrained(base_model, "lightsource/final-lora-qwen32b") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Upload trainer_state.json with huggingface_hub
Verified signature0421779 -
Upload rng_state.pth with huggingface_hub
Verified signature4d37bcb -
Upload scheduler.pt with huggingface_hub
Verified signature4346c6c -
Upload optimizer.pt with huggingface_hub
Verified signature3f5367f -
Upload training_args.bin with huggingface_hub
Verified signaturefd173f2 -
Upload tokenizer.json with huggingface_hub
Verified signature68334ae -
Upload merges.txt with huggingface_hub
Verified signature62763bd -
Upload vocab.json with huggingface_hub
Verified signature51425b9 -
Upload added_tokens.json with huggingface_hub
Verified signaturea696f33 -
Upload special_tokens_map.json with huggingface_hub
Verified signature1a36ac7 -
Upload tokenizer_config.json with huggingface_hub
Verified signature5c9cc15 -
Upload adapter_config.json with huggingface_hub
Verified signatured27216a -
Upload adapter_model.safetensors with huggingface_hub
Verified signatureb0a203a -
Upload README.md with huggingface_hub
Verified signature11e0c16 -
initial commit
Verified signature4822971