Text Generation
PEFT
Safetensors
Portuguese
lora
portuguese
question-answering
instruction-tuning
qwen2.5
pt-pt
conversational
Eval Results (legacy)
Instructions to use nelsondiasandre/qwen25-1.5b-pt-qa-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use nelsondiasandre/qwen25-1.5b-pt-qa-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-1.5B-Instruct") model = PeftModel.from_pretrained(base_model, "nelsondiasandre/qwen25-1.5b-pt-qa-lora") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from nelsondiasandre/qwen25-1.5b-pt-qa-lora: direct link, hf CLI and curl.
- Browser
- Download file 11.4 MB
-
https://huggingface.co/nelsondiasandre/qwen25-1.5b-pt-qa-lora/resolve/main/tokenizer.json
- Command line
-
hf download hf://nelsondiasandre/qwen25-1.5b-pt-qa-lora/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/nelsondiasandre/qwen25-1.5b-pt-qa-lora/resolve/main/tokenizer.json
11.4 MB
- Xet hash:
- 84057876e745b7621cb1b682794c63e6425660ba452648e9c935a59e11a2f499
- Size of remote file:
- 11.4 MB
- SHA256:
- 962b8d8c521fefa934665afddae177326e974ddd6a26e69ff31ad6bccbb5593b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.