Question Answering
Transformers
Safetensors
Bengali
llama
text-generation
trl
sft
text-generation-inference
4-bit precision
bitsandbytes
Instructions to use asif00/bangla-llama-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use asif00/bangla-llama-4bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="asif00/bangla-llama-4bit")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("asif00/bangla-llama-4bit") model = AutoModelForCausalLM.from_pretrained("asif00/bangla-llama-4bit") - Notebooks
- Google Colab
- Kaggle
Can you help me with your Finetune script
#1
by ar08 - opened
Can you help me with your Finetuning script
You mean, fine-tuning script, right? Sure. I'll upload that too.
Yea
@ar08 I have added the fine-tune script to it's github repo.
Find it here: https://github.com/asiff00/Bangla-Llama
ar08 changed discussion title from Can you help me with your pretraining script to Can you help me with your Finetune script
Thank you so much!
ar08 changed discussion status to closed