# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("iamplus/bloomz-7b1-v4")
model = AutoModelForCausalLM.from_pretrained("iamplus/bloomz-7b1-v4")Quick Links
Instruction Tuned Bloomz-7B1 Model on Stanford Alpaca-2 Instruction Tuning dataset (outputs from ChatGPT) (52k data) using Colossal AI
Base Model: bigscience/bloomz-7b1
Training Details :
- Epochs: 5
- Batch Size : 16 instantaneous per device x 1 gradient accumulation steps x 8 gpus = 128
- Max Length : 1024
- Weight Decay : 0
- Learning Rate : 2e-5
- Learning Rate Scheduler Type : Cosine
- Number of warmup steps : 30
- Machine : 8xA100 80GB
Dataset Details :
Dataset : iamplus/Instruction_Tuning
Files :
- stanford_alpaca_it_v2.csv
- Downloads last month
- 7
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="iamplus/bloomz-7b1-v4")