README.md

metadata

base_model: mistralai/Mistral-7B-Instruct-v0.2
datasets:
  - mwitiderrick/SwahiliAlpaca
inference: true
model_type: mistral
created_by: mwitiderrick
tags:
  - transformers
license: apache-2.0
language:
  - en
library_name: transformers
pipeline_tag: text-generation

SwahiliInstruct

This is a Mistral model that has been fine-tuned on the Swahili Alpaca dataset for 3 epochs.

Usage

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mwitiderrick/SwahiliInstruct-v0.2")
model = AutoModelForCausalLM.from_pretrained("mwitiderrick/SwahiliInstruct-v0.2", device_map="auto")
query = "Nipe maagizo ya kutengeneza mkate wa mandizi"
text_gen = pipeline(task="text-generation", model=model, tokenizer=tokenizer, max_length=200, do_sample=True, repetition_penalty=1.1)
output = text_gen(f"### Maelekezo:\n{query}\n### Jibu:\n")
print(output[0]['generated_text'])


"""

"""