aphrc-v2

aphrc-v2

This is a fine-tuned LoRA adapter for the Mistral-7B-Instruct-v0.3 model, specifically trained on the aphrc dataset to improve performance on African health and development questions.

Model Details

• Base Model: mistralai/Mistral-7B-Instruct-v0.3
• Adapter Type: LoRA (Low-Rank Adaptation)
• Target Task: Question answering on African health and development topics
• Training Method: Supervised Fine-Tuning (SFT)
• Author: Adams Wakhungu, Adanian Labs

How to Use

With Transformers and PEFT

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

# Load base model
base_model = "mistralai/Mistral-7B-Instruct-v0.3"
model = AutoModelForCausalLM.from_pretrained(
    base_model,
    torch_dtype=torch.float16,
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(base_model)

# Load the LoRA adapter
model = PeftModel.from_pretrained(model, "adamsw/aphrc-v2")

# Generate text
question = "What are the major health challenges facing Africa today?"
messages = [
    {"role": "user", "content": question}
]

input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
outputs = model.generate(input_ids=input_ids, max_new_tokens=512, temperature=0.7)
response = tokenizer.decode(outputs[0][input_ids.shape[1]:], skip_special_tokens=True)

print(response)

Using Hugging Face Pipeline

from transformers import pipeline
from peft import PeftModel, PeftConfig
from transformers import AutoModelForCausalLM, AutoTokenizer

config = PeftConfig.from_pretrained("adamsw/aphrc-v2")
model = AutoModelForCausalLM.from_pretrained(
    config.base_model_name_or_path,
    torch_dtype=torch.float16,
    device_map="auto"
)
model = PeftModel.from_pretrained(model, "adamsw/aphrc-v2")
tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)

generator = pipeline(
    "text-generation", 
    model=model, 
    tokenizer=tokenizer,
    device_map="auto"
)

question = "What are the major health challenges facing Africa today?"
messages = [
    {"role": "user", "content": question}
]

output = generator(
    messages,
    max_new_tokens=512,
    temperature=0.7,
    pad_token_id=tokenizer.eos_token_id
)
print(output[0]['generated_text'][-1]['content'])

Training Procedure

This model was trained using Supervised Fine-Tuning (SFT) with the TRL library. The training data consisted of African health and development questions with reference answers.

Framework Versions

• PEFT 0.17.1
• TRL: 0.23.0
• Transformers: 4.56.2
• Pytorch: 2.7.1+cu118
• Datasets: 4.1.1
• Tokenizers: 0.22.1

About the Author

This model was developed by Adams Wakhungu at Adanian Labs, focusing on improving language model performance for African health and development contexts.

Citation

If you use this model, please cite:

Cite TRL as:
    
@misc{vonwerra2022trl,
    title        = {{TRL: Transformer Reinforcement Learning}},
    author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
    year         = 2020,
    journal      = {GitHub repository},
    publisher    = {GitHub},
    howpublished = {\url{https://github.com/huggingface/trl}}
}