|
|
--- |
|
|
library_name: peft |
|
|
license: mit |
|
|
base_model: microsoft/Phi-4-mini-instruct |
|
|
tags: |
|
|
- axolotl |
|
|
- base_model:adapter:microsoft/Phi-4-mini-instruct |
|
|
- lora |
|
|
- transformers |
|
|
datasets: |
|
|
- DannyAI/African-History-QA-Dataset |
|
|
pipeline_tag: text-generation |
|
|
model-index: |
|
|
- name: phi4_lora_axolotl |
|
|
results: [] |
|
|
language: |
|
|
- en |
|
|
metrics: |
|
|
- bertscore |
|
|
--- |
|
|
|
|
|
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) |
|
|
<details><summary>See axolotl config</summary> |
|
|
|
|
|
axolotl version: `0.14.0.dev0` |
|
|
```yaml |
|
|
base_model: microsoft/Phi-4-mini-instruct |
|
|
model_type: AutoModelForCausalLM |
|
|
tokenizer_type: AutoTokenizer |
|
|
|
|
|
# 1. Dataset Configuration |
|
|
datasets: |
|
|
- path: DannyAI/African-History-QA-Dataset |
|
|
split: train |
|
|
type: alpaca_chat.load_qa |
|
|
system_prompt: "You are a helpful AI assistant specialised in African history which gives concise answers to questions asked" |
|
|
test_datasets: |
|
|
- path: DannyAI/African-History-QA-Dataset |
|
|
split: validation |
|
|
type: alpaca_chat.load_qa |
|
|
# Fixed the missing quote and indentation below |
|
|
system_prompt: "You are a helpful AI assistant specialised in African history which gives concise answers to questions asked" |
|
|
|
|
|
# 2. Output & Chat Configuration |
|
|
output_dir: ./phi4_african_history_lora_out |
|
|
chat_template: tokenizer_default |
|
|
train_on_inputs: false |
|
|
|
|
|
# 3. Batch Size Configuration |
|
|
micro_batch_size: 2 |
|
|
gradient_accumulation_steps: 4 |
|
|
|
|
|
# 4. LoRA Configuration |
|
|
adapter: lora |
|
|
lora_r: 8 |
|
|
lora_alpha: 16 |
|
|
lora_dropout: 0.05 |
|
|
lora_target_modules: [q_proj, v_proj, k_proj, o_proj] |
|
|
|
|
|
# 5. Hardware & Efficiency |
|
|
sequence_len: 2048 |
|
|
sample_packing: true |
|
|
eval_sample_packing: false |
|
|
pad_to_sequence_len: true |
|
|
bf16: true |
|
|
fp16: false |
|
|
|
|
|
# 6. Training Duration & Optimizer |
|
|
max_steps: 650 |
|
|
# removed |
|
|
# num_epochs: |
|
|
warmup_steps: 20 |
|
|
learning_rate: 0.00002 |
|
|
optimizer: adamw_torch |
|
|
lr_scheduler: cosine |
|
|
|
|
|
# 7. Logging & Evaluation |
|
|
wandb_project: phi4_african_history |
|
|
wandb_name: phi4_lora_axolotl |
|
|
|
|
|
eval_strategy: steps |
|
|
eval_steps: 50 |
|
|
save_strategy: steps |
|
|
save_steps: 100 |
|
|
logging_steps: 5 |
|
|
|
|
|
# 8. Public Hugging Face Hub Upload |
|
|
hub_model_id: DannyAI/phi4_lora_axolotl |
|
|
push_adapter_to_hub: true |
|
|
hub_private_repo: false |
|
|
|
|
|
``` |
|
|
|
|
|
</details><br> |
|
|
|
|
|
# Model Card for Model ID |
|
|
|
|
|
This is a LoRA fine-tuned version of **microsoft/Phi-4-mini-instruct** for African History using the **DannyAI/African-History-QA-Dataset** dataset. |
|
|
It achieves a loss value of 1.7479 on the validation set |
|
|
|
|
|
## Model Details |
|
|
|
|
|
### Model Description |
|
|
|
|
|
- **Developed by:** Daniel Ihenacho |
|
|
- **Funded by:** Daniel Ihenacho |
|
|
- **Shared by:** Daniel Ihenacho |
|
|
- **Model type:** Text Generation |
|
|
- **Language(s) (NLP):** English |
|
|
- **License:** mit |
|
|
- **Finetuned from model:** microsoft/Phi-4-mini-instruct |
|
|
|
|
|
## Uses |
|
|
|
|
|
This can be used for QA datasets about African History |
|
|
|
|
|
### Out-of-Scope Use |
|
|
|
|
|
Can be used beyond African History but should not. |
|
|
|
|
|
## How to Get Started with the Model |
|
|
|
|
|
```python |
|
|
from transformers import pipeline |
|
|
from transformers import ( |
|
|
AutoTokenizer, |
|
|
AutoModelForCausalLM) |
|
|
from peft import PeftModel |
|
|
|
|
|
|
|
|
model_id = "microsoft/Phi-4-mini-instruct" |
|
|
|
|
|
tokeniser = AutoTokenizer.from_pretrained(model_id) |
|
|
|
|
|
# load base model |
|
|
model = AutoModelForCausalLM.from_pretrained( |
|
|
model_id, |
|
|
device_map = "auto", |
|
|
torch_dtype = torch.bfloat16, |
|
|
trust_remote_code = False |
|
|
) |
|
|
|
|
|
# Load the fine-tuned LoRA model |
|
|
lora_id = "DannyAI/phi4_lora_axolotl" |
|
|
lora_model = PeftModel.from_pretrained( |
|
|
model,lora_id |
|
|
) |
|
|
|
|
|
generator = pipeline( |
|
|
"text-generation", |
|
|
model=lora_model, |
|
|
tokenizer=tokeniser, |
|
|
) |
|
|
question = "What is the significance of African feminist scholarly activism in contemporary resistance movements?" |
|
|
def generate_answer(question)->str: |
|
|
"""Generates an answer for the given question using the fine-tuned LoRA model. |
|
|
""" |
|
|
messages = [ |
|
|
{"role": "system", "content": "You are a helpful AI assistant specialised in African history which gives concise answers to questions asked."}, |
|
|
{"role": "user", "content": question} |
|
|
] |
|
|
|
|
|
output = generator( |
|
|
messages, |
|
|
max_new_tokens=2048, |
|
|
temperature=0.1, |
|
|
do_sample=False, |
|
|
return_full_text=False |
|
|
) |
|
|
return output[0]['generated_text'].strip() |
|
|
``` |
|
|
``` |
|
|
# Example output |
|
|
African feminist scholarly activism is significant in contemporary resistance movements as it provides a critical framework for understanding and addressing the specific challenges faced by African women in the context of global capitalism, neocolonialism, and patriarchal structures. |
|
|
``` |
|
|
|
|
|
## Training Details |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Ppl | Active (gib) | Allocated (gib) | Reserved (gib) | |
|
|
|:-------------:|:-------:|:----:|:---------------:|:------:|:------------:|:---------------:|:--------------:| |
|
|
| No log | 0 | 0 | 2.1184 | 8.3175 | 14.82 | 14.82 | 15.37 | |
|
|
| 5.394 | 3.8627 | 50 | 2.1004 | 8.1694 | 14.84 | 14.84 | 31.82 | |
|
|
| 4.4484 | 7.7059 | 100 | 2.0367 | 7.6652 | 14.84 | 14.84 | 31.84 | |
|
|
| 3.7583 | 11.5490 | 150 | 1.9785 | 7.2316 | 14.84 | 14.84 | 31.84 | |
|
|
| 3.363 | 15.3922 | 200 | 1.9299 | 6.8886 | 14.84 | 14.84 | 31.84 | |
|
|
| 3.0568 | 19.2353 | 250 | 1.8664 | 6.4652 | 14.84 | 14.84 | 31.84 | |
|
|
| 2.8736 | 23.0784 | 300 | 1.8134 | 6.1314 | 14.84 | 14.84 | 31.79 | |
|
|
| 2.7646 | 26.9412 | 350 | 1.7851 | 5.9604 | 14.84 | 14.84 | 31.79 | |
|
|
| 2.6891 | 30.7843 | 400 | 1.7668 | 5.8523 | 14.84 | 14.84 | 31.79 | |
|
|
| 2.6843 | 34.6275 | 450 | 1.7581 | 5.8014 | 14.84 | 14.84 | 31.79 | |
|
|
| 2.6048 | 38.4706 | 500 | 1.7534 | 5.7739 | 14.84 | 14.84 | 31.79 | |
|
|
| 2.6118 | 42.3137 | 550 | 1.7505 | 5.7573 | 14.84 | 14.84 | 31.79 | |
|
|
| 2.6024 | 46.1569 | 600 | 1.7503 | 5.7565 | 14.84 | 14.84 | 31.79 | |
|
|
| 2.5727 | 50.0 | 650 | 1.7479 | 5.7428 | 14.84 | 14.84 | 31.79 | |
|
|
|
|
|
|
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 2e-05 |
|
|
- train_batch_size: 2 |
|
|
- eval_batch_size: 2 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 8 |
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_steps: 20 |
|
|
- training_steps: 650 |
|
|
|
|
|
### Lora Configuration |
|
|
- r: 8 |
|
|
- lora_alpha: 16 |
|
|
- target_modules: ["q_proj", "v_proj", "k_proj", "o_proj"] |
|
|
- lora_dropout: 0.05 # dataset is small, hence a low dropout value |
|
|
- bias: "none" |
|
|
- task_type: "CAUSAL_LM" |
|
|
|
|
|
## Evaluation |
|
|
|
|
|
#### Metrics |
|
|
| Models | Bert Score | TinyMMLU| TinyTrufulQA |
|
|
|------|--------------|----------------|----------------| |
|
|
| Base model | 0.88868 | 0.6837 |0.49745| |
|
|
| Fine tuned Model | 0.88981 | 0.67371 |0.46626| |
|
|
|
|
|
## Compute Infrastructure |
|
|
|
|
|
[Runpod](https://console.runpod.io/). |
|
|
|
|
|
### Hardware |
|
|
|
|
|
Runpod A40 GPU instance |
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.18.1 |
|
|
- Transformers 4.57.6 |
|
|
- Pytorch 2.9.1+cu128 |
|
|
- Datasets 4.5.0 |
|
|
- Tokenizers 0.22.2 |
|
|
|
|
|
|
|
|
## Citation |
|
|
|
|
|
If you use this dataset, please cite: |
|
|
``` |
|
|
@Model{ |
|
|
Ihenacho2026phi4_lora_axolotl, |
|
|
author = {Daniel Ihenacho}, |
|
|
title = {phi4_lora_axolotl}, |
|
|
year = {2026}, |
|
|
publisher = {Hugging Face Models}, |
|
|
url = {https://huggingface.co/DannyAI/phi4_lora_axolotl}, |
|
|
urldate = {2026-01-27}, |
|
|
} |
|
|
``` |
|
|
|
|
|
## Model Card Authors |
|
|
|
|
|
Daniel Ihenacho |
|
|
|
|
|
## Model Card Contact |
|
|
|
|
|
- [LinkedIn](https://www.linkedin.com/in/daniel-ihenacho-637467223) |
|
|
- [GitHub](https://github.com/daniau23) |
