Instructions to use DannyAI/phi4_lora_axolotl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DannyAI/phi4_lora_axolotl with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("microsoft/Phi-4-mini-instruct")
model = PeftModel.from_pretrained(base_model, "DannyAI/phi4_lora_axolotl")

Transformers

How to use DannyAI/phi4_lora_axolotl with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="DannyAI/phi4_lora_axolotl", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DannyAI/phi4_lora_axolotl", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("DannyAI/phi4_lora_axolotl", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use DannyAI/phi4_lora_axolotl with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DannyAI/phi4_lora_axolotl"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DannyAI/phi4_lora_axolotl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DannyAI/phi4_lora_axolotl

SGLang

How to use DannyAI/phi4_lora_axolotl with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "DannyAI/phi4_lora_axolotl" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DannyAI/phi4_lora_axolotl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "DannyAI/phi4_lora_axolotl" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DannyAI/phi4_lora_axolotl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DannyAI/phi4_lora_axolotl with Docker Model Runner:
```
docker model run hf.co/DannyAI/phi4_lora_axolotl
```

See axolotl config

axolotl version: 0.14.0.dev0

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

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

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.

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

Downloads last month: 4

Model tree for DannyAI/phi4_lora_axolotl

Base model

microsoft/Phi-4-mini-instruct

Adapter

(173)

this model

DannyAI
/

phi4_lora_axolotl