Instructions to use abubakaraabi786/tinyllama-peft-merged with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use abubakaraabi786/tinyllama-peft-merged with Transformers:

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

pipe = pipeline("text-generation", model="abubakaraabi786/tinyllama-peft-merged")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("abubakaraabi786/tinyllama-peft-merged")
model = AutoModelForCausalLM.from_pretrained("abubakaraabi786/tinyllama-peft-merged")
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]:]))

PEFT
How to use abubakaraabi786/tinyllama-peft-merged with PEFT:
```
Task type is invalid.
```
Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use abubakaraabi786/tinyllama-peft-merged with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "abubakaraabi786/tinyllama-peft-merged"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "abubakaraabi786/tinyllama-peft-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/abubakaraabi786/tinyllama-peft-merged

SGLang

How to use abubakaraabi786/tinyllama-peft-merged 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 "abubakaraabi786/tinyllama-peft-merged" \
    --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": "abubakaraabi786/tinyllama-peft-merged",
		"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 "abubakaraabi786/tinyllama-peft-merged" \
        --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": "abubakaraabi786/tinyllama-peft-merged",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use abubakaraabi786/tinyllama-peft-merged with Docker Model Runner:
```
docker model run hf.co/abubakaraabi786/tinyllama-peft-merged
```

🦙 TinyLlama PEFT Merged

A fully merged, production-ready TinyLlama model fine-tuned with PEFT LoRA

📌 Quick Facts

Attribute	Value
Model Size	2.2 GB
Parameters	1.1 Billion
Format	PyTorch Safetensors
Precision	FP16
Context	2048 tokens
Training Framework	PEFT + TRL
Inference	No PEFT required

🚀 Quick Start

from transformers import AutoTokenizer, AutoModelForCausalLM

# One-liner to load
tokenizer = AutoTokenizer.from_pretrained("arif-butt/tinyllama-peft-merged")
model = AutoModelForCausalLM.from_pretrained(
    "arif-butt/tinyllama-peft-merged",
    torch_dtype=torch.float16,
    device_map="auto"
)

# Generate
prompt = "Q: What courses does Arif teach?\nA:"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=100)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

📦 What's Inside
tinyllama-peft-merged/
├── model.safetensors      # 2.2 GB — merged weights
├── config.json            # Model architecture
├── generation_config.json # Default generation settings
├── tokenizer.json         # Vocabulary (1.76 MB)
├── tokenizer_config.json  # Tokenizer settings
└── special_tokens_map.json # Special tokens

No adapter files. No PEFT needed. Just load and go.


🔧 Generation Settings
outputs = model.generate(
    **inputs,
    max_new_tokens=150,
    temperature=0.7,
    top_p=0.95,
    do_sample=True,
    repetition_penalty=1.1,
    pad_token_id=tokenizer.eos_token_id,
)


💬 Prompt Format
Q: Your question here?
A:
Example:

  Q: What is deep learning?
A: Deep learning is a subset of machine learning...


Q: What is Python?
A: Python is a high-level, interpreted programming language known for its simple, readable syntax. It supports multiple programming paradigms including object-oriented, imperative, and functional programming.

Q: Explain gradient descent
A: Gradient descent is an optimization algorithm used to minimize the loss function in machine learning models. It works by iteratively moving parameters in the direction of the negative gradient.

Q: Name Arif's courses
A: Dr. Muhammad Arif Butt teaches Python Programming, Data Structures & Algorithms, Machine Learning, and Deep Learning courses.

Epoch 1: ████████████████░░░░ 0.8
Epoch 2: ████████████████████ 0.4
Epoch 3: ████████████████████ 0.05

Downloads last month: 1,951

Safetensors

Model size

1B params

Tensor type

F16

Model tree for abubakaraabi786/tinyllama-peft-merged

Base model

TinyLlama/TinyLlama-1.1B-Chat-v1.0

Adapter

(1508)

this model

abubakaraabi786
/

tinyllama-peft-merged

🦙 TinyLlama PEFT Merged

📌 Quick Facts

🚀 Quick Start

Model tree for abubakaraabi786/tinyllama-peft-merged

Dataset used to train abubakaraabi786/tinyllama-peft-merged