Instructions to use Shijasmon/daily_tasks_fine_tuned_llama3_2_1b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Shijasmon/daily_tasks_fine_tuned_llama3_2_1b with Transformers:

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

pipe = pipeline("text-generation", model="Shijasmon/daily_tasks_fine_tuned_llama3_2_1b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Shijasmon/daily_tasks_fine_tuned_llama3_2_1b", dtype="auto")

PEFT
How to use Shijasmon/daily_tasks_fine_tuned_llama3_2_1b with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Shijasmon/daily_tasks_fine_tuned_llama3_2_1b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Shijasmon/daily_tasks_fine_tuned_llama3_2_1b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Shijasmon/daily_tasks_fine_tuned_llama3_2_1b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Shijasmon/daily_tasks_fine_tuned_llama3_2_1b

SGLang

How to use Shijasmon/daily_tasks_fine_tuned_llama3_2_1b 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 "Shijasmon/daily_tasks_fine_tuned_llama3_2_1b" \
    --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": "Shijasmon/daily_tasks_fine_tuned_llama3_2_1b",
		"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 "Shijasmon/daily_tasks_fine_tuned_llama3_2_1b" \
        --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": "Shijasmon/daily_tasks_fine_tuned_llama3_2_1b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Shijasmon/daily_tasks_fine_tuned_llama3_2_1b with Docker Model Runner:
```
docker model run hf.co/Shijasmon/daily_tasks_fine_tuned_llama3_2_1b
```

Daily Tasks Fine Tuned LLaMA 3.2 1B – Weekly & Daily Task Planner

Model Description

This is a fine-tuned LLaMA 3.2 1B model designed to generate structured weekly and daily plans. It can produce:

Workout routines
Study schedules
Meal plans
Other daily task setups

Fine-tuning was done using PEFT LoRA with float16 precision for efficient training on GPU.

Intended Use

This model is intended for personal productivity, fitness planning, and educational scheduling. It is not meant for medical, legal, or critical decision-making.

Usage

from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM

model_name = "your-username/daily_tasks_fine_tuned_llama3_2_1b"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

generator = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
    device=0  # Use -1 for CPU
)

prompt = "Plan a 7-day workout routine for cardiovascular health."
output = generator(prompt, max_new_tokens=600)
print(output[0]['generated_text'])

Downloads last month: -; Downloads are not tracked for this model. How to track