Instructions to use ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned with Transformers:

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

pipe = pipeline("text-generation", model="ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned")
model = AutoModelForCausalLM.from_pretrained("ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned

SGLang

How to use ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned 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 "ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned with Docker Model Runner:
```
docker model run hf.co/ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned
```

Model Card for Model ID

Model Details

This is the model card of a 🤗 transformers model that was developed in the scope of e-commerce hackathon that organized by Teknofest and Trendyol by Lyra AI team, Ahmet Erdem Pamuk.

Developed by: Ahmet Erdem Pamuk
Model type: Text Generation
Language(s) (NLP): English
License: Apache 2.0 LICENSE
Finetuned from model Llama3.1 8B: https://huggingface.co/meta-llama/Llama-3.1-8B

Training Data

The training data was created by open-source LLMs using few-shot prompting technique.

Model Card Contact

You can contact with me on Linkedln, https://linkedin.com/in/ahmet-erdem-pamuk

Downloads last month: 3

Safetensors

Model size

8B params

Tensor type

F32

Model tree for ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned

Base model

meta-llama/Llama-3.1-8B

Finetuned

(1408)

this model

ahmeterdempmk
/

Llama3.1-8B-Trendyol-Hackathon-Tuned

Model Card for Model ID

Model Details

Training Data

Model Card Contact

Model tree for ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned

Dataset used to train ahmeterdempmk/Llama3.1-8B-Trendyol-Hackathon-Tuned