Instructions to use mbakry484/Llama_Ragging_Tuned with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mbakry484/Llama_Ragging_Tuned with Transformers:

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

pipe = pipeline("text-generation", model="mbakry484/Llama_Ragging_Tuned")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mbakry484/Llama_Ragging_Tuned")
model = AutoModelForCausalLM.from_pretrained("mbakry484/Llama_Ragging_Tuned", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mbakry484/Llama_Ragging_Tuned with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mbakry484/Llama_Ragging_Tuned"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mbakry484/Llama_Ragging_Tuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/mbakry484/Llama_Ragging_Tuned

SGLang

How to use mbakry484/Llama_Ragging_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 "mbakry484/Llama_Ragging_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": "mbakry484/Llama_Ragging_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 "mbakry484/Llama_Ragging_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": "mbakry484/Llama_Ragging_Tuned",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use mbakry484/Llama_Ragging_Tuned with Docker Model Runner:
```
docker model run hf.co/mbakry484/Llama_Ragging_Tuned
```

Hardware Requirements

GPU with ≥16GB VRAM
CUDA 11.8+
Python 3.9+

Quick Start

# Load full RAG system
from transformers import AutoModelForCausalLM
from langchain.vectorstores import FAISS

model = AutoModelForCausalLM.from_pretrained(
    "mbakry484/Llama_Ragging_Tuned",
    device_map="auto"
)

# Load FAISS index
vector_store = FAISS.load_local(
    "faiss_index",
    embeddings,
    index_name="cognitive_therapy_index",
    allow_dangerous_deserialization=True
)

Downloads last month: 10

Safetensors

Model size

1B params

Tensor type

F32

F16