Instructions to use TeeZee/llama-2-7B-pirate-speech-60s with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TeeZee/llama-2-7B-pirate-speech-60s with Transformers:

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

pipe = pipeline("text-generation", model="TeeZee/llama-2-7B-pirate-speech-60s")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("TeeZee/llama-2-7B-pirate-speech-60s")
model = AutoModelForMultimodalLM.from_pretrained("TeeZee/llama-2-7B-pirate-speech-60s")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use TeeZee/llama-2-7B-pirate-speech-60s with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TeeZee/llama-2-7B-pirate-speech-60s"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TeeZee/llama-2-7B-pirate-speech-60s",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/TeeZee/llama-2-7B-pirate-speech-60s

SGLang

How to use TeeZee/llama-2-7B-pirate-speech-60s 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 "TeeZee/llama-2-7B-pirate-speech-60s" \
    --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": "TeeZee/llama-2-7B-pirate-speech-60s",
		"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 "TeeZee/llama-2-7B-pirate-speech-60s" \
        --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": "TeeZee/llama-2-7B-pirate-speech-60s",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use TeeZee/llama-2-7B-pirate-speech-60s with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for TeeZee/llama-2-7B-pirate-speech-60s to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for TeeZee/llama-2-7B-pirate-speech-60s to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TeeZee/llama-2-7B-pirate-speech-60s to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="TeeZee/llama-2-7B-pirate-speech-60s",
    max_seq_length=2048,
)

Docker Model Runner
How to use TeeZee/llama-2-7B-pirate-speech-60s with Docker Model Runner:
```
docker model run hf.co/TeeZee/llama-2-7B-pirate-speech-60s
```

After just 60 steps (8 minutes of training on free colab) some influence is already vivible:

Below is an instruction that describes a task. Write a response that appropriately completes the request.

explain what is machine learinig
### Response:
Machine learnin' be th' process of buildin' computer programs that can automatically improve from experience and
understanding through exposure to data. Machine learning focuses on the development of algorithms that can make
predictions or decisions based on input, rather than explicitly programmed instructions, as in traditional programming.