Instructions to use kingabzpro/llama-2-7b-chat-guanaco with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kingabzpro/llama-2-7b-chat-guanaco with Transformers:

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

pipe = pipeline("text-generation", model="kingabzpro/llama-2-7b-chat-guanaco")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kingabzpro/llama-2-7b-chat-guanaco")
model = AutoModelForCausalLM.from_pretrained("kingabzpro/llama-2-7b-chat-guanaco")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kingabzpro/llama-2-7b-chat-guanaco with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kingabzpro/llama-2-7b-chat-guanaco

SGLang

How to use kingabzpro/llama-2-7b-chat-guanaco 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 "kingabzpro/llama-2-7b-chat-guanaco" \
    --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": "kingabzpro/llama-2-7b-chat-guanaco",
		"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 "kingabzpro/llama-2-7b-chat-guanaco" \
        --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": "kingabzpro/llama-2-7b-chat-guanaco",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kingabzpro/llama-2-7b-chat-guanaco with Docker Model Runner:
```
docker model run hf.co/kingabzpro/llama-2-7b-chat-guanaco
```

How to use it

# pip install transformers accelerate
from transformers import AutoTokenizer
import transformers
import torch
model = "kingabzpro/llama-2-7b-chat-guanaco"
prompt = "Who is Leonardo Da Vinci?"
tokenizer = AutoTokenizer.from_pretrained(model)
pipeline = transformers.pipeline(
    "text-generation",
    model=model,
    torch_dtype=torch.float16,
    device_map="auto",
)
sequences = pipeline(
    f'<s>[INST] {prompt} [/INST]',
    do_sample=True,
    top_k=10,
    num_return_sequences=1,
    eos_token_id=tokenizer.eos_token_id,
    max_length=200,
)
for seq in sequences:
    print(f"Result: {seq['generated_text']}")

Output

Result: <s>[INST] Who is Leonardo Da Vinci? [/INST] Leonardo da Vinci (1452-1519) was a famous Italian polymath, artist, and inventor. (polymath: a person who knows a lot about many different subjects). He is considered one of the greatest painters of all time, and his paintings have had a big influence on many people who have lived after him.

As an artist, Leonardo da Vinci painted beautiful paintings using his skills and knowledge. Some of his most famous paintings are:

* The Mona Lisa: a painting of a woman who is smiling mysteriously, and is considered one of the greatest works of art of the Renaissance.
* The Last Supper: a mural painting depicting the last meal Jesus shared with his twelve disciples before he died.
* The Virgin and Child with St. Anne and St. John the

Downloads last month: 5

Dataset used to train kingabzpro/llama-2-7b-chat-guanaco

Collection including kingabzpro/llama-2-7b-chat-guanaco

ML Projects for Blogs

Collection

Collection of ML projects that I have created over time. • 20 items • Updated Jul 29, 2024 • 2