Instructions to use GrazittiInteractive/llama-2-13b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GrazittiInteractive/llama-2-13b with Transformers:

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

pipe = pipeline("text-generation", model="GrazittiInteractive/llama-2-13b")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("GrazittiInteractive/llama-2-13b")
model = AutoModelForCausalLM.from_pretrained("GrazittiInteractive/llama-2-13b")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use GrazittiInteractive/llama-2-13b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GrazittiInteractive/llama-2-13b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GrazittiInteractive/llama-2-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/GrazittiInteractive/llama-2-13b

SGLang

How to use GrazittiInteractive/llama-2-13b 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 "GrazittiInteractive/llama-2-13b" \
    --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": "GrazittiInteractive/llama-2-13b",
		"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 "GrazittiInteractive/llama-2-13b" \
        --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": "GrazittiInteractive/llama-2-13b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use GrazittiInteractive/llama-2-13b with Docker Model Runner:
```
docker model run hf.co/GrazittiInteractive/llama-2-13b
```

GrazittiInteractive commited on Aug 2, 2023

Commit

38cbb0f

1 Parent(s): 4a48871

13 B ggml

Browse files

Files changed (1) hide show

ggml-model-q4_0.bin +3 -0

ggml-model-q4_0.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:95c6fa19e018342af4eb7e81adc87a274ebc309e448a822826fb2dc99c49027a
+size 7365545088