Instructions to use wirthual/Meta-Llama-3.2-1B-Instruct-llamafile with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wirthual/Meta-Llama-3.2-1B-Instruct-llamafile with Transformers:

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

pipe = pipeline("text-generation", model="wirthual/Meta-Llama-3.2-1B-Instruct-llamafile")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("wirthual/Meta-Llama-3.2-1B-Instruct-llamafile", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wirthual/Meta-Llama-3.2-1B-Instruct-llamafile with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "wirthual/Meta-Llama-3.2-1B-Instruct-llamafile"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "wirthual/Meta-Llama-3.2-1B-Instruct-llamafile",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/wirthual/Meta-Llama-3.2-1B-Instruct-llamafile

SGLang

How to use wirthual/Meta-Llama-3.2-1B-Instruct-llamafile 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 "wirthual/Meta-Llama-3.2-1B-Instruct-llamafile" \
    --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": "wirthual/Meta-Llama-3.2-1B-Instruct-llamafile",
		"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 "wirthual/Meta-Llama-3.2-1B-Instruct-llamafile" \
        --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": "wirthual/Meta-Llama-3.2-1B-Instruct-llamafile",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use wirthual/Meta-Llama-3.2-1B-Instruct-llamafile with Docker Model Runner:
```
docker model run hf.co/wirthual/Meta-Llama-3.2-1B-Instruct-llamafile
```

wirthual commited on Sep 26, 2024

Commit

2f0473a

verified ·

1 Parent(s): 9626f29

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -218,7 +218,7 @@ FreeBSD, OpenBSD and NetBSD systems you control on both AMD64 and ARM64.
 ## Quickstart
 ```
-wget https://huggingface.co/wirthual/Meta-Llama-3.2-3B-Instruct-llamafile/resolve/main/Meta-Llama-3.2-1B-Instruct-Q8_0.llamafile
 chmod +x Meta-Llama-3.2-1B-Instruct-Q8_0.llamafile
 ./Meta-Llama-3.2-1B-Instruct-Q8_0.llamafile
 ```

 ## Quickstart
 ```
+wget https://huggingface.co/wirthual/Meta-Llama-3.2-1B-Instruct-llamafile/resolve/main/Meta-Llama-3.2-1B-Instruct-Q8_0.llamafile
 chmod +x Meta-Llama-3.2-1B-Instruct-Q8_0.llamafile
 ./Meta-Llama-3.2-1B-Instruct-Q8_0.llamafile
 ```