Instructions to use smithblack-0/llama3_baseline with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use smithblack-0/llama3_baseline with Transformers:

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

pipe = pipeline("text-generation", model="smithblack-0/llama3_baseline", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("smithblack-0/llama3_baseline", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use smithblack-0/llama3_baseline with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "smithblack-0/llama3_baseline"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "smithblack-0/llama3_baseline",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/smithblack-0/llama3_baseline

SGLang

How to use smithblack-0/llama3_baseline 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 "smithblack-0/llama3_baseline" \
    --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": "smithblack-0/llama3_baseline",
		"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 "smithblack-0/llama3_baseline" \
        --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": "smithblack-0/llama3_baseline",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use smithblack-0/llama3_baseline with Docker Model Runner:
```
docker model run hf.co/smithblack-0/llama3_baseline
```

llama3_baseline / __init__.py

smithblack-0

Update architecture and tokenizer

b7858ac verified 2 months ago

raw

history blame contribute delete

397 Bytes

	from .attention import GroupedQueryAttention
	from .configuration import Llama3Config
	from .decoder_layer import DecoderLayer
	from .huggingface import Llama3ForCausalLM
	from .mlp import SwiGLUMLP
	from .model import Llama3Model
	from .rope import RotaryEmbedding

	__all__ = ["DecoderLayer", "GroupedQueryAttention", "Llama3Config", "Llama3ForCausalLM", "Llama3Model", "RotaryEmbedding", "SwiGLUMLP"]