Instructions to use FriendliAI/Meta-Llama-3-70B-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FriendliAI/Meta-Llama-3-70B-fp8 with Transformers:

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

pipe = pipeline("text-generation", model="FriendliAI/Meta-Llama-3-70B-fp8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FriendliAI/Meta-Llama-3-70B-fp8")
model = AutoModelForCausalLM.from_pretrained("FriendliAI/Meta-Llama-3-70B-fp8", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FriendliAI/Meta-Llama-3-70B-fp8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FriendliAI/Meta-Llama-3-70B-fp8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FriendliAI/Meta-Llama-3-70B-fp8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/FriendliAI/Meta-Llama-3-70B-fp8

SGLang

How to use FriendliAI/Meta-Llama-3-70B-fp8 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 "FriendliAI/Meta-Llama-3-70B-fp8" \
    --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": "FriendliAI/Meta-Llama-3-70B-fp8",
		"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 "FriendliAI/Meta-Llama-3-70B-fp8" \
        --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": "FriendliAI/Meta-Llama-3-70B-fp8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use FriendliAI/Meta-Llama-3-70B-fp8 with Docker Model Runner:
```
docker model run hf.co/FriendliAI/Meta-Llama-3-70B-fp8
```

pigbug419 commited on Aug 1, 2024

Commit

5dc9fa1

verified ·

1 Parent(s): 1399254

Remove chat template

Browse files

Files changed (1) hide show

tokenizer_config.json +0 -1

tokenizer_config.json CHANGED Viewed

@@ -2050,7 +2050,6 @@
     }
   },
   "bos_token": "<|begin_of_text|>",
-  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
   "model_input_names": [

     }
   },
   "bos_token": "<|begin_of_text|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
   "model_input_names": [