Instructions to use fsaudm/Meta-Llama-3.1-8B-Instruct-INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fsaudm/Meta-Llama-3.1-8B-Instruct-INT8 with Transformers:

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

pipe = pipeline("text-generation", model="fsaudm/Meta-Llama-3.1-8B-Instruct-INT8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fsaudm/Meta-Llama-3.1-8B-Instruct-INT8")
model = AutoModelForCausalLM.from_pretrained("fsaudm/Meta-Llama-3.1-8B-Instruct-INT8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use fsaudm/Meta-Llama-3.1-8B-Instruct-INT8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fsaudm/Meta-Llama-3.1-8B-Instruct-INT8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fsaudm/Meta-Llama-3.1-8B-Instruct-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fsaudm/Meta-Llama-3.1-8B-Instruct-INT8

SGLang

How to use fsaudm/Meta-Llama-3.1-8B-Instruct-INT8 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 "fsaudm/Meta-Llama-3.1-8B-Instruct-INT8" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fsaudm/Meta-Llama-3.1-8B-Instruct-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "fsaudm/Meta-Llama-3.1-8B-Instruct-INT8" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fsaudm/Meta-Llama-3.1-8B-Instruct-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fsaudm/Meta-Llama-3.1-8B-Instruct-INT8 with Docker Model Runner:
```
docker model run hf.co/fsaudm/Meta-Llama-3.1-8B-Instruct-INT8
```

Meta-Llama-3.1-8B-Instruct-INT8 / README.md

fsaudm

Update README.md

d03b2f1 verified almost 2 years ago

preview code

raw

history blame contribute delete

1.36 kB

metadata

library_name: transformers
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
license: llama3.1
model-index:
  - name: Meta-Llama-3.1-8B-Instruct-INT8
    results: []
language:
  - en
  - de
  - fr
  - it
  - pt
  - hi
  - es
  - th
tags:
  - facebook
  - meta
  - pytorch
  - llama
  - llama-3

Model Card for Model ID

This is a quantized version of Llama 3.1 8B Instruct. Quantized to 8-bit using bistandbytes and accelerate.

Developed by: Farid Saud @ DSRS
License: llama3.1
Base Model: meta-llama/Meta-Llama-3.1-8B-Instruct

Use this model

Use a pipeline as a high-level helper:

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

messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe = pipeline("text-generation", model="fsaudm/Meta-Llama-3.1-8B-Instruct-INT8")
pipe(messages)

Load model directly

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fsaudm/Meta-Llama-3.1-8B-Instruct-INT8")
model = AutoModelForCausalLM.from_pretrained("fsaudm/Meta-Llama-3.1-8B-Instruct-INT8")

The base model information can be found in the original meta-llama/Meta-Llama-3.1-8B-Instruct