Instructions to use espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_int8 with Transformers:

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

pipe = pipeline("text-generation", model="espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_int8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_int8")
model = AutoModelForCausalLM.from_pretrained("espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_int8", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_int8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_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": "espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_int8

SGLang

How to use espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_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 "espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_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": "espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_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 "espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_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": "espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_int8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_int8 with Docker Model Runner:
```
docker model run hf.co/espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_int8
```

meta-llama/Meta-Llama-3-8B-Instruct - W8A8_int8 Compression

This is a compressed model using llmcompressor.

Compression Configuration

Base Model: meta-llama/Meta-Llama-3-8B-Instruct
Compression Scheme: W8A8_int8
Dataset: HuggingFaceH4/ultrachat_200k
Dataset Split: train_sft
Number of Samples: 512
Preprocessor: chat
Maximum Sequence Length: 8192

Sample Output

Prompt:

<|begin_of_text|><|start_header_id|>user<|end_header_id|>

Who is Alan Turing?<|eot_id|>

Output:

<|begin_of_text|><|begin_of_text|><|start_header_id|>user<|end_header_id|>

Who is Alan Turing?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Alan Turing (1912-1954) was a British mathematician, computer scientist, logician, and philosopher who made significant contributions to the development of computer science, artificial intelligence, and cryptography. He is widely considered one of the most influential figures in the history of computer science and is often referred to as the "father of computer science" or the "father of artificial intelligence."

Turing was born in London, England, and was a brilliant student who excelled in mathematics and logic. He studied at King's College, Cambridge, where he earned a degree in mathematics and was elected a fellow of King's College

Evaluation

Downloads last month: 20

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for espressor/meta-llama.Meta-Llama-3-8B-Instruct_W8A8_int8

Base model

meta-llama/Meta-Llama-3-8B-Instruct

Quantized

(278)

this model

espressor
/

meta-llama.Meta-Llama-3-8B-Instruct_W8A8_int8