Instructions to use RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8")
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 RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8

SGLang

How to use RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8 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 "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8" \
    --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": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8",
		"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 "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8" \
        --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": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a8
```

Update README.md

by mcronomus - opened Nov 2, 2024

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

-6

Files changed (1) hide show

README.md +4 -6

README.md CHANGED Viewed

@@ -107,12 +107,10 @@ ds = load_dataset("neuralmagic/LLM_compression_calibration", split="train")
 ds = ds.shuffle().select(range(num_samples))
 ds = ds.map(preprocess_fn)
-recipe = GPTQModifier(
-  targets="Linear",
-  scheme="W8A8",
-  ignore=["lm_head"],
-  dampening_frac=0.1,
-)
 model = SparseAutoModelForCausalLM.from_pretrained(
   model_id,

 ds = ds.shuffle().select(range(num_samples))
 ds = ds.map(preprocess_fn)
+recipe = [
+  SmoothQuantModifier(smoothing_strength=0.7),
+  GPTQModifier(scheme="W8A8", targets="Linear", ignore=["lm_head"]),
+]
 model = SparseAutoModelForCausalLM.from_pretrained(
   model_id,