Instructions to use RedHatAI/Meta-Llama-3-8B-Instruct-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Meta-Llama-3-8B-Instruct-FP8 with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/Meta-Llama-3-8B-Instruct-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/Meta-Llama-3-8B-Instruct-FP8")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/Meta-Llama-3-8B-Instruct-FP8")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use RedHatAI/Meta-Llama-3-8B-Instruct-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Meta-Llama-3-8B-Instruct-FP8"
# 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-3-8B-Instruct-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/Meta-Llama-3-8B-Instruct-FP8

SGLang

How to use RedHatAI/Meta-Llama-3-8B-Instruct-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 "RedHatAI/Meta-Llama-3-8B-Instruct-FP8" \
    --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-3-8B-Instruct-FP8",
		"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-3-8B-Instruct-FP8" \
        --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-3-8B-Instruct-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/Meta-Llama-3-8B-Instruct-FP8 with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Meta-Llama-3-8B-Instruct-FP8
```

Update README.md

by abhinavnmagic - opened Jun 11, 2024

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+16

-19

Files changed (1) hide show

README.md +16 -19

README.md CHANGED Viewed

@@ -4,28 +4,25 @@ tags:
 - vllm
 ---
 Meta-Llama-3-8B-Instruct quantized to FP8 weights and activations using per-tensor quantization, ready for inference with vLLM >= 0.5.0.
 Produced using [AutoFP8 with calibration samples from ultrachat](https://github.com/neuralmagic/AutoFP8/blob/147fa4d9e1a90ef8a93f96fc7d9c33056ddc017a/example_dataset.py).
-Accuracy on MMLU:
-```
-vllm (pretrained=meta-llama/Meta-Llama-3-8B-Instruct,gpu_memory_utilization=0.4), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 16
-|      Groups      |Version|Filter|n-shot|Metric|Value |   |Stderr|
-|------------------|-------|------|-----:|------|-----:|---|-----:|
-|mmlu              |N/A    |none  |     0|acc   |0.6569|±  |0.0038|
-| - humanities     |N/A    |none  |     5|acc   |0.6049|±  |0.0068|
-| - other          |N/A    |none  |     5|acc   |0.7203|±  |0.0078|
-| - social_sciences|N/A    |none  |     5|acc   |0.7663|±  |0.0075|
-| - stem           |N/A    |none  |     5|acc   |0.5652|±  |0.0085|
-vllm (pretrained=nm-testing/Meta-Llama-3-8B-Instruct-FP8,quantization=fp8,gpu_memory_utilization=0.4), gen_kwargs: (None), limit: None, num_fewshot: 5, batch_size: 16
-|      Groups      |Version|Filter|n-shot|Metric|Value |   |Stderr|
-|------------------|-------|------|-----:|------|-----:|---|-----:|
-|mmlu              |N/A    |none  |     0|acc   |0.6567|±  |0.0038|
-| - humanities     |N/A    |none  |     5|acc   |0.6072|±  |0.0068|
-| - other          |N/A    |none  |     5|acc   |0.7206|±  |0.0078|
-| - social_sciences|N/A    |none  |     5|acc   |0.7618|±  |0.0075|
-| - stem           |N/A    |none  |     5|acc   |0.5649|±  |0.0085|
-```

 - vllm
 ---
+# Meta-Llama-3-8B-Instruct-FP8
+## Model Overview
 Meta-Llama-3-8B-Instruct quantized to FP8 weights and activations using per-tensor quantization, ready for inference with vLLM >= 0.5.0.
+## Usage and Creation
 Produced using [AutoFP8 with calibration samples from ultrachat](https://github.com/neuralmagic/AutoFP8/blob/147fa4d9e1a90ef8a93f96fc7d9c33056ddc017a/example_dataset.py).
+## Evaluation
+### Open LLM Leaderboard evaluation scores
+|                      | Meta-Llama-3-8B-Instruct | Meta-Llama-3-8B-Instruct-FP8<br>(this model) |
+| :------------------: | :----------------------: | :------------------------------------------------: |
+| arc-c<br>25-shot     | 62.54                    | 61.77                                              |
+| hellaswag<br>10-shot | 78.83                    | 78.56                                              |
+| mmlu<br>5-shot       | 66.60                    | 66.27                                              |
+| truthfulqa<br>0-shot | 52.44                    | 52.35                                              |
+| winogrande<br>5-shot | 75.93                    | 76.4                                              |
+| gsm8k<br>5-shot      | 75.96                    | 73.99                                              |
+| **Average<br>Accuracy**  | **68.71**                    |              **68.22**                                     |
+| **Recovery**             | **100%**                     |              **99.28%**                                     |