Instructions to use AXCXEPT/Llama-3.1-70B-EZO-1.1-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AXCXEPT/Llama-3.1-70B-EZO-1.1-it with Transformers:

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

pipe = pipeline("text-generation", model="AXCXEPT/Llama-3.1-70B-EZO-1.1-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AXCXEPT/Llama-3.1-70B-EZO-1.1-it")
model = AutoModelForCausalLM.from_pretrained("AXCXEPT/Llama-3.1-70B-EZO-1.1-it")
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
Local Apps Settings

vLLM

How to use AXCXEPT/Llama-3.1-70B-EZO-1.1-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AXCXEPT/Llama-3.1-70B-EZO-1.1-it"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AXCXEPT/Llama-3.1-70B-EZO-1.1-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AXCXEPT/Llama-3.1-70B-EZO-1.1-it

SGLang

How to use AXCXEPT/Llama-3.1-70B-EZO-1.1-it 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 "AXCXEPT/Llama-3.1-70B-EZO-1.1-it" \
    --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": "AXCXEPT/Llama-3.1-70B-EZO-1.1-it",
		"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 "AXCXEPT/Llama-3.1-70B-EZO-1.1-it" \
        --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": "AXCXEPT/Llama-3.1-70B-EZO-1.1-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AXCXEPT/Llama-3.1-70B-EZO-1.1-it with Docker Model Runner:
```
docker model run hf.co/AXCXEPT/Llama-3.1-70B-EZO-1.1-it
```

KAZUYA commited on Aug 23, 2024

Commit

3b45767

verified ·

1 Parent(s): 276f5ab

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -117,11 +117,11 @@ Axcxept株式会社は、直接的、間接的、特別、偶発的、結果的
 ### [Hardware]
 H100 × 1(Running in 32h)
-### [We are.]
-[![Axcxept logo](https://cdn-uploads.huggingface.co/production/uploads/657e900beaad53ff67ba84db/8OKW86U986ywttvL2RcbG.png)](https://axcxept.com)
 ## クレジット / Credits
 This model is based on Meta AI's Llama 3.1. We acknowledge and thank the Meta AI team for their work on the base model.
-このモデルは Meta AI の Llama 3.1 をベースにしています。ベースモデルの開発に携わった Meta AI チームに感謝いたします。

 ### [Hardware]
 H100 × 1(Running in 32h)
 ## クレジット / Credits
 This model is based on Meta AI's Llama 3.1. We acknowledge and thank the Meta AI team for their work on the base model.
+このモデルは Meta AI の Llama 3.1 をベースにしています。ベースモデルの開発に携わった Meta AI チームに感謝と尊敬の意を表します。
+### [We are.]
+[![Axcxept logo](https://cdn-uploads.huggingface.co/production/uploads/657e900beaad53ff67ba84db/8OKW86U986ywttvL2RcbG.png)](https://axcxept.com)