Instructions to use ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1 with Transformers:

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

pipe = pipeline("text-generation", model="ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1")
model = AutoModelForCausalLM.from_pretrained("ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1

SGLang

How to use ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1 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 "ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1" \
    --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": "ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1",
		"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 "ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1" \
        --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": "ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1 with Docker Model Runner:
```
docker model run hf.co/ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1
```

OwenArli commited on Aug 23, 2024

Commit

4a78bcc

verified ·

1 Parent(s): f186021

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -1

README.md CHANGED Viewed

@@ -13,6 +13,8 @@ This repository is based on the Meta-Llama-3.1-8B-Instruct model and is governed
 Llama-3.1-8B-ArliAI-RPMax-v1.1 is a variant of the Meta-Llama-3.1-8B model, trained on a diverse set of curated RP datasets with a focus on variety and deduplication. This model is designed to be highly creative and non-repetitive, with a unique approach to training that minimizes repetition.
 ### Training Details
 * **Sequence Length**: 8192
@@ -22,7 +24,7 @@ Llama-3.1-8B-ArliAI-RPMax-v1.1 is a variant of the Meta-Llama-3.1-8B model, trai
 ## Quantization
-The model is available in two quantized formats:
 * **FP16**: https://huggingface.co/ArliAI/Llama-3.1-8B-ArliAI-Formax-v1.1
 * **GGUF**: https://huggingface.co/ArliAI/Llama-3.1-8B-ArliAI-Formax-v1.1-GGUF

 Llama-3.1-8B-ArliAI-RPMax-v1.1 is a variant of the Meta-Llama-3.1-8B model, trained on a diverse set of curated RP datasets with a focus on variety and deduplication. This model is designed to be highly creative and non-repetitive, with a unique approach to training that minimizes repetition.
+v1.1 is just a small fix to not train and save the embeddings layer, since v1.0 had the lm_head unnecessarily trained on accident.
 ### Training Details
 * **Sequence Length**: 8192
 ## Quantization
+The model is available in quantized formats:
 * **FP16**: https://huggingface.co/ArliAI/Llama-3.1-8B-ArliAI-Formax-v1.1
 * **GGUF**: https://huggingface.co/ArliAI/Llama-3.1-8B-ArliAI-Formax-v1.1-GGUF