Instructions to use ResplendentAI/Aura_L3_8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ResplendentAI/Aura_L3_8B with Transformers:

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

pipe = pipeline("text-generation", model="ResplendentAI/Aura_L3_8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ResplendentAI/Aura_L3_8B")
model = AutoModelForCausalLM.from_pretrained("ResplendentAI/Aura_L3_8B", 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 ResplendentAI/Aura_L3_8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ResplendentAI/Aura_L3_8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ResplendentAI/Aura_L3_8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ResplendentAI/Aura_L3_8B

SGLang

How to use ResplendentAI/Aura_L3_8B 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 "ResplendentAI/Aura_L3_8B" \
    --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": "ResplendentAI/Aura_L3_8B",
		"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 "ResplendentAI/Aura_L3_8B" \
        --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": "ResplendentAI/Aura_L3_8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ResplendentAI/Aura_L3_8B with Docker Model Runner:
```
docker model run hf.co/ResplendentAI/Aura_L3_8B
```

jeiku commited on Apr 19, 2024

Commit

7a2ab18

verified ·

1 Parent(s): ddca16e

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -35

README.md CHANGED Viewed

@@ -1,41 +1,13 @@
 ---
-base_model:
-- ResplendentAI/BlueMoon_Llama3
-- ResplendentAI/Aura_Llama3
-- DevsDoCode/LLama-3-8b-Uncensored
-- Undi95/Meta-Llama-3-8B-Instruct-hf
 library_name: transformers
-tags:
-- mergekit
-- merge
 ---
-# AuraFine
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
-## Merge Details
-### Merge Method
-This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [Undi95/Meta-Llama-3-8B-Instruct-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-Instruct-hf) as a base.
-### Models Merged
-The following models were included in the merge:
-* Aura + [ResplendentAI/BlueMoon_Llama3](https://huggingface.co/ResplendentAI/BlueMoon_Llama3)
-* Aura + [ResplendentAI/Aura_Llama3](https://huggingface.co/ResplendentAI/Aura_Llama3)
-* Aura + [DevsDoCode/LLama-3-8b-Uncensored](https://huggingface.co/DevsDoCode/LLama-3-8b-Uncensored)
-### Configuration
-The following YAML configuration was used to produce this model:
-```yaml
-models:
-  - model: Aura+ResplendentAI/BlueMoon_Llama3
-  - model: Aura+ResplendentAI/Aura_Llama3
-  - model: Aura+DevsDoCode/LLama-3-8b-Uncensored
-merge_method: model_stock
-base_model: Undi95/Meta-Llama-3-8B-Instruct-hf
-dtype: float16
-```

 ---
 library_name: transformers
+license: apache-2.0
+language:
+- en
 ---
+# Aura L3
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/626dfb8786671a29c715f8a9/Bz0CQP-s2PSXpW9eh1jNC.png)
+The next evolution in Aura models, trained on 6 separate datasets and ready to bring you to your knees.
+I am so happy to be one of the first with a finetune of this amazing model. I hope that you all enjoy the finetune as much as I know I will.