Instructions to use openerotica/Llama-3-lima-nsfw-16k-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openerotica/Llama-3-lima-nsfw-16k-test with Transformers:

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

pipe = pipeline("text-generation", model="openerotica/Llama-3-lima-nsfw-16k-test")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openerotica/Llama-3-lima-nsfw-16k-test")
model = AutoModelForCausalLM.from_pretrained("openerotica/Llama-3-lima-nsfw-16k-test")
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 Settings

vLLM

How to use openerotica/Llama-3-lima-nsfw-16k-test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openerotica/Llama-3-lima-nsfw-16k-test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openerotica/Llama-3-lima-nsfw-16k-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openerotica/Llama-3-lima-nsfw-16k-test

SGLang

How to use openerotica/Llama-3-lima-nsfw-16k-test 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 "openerotica/Llama-3-lima-nsfw-16k-test" \
    --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": "openerotica/Llama-3-lima-nsfw-16k-test",
		"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 "openerotica/Llama-3-lima-nsfw-16k-test" \
        --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": "openerotica/Llama-3-lima-nsfw-16k-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openerotica/Llama-3-lima-nsfw-16k-test with Docker Model Runner:
```
docker model run hf.co/openerotica/Llama-3-lima-nsfw-16k-test
```

Works fine being a test model!

by 1NoobArtist - opened May 26, 2024

Discussion

1NoobArtist

May 26, 2024

•

edited May 26, 2024

Hi,
Many thanks for creating this model. Works fine being a test model.

But this model is very adamant. It should be taught to answer next set of questions or respond as per the flow of the conversation. At present, this model seems to force its own wishes (as the character). It disregards the next set of commands/chat from the user.

Thanks!

basiliskinstitute

openerotica org May 26, 2024

I noticed the same thing. I'm hoping to fix it with the next iteration which is going to include a lot more multi-turn data and variety. I mostly wanted to do a quick test to make sure I could reasonably extend the context with rope, which did seem to work well.

1NoobArtist

May 26, 2024

will look forward to the next update!

1NoobArtist changed discussion status to closed May 26, 2024

1NoobArtist changed discussion status to open May 26, 2024

Super-Kenil

Sep 13, 2024

This comment has been hidden (marked as Resolved)

1NoobArtist

Nov 14, 2024

@1NoobArtist , I am a complete noob at using Language models, can you tell me how do I use this model?

You can follow this link:
https://youtu.be/1jXiXVWbbRY?si=oZDVts6YkXoLdiUu

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment