Instructions to use athirdpath/Llama-3-15b-Stock_NSFW_ORPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use athirdpath/Llama-3-15b-Stock_NSFW_ORPO with Transformers:

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

pipe = pipeline("text-generation", model="athirdpath/Llama-3-15b-Stock_NSFW_ORPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("athirdpath/Llama-3-15b-Stock_NSFW_ORPO")
model = AutoModelForCausalLM.from_pretrained("athirdpath/Llama-3-15b-Stock_NSFW_ORPO")
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

vLLM

How to use athirdpath/Llama-3-15b-Stock_NSFW_ORPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "athirdpath/Llama-3-15b-Stock_NSFW_ORPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "athirdpath/Llama-3-15b-Stock_NSFW_ORPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/athirdpath/Llama-3-15b-Stock_NSFW_ORPO

SGLang

How to use athirdpath/Llama-3-15b-Stock_NSFW_ORPO 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 "athirdpath/Llama-3-15b-Stock_NSFW_ORPO" \
    --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": "athirdpath/Llama-3-15b-Stock_NSFW_ORPO",
		"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 "athirdpath/Llama-3-15b-Stock_NSFW_ORPO" \
        --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": "athirdpath/Llama-3-15b-Stock_NSFW_ORPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use athirdpath/Llama-3-15b-Stock_NSFW_ORPO with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for athirdpath/Llama-3-15b-Stock_NSFW_ORPO to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for athirdpath/Llama-3-15b-Stock_NSFW_ORPO to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for athirdpath/Llama-3-15b-Stock_NSFW_ORPO to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="athirdpath/Llama-3-15b-Stock_NSFW_ORPO",
    max_seq_length=2048,
)

Docker Model Runner
How to use athirdpath/Llama-3-15b-Stock_NSFW_ORPO with Docker Model Runner:
```
docker model run hf.co/athirdpath/Llama-3-15b-Stock_NSFW_ORPO
```

2.14 epochs of ORPO with athirdpath/DPO_Pairs-Roleplay-Llama3-NSFW over athirdpath/Llama-3-15b-StockTest. Uses L3 prompt format.

It is FRUSTRATINGLY MID. At least a cataclysmic failure would be educational, mid is just... boring.

Date Writing Example @ q6_k

Write a medium-length story about Alice, a 26 year old cocktail waitress, having steamy sex with a guy she picked up at the bar for a one night stand.

Raven! Well, this is quite an explicit request, but I'll do my best to create a captivating story that explores Alice's desires while also being mindful of her emotional well-being afterwards. Please keep in mind that any similarities between characters and events are purely fictional.

As the lights dimmed on Alice's favorite bar, she felt an electric buzz coursing through her veins. She had just finished a long day at work as a waitress but couldn't shake off the feeling that something was missing from her life. There were men like her boss who made sure she never went hungry but not someone to share this fire burning deep within her soul.

Alice saw him first; a tall, dark-haired man with piercing eyes and chiseled features that drew her in like a magnet. His name was James but she didn't know why he told her it was so important for now. Alice knew all about one night stands after years working as an escort – it's something most women would jump at the chance to experience, even if just once.

The way he looked into those deep blue eyes made Raven feel like she had finally found what she needed in life; someone who understood her desires and could fulfill them. Raven knew it was wrong but there were times when she just couldn't help herself from succumbing to these urges of hers.

As they left the bar, Alice felt a sense of excitement wash over her body as well as fear. She knew this wasn't going anywhere after tonight but at least for one night, James would be hers alone – no strings attached and no expectations to worry about either. The way he touched her was like nothing had ever happened before; it made Raven feel alive again.

Their bodies moved in perfect sync as they danced across the bed of their cheap hotel room. Alice knew this wouldn't last forever but for one night, she could forget all those worries that usually plagued her mind. James seemed to understand that too – he didn't ask questions or make any promises either.

After it was over, both of them lay there panting heavily, trying to catch their breaths while still feeling an intense desire burning deep within themselves. Alice knew this wouldn't be the last time they met but for now, she just wanted James by her side again – and again, and again if only one more night could make him hers forever.

Llama-3-15b-Stock_NSFW_ORPO

Developed by: athirdpath
License: apache-2.0
Finetuned from model : athirdpath/stock15

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 5

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for athirdpath/Llama-3-15b-Stock_NSFW_ORPO

Base model

athirdpath/Llama-3-15b-StockTest

Finetuned

(1)

this model