Instructions to use LatitudeGames/Wayfarer-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LatitudeGames/Wayfarer-12B with Transformers:

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

pipe = pipeline("text-generation", model="LatitudeGames/Wayfarer-12B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LatitudeGames/Wayfarer-12B")
model = AutoModelForCausalLM.from_pretrained("LatitudeGames/Wayfarer-12B")
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

vLLM

How to use LatitudeGames/Wayfarer-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LatitudeGames/Wayfarer-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LatitudeGames/Wayfarer-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LatitudeGames/Wayfarer-12B

SGLang

How to use LatitudeGames/Wayfarer-12B 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 "LatitudeGames/Wayfarer-12B" \
    --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": "LatitudeGames/Wayfarer-12B",
		"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 "LatitudeGames/Wayfarer-12B" \
        --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": "LatitudeGames/Wayfarer-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LatitudeGames/Wayfarer-12B with Docker Model Runner:
```
docker model run hf.co/LatitudeGames/Wayfarer-12B
```

Bigger models of this?

by Adzeiros - opened Jan 26, 2025

Discussion

Adzeiros

Jan 26, 2025

Curious if you would be making a version of this using a bigger model? 32B, 70B, 100B?

Love the idea of this model, and it works rlly well, just think a bigger model could really do this type of system well. I did notice times where this model did not fully understand the context or words correctly in some messages, getting mad at a character even though the character agreed with them, etc...

SkyStach

Feb 16, 2025

I've noticed these context and wording issues too. This model has potential though. I think it need a V2 was made that fixes it up but it's creative and entertaining otherwise.

Gryphe

Latitude org Feb 21, 2025

In case you haven't noticed, there's a 70B version now!

Gryphe changed discussion status to closed Feb 21, 2025

ThijsL202

Feb 21, 2025

•

edited Feb 21, 2025

In case you haven't noticed, there's a 70B version now!

I tried it and... As much as I dislike Llama 3 70B... It's surprisingly good for normal back-and-forth roleplay, I've never had any coherence with 70B models until I tried this one. (104 messages in)

Using IQ4_XS
Thank you all!

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