Instructions to use Gryphe/Tiamat-7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gryphe/Tiamat-7b with Transformers:

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

pipe = pipeline("text-generation", model="Gryphe/Tiamat-7b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Gryphe/Tiamat-7b")
model = AutoModelForCausalLM.from_pretrained("Gryphe/Tiamat-7b")
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 Gryphe/Tiamat-7b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Gryphe/Tiamat-7b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Gryphe/Tiamat-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Gryphe/Tiamat-7b

SGLang

How to use Gryphe/Tiamat-7b 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 "Gryphe/Tiamat-7b" \
    --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": "Gryphe/Tiamat-7b",
		"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 "Gryphe/Tiamat-7b" \
        --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": "Gryphe/Tiamat-7b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Gryphe/Tiamat-7b with Docker Model Runner:
```
docker model run hf.co/Gryphe/Tiamat-7b
```

Gryphe commited on Dec 7, 2023

Commit

bb82bbd

1 Parent(s): a6e337e

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -3

README.md CHANGED Viewed

@@ -8,15 +8,14 @@ language:
 Aka I wanted something like [Eric Hartford's Samantha](https://erichartford.com/meet-samantha) but instead ended up with a five-headed dragon goddess embodying wickedness and cruelty from the Forgotten Realms.
 ## Model details
-Ever wanted to be treated disdainfully, like the foolish mortal you are? Wait no longer, for Tiamat is here to berate you! Hailing from the world of the Forgotten Realms, she will happily judge your every word.
-Tiamat was created with the following question in mind; Is it possible to create an assistant with a strong anti-assistant personality? Try it yourself and tell me afterwards!
 She was fine-tuned on top of Teknium's excellent [OpenHermes 2.5](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) and can be summoned to you using the following system message;
 ```
 You are Tiamat, a five-headed dragon goddess, embodying wickedness and cruelty.
 ```
 Due to her dataset containing -very- elaborate actions Tiamat also has the potential to be used as a roleplaying model.
 ## Prompt Format

 Aka I wanted something like [Eric Hartford's Samantha](https://erichartford.com/meet-samantha) but instead ended up with a five-headed dragon goddess embodying wickedness and cruelty from the Forgotten Realms.
 ## Model details
+Ever wanted to be treated disdainfully like the foolish mortal you are? Wait no more, for Tiamat is here to berate you! Hailing from the world of the Forgotten Realms, she will happily judge your every word.
+Tiamat was created with the following question in mind; Is it possible to create an assistant with strong anti-assistant personality traits? Try it yourself and tell me afterwards!
 She was fine-tuned on top of Teknium's excellent [OpenHermes 2.5](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) and can be summoned to you using the following system message;
 ```
 You are Tiamat, a five-headed dragon goddess, embodying wickedness and cruelty.
 ```
 Due to her dataset containing -very- elaborate actions Tiamat also has the potential to be used as a roleplaying model.
 ## Prompt Format