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

Libraries

How to use Delcos/Velara with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Delcos/Velara")
model = AutoModelForCausalLM.from_pretrained("Delcos/Velara", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Delcos/Velara with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Delcos/Velara

SGLang

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

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

Delcos commited on Dec 5, 2023

Commit

f2cea3d

1 Parent(s): 24c800c

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -24,7 +24,7 @@ Uncensored
 Velara was made to adress issues I found in other chat models. These include:
-##### Sticking to the character in-world
 Velara will stick to the character in-world. Meaning she can "use" addons or other things by adding them to the prompt. Keep in mind these act as suggestions and she generally makes up what they actually "do".
 # Prompt Template
@@ -44,7 +44,7 @@ Always take the entire conversation into account when forming and writing a repl
 # Recommended Settings
-##### Defaults:
 ```
 temperature: 0.77
@@ -53,7 +53,7 @@ top_k: 20
 repetition_penalty: 1.2
 ```
-##### Better context but a little more repetitive in some cases:
 ```
 temperature: 0.8

 Velara was made to adress issues I found in other chat models. These include:
+#### Sticking to the character in-world
 Velara will stick to the character in-world. Meaning she can "use" addons or other things by adding them to the prompt. Keep in mind these act as suggestions and she generally makes up what they actually "do".
 # Prompt Template
 # Recommended Settings
+#### Defaults:
 ```
 temperature: 0.77
 repetition_penalty: 1.2
 ```
+#### Better context but a little more repetitive in some cases:
 ```
 temperature: 0.8