Instructions to use mhenrichsen/danskgpt-tiny-chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mhenrichsen/danskgpt-tiny-chat with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mhenrichsen/danskgpt-tiny-chat")
model = AutoModelForCausalLM.from_pretrained("mhenrichsen/danskgpt-tiny-chat")
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 Settings

vLLM

How to use mhenrichsen/danskgpt-tiny-chat with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/mhenrichsen/danskgpt-tiny-chat

SGLang

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

Docker Model Runner
How to use mhenrichsen/danskgpt-tiny-chat with Docker Model Runner:
```
docker model run hf.co/mhenrichsen/danskgpt-tiny-chat
```

How to convert the model to a gguf model?

by pksorensen - opened Apr 13, 2024

Discussion

pksorensen

Apr 13, 2024

Hi Mads,

I am playing around and would like to convert it to gguf but have given up now :D (i am a newbie) I came to the conclussion that its based on llama and tried using the llama.cpp convert, but failed to do so. Any pointers ?

pksorensen

Apr 13, 2024

Figured it out, was on the right approach but just some currupted files that was messing with me.

tintwotin

Jun 18, 2024

•

edited Jun 18, 2024

Can you share some details on how to convert it to gguf? Would like to try the model in GPT4ALL.

mhenrichsen

Owner Jun 20, 2024

Hi @pksorensen and @tintwotin

I'm sorry about the late reply, I have not been getting any notifications about the discussions.

To convert to gguf, please use llama.cpp: https://github.com/ggerganov/llama.cpp

Remember to use the correct prompt format when chatting with the model :)

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