Instructions to use BeaverAI/mistral-dory-12b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BeaverAI/mistral-dory-12b with Transformers:

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

pipe = pipeline("text-generation", model="BeaverAI/mistral-dory-12b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BeaverAI/mistral-dory-12b")
model = AutoModelForCausalLM.from_pretrained("BeaverAI/mistral-dory-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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use BeaverAI/mistral-dory-12b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BeaverAI/mistral-dory-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": "BeaverAI/mistral-dory-12b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BeaverAI/mistral-dory-12b

SGLang

How to use BeaverAI/mistral-dory-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 "BeaverAI/mistral-dory-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": "BeaverAI/mistral-dory-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 "BeaverAI/mistral-dory-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": "BeaverAI/mistral-dory-12b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BeaverAI/mistral-dory-12b with Docker Model Runner:
```
docker model run hf.co/BeaverAI/mistral-dory-12b
```

Repetition issue

by mpasila - opened Jul 21, 2024

Discussion

mpasila

Jul 21, 2024

This model seems to suffer from repetition, like it'll get into loops where it'll just repeat stuff over and over again. The normal Instruct model from MistralAI didn't suffer from the same issue.

Fizzarolli

Jul 21, 2024

What do your sampling and formatting settings look like? I didn't experience repetition much in my testing

mpasila

Jul 21, 2024

Ok so after further testing it seems to be mostly caused by DRY repetition penalty not working, when using regular repetition penalty that seems to fix the issue. Though other models seemed to not have trouble with that for some reason.

mpasila changed discussion status to closed Jul 21, 2024

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