Instructions to use Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS with Transformers:

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

pipe = pipeline("text-generation", model="Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS")
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("Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS")
model = AutoModelForCausalLM.from_pretrained("Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS", 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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS

SGLang

How to use Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS 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 "Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS" \
    --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": "Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS",
		"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 "Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS" \
        --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": "Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS with Docker Model Runner:
```
docker model run hf.co/Kooten/Mistral-Nemo-Instruct-2407-norefuse-OAS
```

Getting a ValueError upon loading the model, tensors are not matching.

by johann15 - opened Jul 18, 2024

Discussion

johann15

Jul 18, 2024

Getting this problem whenever I load it with Transformers with oobabooga. Am I missing something to load it?

"ValueError: Trying to set a tensor of shape torch.Size([1024, 5120]) in "weight" (which has shape torch.Size([1280, 5120])), this look incorrect."

Kooten

Owner Jul 18, 2024

You need to update transformers
run cmd_windows.bat and then you run pip install git+https://github.com/huggingface/transformers.git -U
this will update transformers and allow you to run the model.

johann15

Jul 18, 2024

Yes, thank you. It's working but it's pretty slow, around 2.32 t/s. I am running it on a 3090, so I guess it has to do with my config.

Kooten

Owner Jul 18, 2024

I get about 5t/s with load-in-8bit, might be overflowing in to ram for you

I'm uploading an exllama version in a few minutes, that gives me about 50t/s at 6.5bpw

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