Instructions to use nvidia/Mistral-NeMo-Minitron-8B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nvidia/Mistral-NeMo-Minitron-8B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="nvidia/Mistral-NeMo-Minitron-8B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nvidia/Mistral-NeMo-Minitron-8B-Instruct")
model = AutoModelForCausalLM.from_pretrained("nvidia/Mistral-NeMo-Minitron-8B-Instruct", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nvidia/Mistral-NeMo-Minitron-8B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nvidia/Mistral-NeMo-Minitron-8B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nvidia/Mistral-NeMo-Minitron-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nvidia/Mistral-NeMo-Minitron-8B-Instruct

SGLang

How to use nvidia/Mistral-NeMo-Minitron-8B-Instruct 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 "nvidia/Mistral-NeMo-Minitron-8B-Instruct" \
    --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": "nvidia/Mistral-NeMo-Minitron-8B-Instruct",
		"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 "nvidia/Mistral-NeMo-Minitron-8B-Instruct" \
        --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": "nvidia/Mistral-NeMo-Minitron-8B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nvidia/Mistral-NeMo-Minitron-8B-Instruct with Docker Model Runner:
```
docker model run hf.co/nvidia/Mistral-NeMo-Minitron-8B-Instruct
```

suhara commited on Oct 3, 2024

Commit

1a28cca

verified ·

1 Parent(s): 02287b6

Update README.md

Browse files

Files changed (1) hide show

README.md +15 -1

README.md CHANGED Viewed

@@ -11,7 +11,7 @@ base_model:
 ## Model Overview
-Mistral-NeMo-Minitron-8B-Instruct is a model for generating responses for various text-generation tasks including roleplaying, retrieval augmented generation, and function calling. It is a fine-tuned version of [nvidia/Mistral-NeMo-Minitron-8B-Base](https://huggingface.co/nvidia/Mistral-NeMo-Minitron-8B-Base), which was pruned and distilled from [Mistral-NeMo 12B](https://huggingface.co/nvidia/Mistral-NeMo-12B-Base) using [our LLM compression technique](https://arxiv.org/abs/2407.14679). The model supports a context length of 8,192 tokens.
 Try this model on [build.nvidia.com](https://build.nvidia.com/nvidia/mistral-nemo-minitron-8b-8k-instruct).
@@ -88,6 +88,20 @@ pipe = pipeline("text-generation", model="nvidia/Mistral-NeMo-Minitron-8B-Instru
 pipe(messages, max_length=64)
 ```
 ## AI Safety Efforts
 The Mistral-NeMo-Minitron-8B-Instruct model underwent AI safety evaluation including adversarial testing via three distinct methods:

 ## Model Overview
+Mistral-NeMo-Minitron-8B-Instruct is a model for generating responses for various text-generation tasks including roleplaying, retrieval augmented generation, and function calling. It is a fine-tuned version of [nvidia/Mistral-NeMo-Minitron-8B-Base](https://huggingface.co/nvidia/Mistral-NeMo-Minitron-8B-Base), which was pruned and distilled from [Mistral-NeMo 12B](https://huggingface.co/nvidia/Mistral-NeMo-12B-Base) using [our LLM compression technique](https://arxiv.org/abs/2407.14679). The model was trained using a multi-stage SFT and preference-based alignment technique with [NeMo Aligner](https://github.com/NVIDIA/NeMo-Aligner). For details on the alignment technique, please refer to the [Nemotron-4 340B Technical Report](https://arxiv.org/abs/2406.11704).
 Try this model on [build.nvidia.com](https://build.nvidia.com/nvidia/mistral-nemo-minitron-8b-8k-instruct).
 pipe(messages, max_length=64)
 ```
+## Evaluation Results
+| Category              | Benchmark             | # Shots | Mistral-NeMo-Minitron-8B-Instruct |
+|-----------------------|-----------------------|---------|-----------------------------------|
+| General               | MMLU                  |       5 |                              70.4 |
+|                       | MT Bench (GPT4-Turbo) |       0 |                              7.86 |
+| Math                  | GMS8K                 |       0 |                              87.1 |
+| Reasoning             | GPQA                  |       0 |                              31.5 |
+| Code                  | HumanEval             |       0 |                              71.3 |
+|                       | MBPP                  |       0 |                              72.5 |
+| Instruction Following | IFEval                |       0 |                              84.4 |
+| Tool Use              | BFCL v2 Live          |       0 |                              67.6 |
 ## AI Safety Efforts
 The Mistral-NeMo-Minitron-8B-Instruct model underwent AI safety evaluation including adversarial testing via three distinct methods: