The Fireball-MathMistral-Nemo-Base-2407 Large Language Model (LLM) is a pretrained generative text model of 12B parameters, it significantly outperforms existing models smaller or similar in size.

For more details about this model please refer to our release blog post.

Key features

Released under the Apache 2 License
Trained with a 128k context window
Trained on a large proportion of multilingual and code data
Drop-in replacement of Mistral 7B

Model Architecture

Mistral Nemo is a transformer model, with the following architecture choices:

Layers: 40
Dim: 5,120
Head dim: 128
Hidden dim: 14,436
Activation Function: SwiGLU
Number of heads: 32
Number of kv-heads: 8 (GQA)
Vocabulary size: 2**17 ~= 128k
Rotary embeddings (theta = 1M)

Demo

After installing mistral_inference, a mistral-demo CLI command should be available in your environment.

Transformers

[!IMPORTANT] NOTE: Until a new release has been made, you need to install transformers from source:

pip install git+https://github.com/huggingface/transformers.git

If you want to use Hugging Face transformers to generate text, you can do something like this.

from transformers import AutoModelForCausalLM, AutoTokenizer
model_id = "EpistemeAI/Fireball-MathMistral-Nemo-Base-2407"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)
inputs = tokenizer("Hello my name is", return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=20)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

[!TIP] Unlike previous Mistral models, Mistral Nemo requires smaller temperatures. We recommend to use a temperature of 0.3.

Note

Mistral-Nemo-Base-2407 is a pretrained base model and therefore does not have any moderation mechanisms.