Mixtral-8x7B-Instruct-v0.1 | NVIDIA NeMo AutoModel

Mixtral-8x7B-Instruct-v0.1 has a checked-in NeMo AutoModel recipe for text generation. The Hugging Face configuration declares the MixtralForCausalLM architecture.

Fine-Tune Mixtral-8x7B-Instruct-v0.1

Follow the installation instructions, then run the recipe from the repository root:

automodel examples/llm_finetune/mistral/mixtral-8x7b-v0-1_squad_peft.yaml --nproc-per-node 8

Use the Slurm launcher guide for the multi-node run.

Choose a Workflow

Goal	Start Here
Run the primary recipe for this model	Use the recipe configuration.
Try another checked-in recipe for this model	Use the alternate recipe.

Configuration

Setting	Configuration
Hardware	-
Strategy	FSDP2; tp_size=4, pp_size=1, cp_size=1
Nodes	2
Features	Checkpointing (enabled=true), LoRA
Advanced	bf16

More Recipes for This Model

mixtral_8x7b_instruct_squad_peft.yaml

Model Reference

Model Architecture

Property	Value
Task	Text generation
Architecture	`MixtralForCausalLM`

Available Models

mistralai/Mixtral-8x7B-Instruct-v0.1

LLM fine-tuning guide