Instructions to use fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2 with Transformers:

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

pipe = pipeline("text-generation", model="fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2")
model = AutoModelForCausalLM.from_pretrained("fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2")
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 fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2

SGLang

How to use fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2 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 "fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2" \
    --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": "fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2",
		"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 "fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2" \
        --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": "fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2 with Docker Model Runner:
```
docker model run hf.co/fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2
```

Mistral-7B-Instruct-v0.3 — Pre-compiled for AWS Inferentia2

Pre-compiled Neuron artifacts for Mistral-7B-Instruct-v0.3, ready to run on AWS Inferentia2 with vLLM + vllm-neuron.

No compilation needed — loads directly on inf2.xlarge or inf2.8xlarge.

Compilation parameters

Parameter	Value
tensor-parallel-size	2
max-model-len	4096
max-num-seqs	4
block-size	32
save_sharded_checkpoint	true
NEURON_CC_FLAGS	-O1
Neuron SDK	2.x (NxDI >= 0.7)
vLLM	0.13.0

Repo structure

.
├── config.json, tokenizer.json, ...        # Model config + tokenizer (from base model)
├── model.safetensors                       # Dummy (161 bytes) — required by transformers validation
└── neuron-compiled-artifacts/
    ├── model.pt                            # Compiled NEFF (128 MB)
    ├── neuron_config.json                  # NxDI configuration
    └── weights/
        ├── tp0_sharded_checkpoint.safetensors   # 6.8 GB, rank 0
        └── tp1_sharded_checkpoint.safetensors   # 6.8 GB, rank 1

Why `model.safetensors` is a dummy

The transformers library performs a hard-coded validation check for standard weight files (model.safetensors, pytorch_model.bin, etc.) before any custom model loader can take over. This 161-byte dummy file satisfies that check. The actual weights are the pre-sharded safetensors in neuron-compiled-artifacts/weights/.

Why `save_sharded_checkpoint`

With sharded checkpoints, each NeuronCore rank loads only its ~7 GB shard instead of the full 14 GB model. This cuts peak system RAM usage in half, making inf2.xlarge (16 GB RAM) viable for a 7B model.

Usage with vLLM

This repo is designed to work with vllm-neuron-rosa, which provides a custom entrypoint.sh that:

Runs snapshot_download to fetch the full repo (including neuron-compiled-artifacts/)
Sets NEURON_COMPILED_ARTIFACTS to bypass NxDI's config hash lookup
Launches vLLM with --model pointing to the local download

Deploy on OpenShift / ROSA

# Prerequisites (NFD, KMM, Neuron operators)
oc apply -k https://github.com/fjcloud/vllm-neuron-rosa/deploy/prereqs

# Create namespace
oc new-project neuron-inference

# Deploy
oc apply -k https://github.com/fjcloud/vllm-neuron-rosa/deploy -n neuron-inference

# Build image (first time)
oc start-build vllm-neuron -n neuron-inference --follow

Standalone vLLM (if you handle the download yourself)

# 1. Download the full repo
huggingface-cli download fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2 --local-dir ./model

# 2. Run vLLM with NEURON_COMPILED_ARTIFACTS set
export NEURON_COMPILED_ARTIFACTS=./model/neuron-compiled-artifacts
python -m vllm.entrypoints.openai.api_server \
  --model ./model \
  --tensor-parallel-size 2 \
  --max-model-len 4096 \
  --max-num-seqs 4 \
  --block-size 32 \
  --num-gpu-blocks-override 4 \
  --no-enable-prefix-caching \
  --additional-config '{"override_neuron_config": {"save_sharded_checkpoint": true}}'

Hardware requirements

Instance	RAM	Works?	Notes
`inf2.xlarge`	16 GB	Yes	With pre-sharded weights
`inf2.8xlarge`	128 GB	Yes	Also suitable for recompilation

License

Same as the base model: Mistral License.

Downloads last month: 18

Safetensors

Model size

1 params

Tensor type

F32

Model tree for fjcloud/Mistral-7B-Instruct-v0.3-neuron-inf2-tp2

Base model

mistralai/Mistral-7B-v0.3

Finetuned

mistralai/Mistral-7B-Instruct-v0.3