Instructions to use mistral-hackaton-2026/Mistral_SmartContract_Security with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mistral-hackaton-2026/Mistral_SmartContract_Security with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.3")
model = PeftModel.from_pretrained(base_model, "mistral-hackaton-2026/Mistral_SmartContract_Security")

Transformers

How to use mistral-hackaton-2026/Mistral_SmartContract_Security with Transformers:

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

pipe = pipeline("text-generation", model="mistral-hackaton-2026/Mistral_SmartContract_Security")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mistral-hackaton-2026/Mistral_SmartContract_Security", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use mistral-hackaton-2026/Mistral_SmartContract_Security with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mistral-hackaton-2026/Mistral_SmartContract_Security"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mistral-hackaton-2026/Mistral_SmartContract_Security",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mistral-hackaton-2026/Mistral_SmartContract_Security

SGLang

How to use mistral-hackaton-2026/Mistral_SmartContract_Security 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 "mistral-hackaton-2026/Mistral_SmartContract_Security" \
    --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": "mistral-hackaton-2026/Mistral_SmartContract_Security",
		"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 "mistral-hackaton-2026/Mistral_SmartContract_Security" \
        --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": "mistral-hackaton-2026/Mistral_SmartContract_Security",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use mistral-hackaton-2026/Mistral_SmartContract_Security with Docker Model Runner:
```
docker model run hf.co/mistral-hackaton-2026/Mistral_SmartContract_Security
```

sammy786 commited on Mar 1

Commit

7959187

verified ·

1 Parent(s): bb01f72

Add tokenizer_config.json

Browse files

Files changed (1) hide show

tokenizer_config.json +56 -0

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,56 @@

+{
+  "add_prefix_space": true,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<ANALYZE>",
+    "</ANALYZE>",
+    "<CRITICAL>",
+    "<HIGH>",
+    "<MEDIUM>",
+    "<LOW>",
+    "<VULN_REENTRANCY>",
+    "<VULN_ACCESS>",
+    "<VULN_OVERFLOW>",
+    "<VULN_UNCHECKED>",
+    "<VULN_DOS>",
+    "<VULN_TIMESTAMP>",
+    "<LOCATION>",
+    "</LOCATION>",
+    "<FUNCTION>",
+    "</FUNCTION>",
+    "<LINE>",
+    "</LINE>",
+    "<FIX>",
+    "</FIX>",
+    "<CODE>",
+    "</CODE>",
+    "<EXPLOIT_VECTOR>",
+    "</EXPLOIT_VECTOR>",
+    "<IMPACT>",
+    "</IMPACT>",
+    "<RECOMMENDATION>",
+    "</RECOMMENDATION>",
+    "<CONFIDENCE>",
+    "</CONFIDENCE>",
+    "<GAS_IMPACT>",
+    "</GAS_IMPACT>",
+    "<REPORT>",
+    "</REPORT>",
+    "<SUMMARY>",
+    "</SUMMARY>",
+    "<INFO>",
+    "</INFO>"
+  ],
+  "is_local": false,
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}