Instructions to use JackKozmo29/mailguard-jev-style-1.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JackKozmo29/mailguard-jev-style-1.5b with Transformers:

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

pipe = pipeline("text-generation", model="JackKozmo29/mailguard-jev-style-1.5b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("JackKozmo29/mailguard-jev-style-1.5b")
model = AutoModelForCausalLM.from_pretrained("JackKozmo29/mailguard-jev-style-1.5b", 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 JackKozmo29/mailguard-jev-style-1.5b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JackKozmo29/mailguard-jev-style-1.5b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JackKozmo29/mailguard-jev-style-1.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/JackKozmo29/mailguard-jev-style-1.5b

SGLang

How to use JackKozmo29/mailguard-jev-style-1.5b 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 "JackKozmo29/mailguard-jev-style-1.5b" \
    --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": "JackKozmo29/mailguard-jev-style-1.5b",
		"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 "JackKozmo29/mailguard-jev-style-1.5b" \
        --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": "JackKozmo29/mailguard-jev-style-1.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use JackKozmo29/mailguard-jev-style-1.5b with Docker Model Runner:
```
docker model run hf.co/JackKozmo29/mailguard-jev-style-1.5b
```

JackKozmo29 commited on 5 days ago

Commit

af0e951

verified ·

1 Parent(s): ae6cd4d

Update README.md

Browse files

Files changed (1) hide show

README.md +13 -26

README.md CHANGED Viewed

@@ -1,3 +1,16 @@
 # mailguard-jev-style-1.5b
 **Local System One model for enterprise inbox triage. JEV-compatible typed decisions, no API key required.**
@@ -87,32 +100,6 @@ result = triage(
 ---
-## OpenAI-shim + LangChain (drop-in for Jev pipelines)
-If you already run a LangChain or langgraph agent against Jev, swap the base URL:
-```python
-# Before (Jev):
-llm = ChatOpenAI(base_url="https://api.typesafe.ai/v1", api_key=JEV_API_KEY, model="jev-latest")
-# After (MailGuard local):
-llm = ChatOpenAI(base_url="http://localhost:8000/v1", api_key="not-needed", model="mailguard-jev-style-1.5b")
-```
-Run the OpenAI-compatible shim alongside the model:
-```bash
-pip install fastapi uvicorn transformers torch
-python -c "
-import uvicorn
-# serve_openai_shim.py included in this repo
-"
-```
-Full shim script: [`serve_openai_shim.py`](serve_openai_shim.py) in this repository.
----
 ## Training
 Fine-tuned with LoRA (r=16, alpha=32) on a curated enterprise email corpus:

+---
+language:
+- en
+license: apache-2.0
+tags:
+- text-classification
+- email
+- triage
+- enterprise
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+pipeline_tag: text-generation
+---
 # mailguard-jev-style-1.5b
 **Local System One model for enterprise inbox triage. JEV-compatible typed decisions, no API key required.**
 ---
 ## Training
 Fine-tuned with LoRA (r=16, alpha=32) on a curated enterprise email corpus: