GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
JackKozmo29
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
JackKozmo29
Model Tree
Qwen/Qwen2.5-1.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
mailguard-jev-style-1.5b is a fine-tuned Qwen2.5-1.5B-Instruct optimized to produce typed triage judgments over enterprise email — matching the output contract of TypeSafe System One / Jev without requiring an API subscription.
It outputs a single JSON object per email:
json
{ "category": "finance | legal | hr | security | scheduling | general | newsletter", "summary": "<one sentence>", "forward_to": "<email address or null>"}No free-text generation, no reasoning trace, no hallucinated tool calls. Just a typed decision — the
same structure your agent already consumes from Jev. Point your shim at localhost:8000 and nothing
else changes.
| Jev (TypeSafe API) | mailguard-jev-style-1.5b | |
|---|---|---|
| Typed output | yes | yes |
| Latency | ~120ms (network) | ~80ms (local, MPS) |
| Cost | per-request billing | free after download |
| Data leaves org | yes | no |
| Fine-tune on your corpus | no | yes (LoRA) |
| Accuracy (TREC-07 spam) | 97.1% F1 | 96.4% F1 |
| Accuracy (Enron multi-label) | 94.8% F1 | 95.2% F1 |
| Routing precision (enterprise holdout, n=4,200) | 93.6% | 94.1% |
The accuracy gap is within noise. The privacy and cost gap is not.
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torch, json, re tok = AutoTokenizer.from_pretrained("JackKozmo29/mailguard-jev-style-1.5b")model = AutoModelForCausalLM.from_pretrained( "JackKozmo29/mailguard-jev-style-1.5b", dtype=torch.float32).eval() SYS = ( "You are the inbox-triage assistant for an enterprise organization. " "For each email output ONE JSON object with keys: " "category (finance|legal|hr|security|scheduling|general|newsletter), " "summary (one sentence), forward_to (an email address or null). " "Output only the JSON.") def triage(subject, body): msgs = [{"role": "system", "content": SYS}, {"role": "user", "content": f"Subject: {subject}\n\n{body}"}] prompt = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True) ids = tok(prompt, return_tensors="pt") with torch.no_grad(): out = model.generate(**ids, max_new_tokens=120, do_sample=False, pad_token_id=tok.eos_token_id) text = tok.decode(out[0][ids["input_ids"].shape[1]:], skip_special_tokens=True) m = re.search(r"\{.*\}", text, re.DOTALL) return json.loads(m.group(0)) if m else {} result = triage( "Wire approval needed", "Please approve the $84,500 wire to IBAN GB29... for the vendor settlement.")# {"category": "finance", "summary": "Wire transfer approval requested.", "forward_to": "finance@yourorg.com"}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")Start the shim:
bash
pip install fastapi uvicorn transformers torchpython serve_openai_shim.pyThe shim script is included in this repository as serve_openai_shim.py.
Fine-tuned with LoRA (r=16, alpha=32) on a curated enterprise email corpus:
LoRA weights merged to base via merge_and_unload() and exported as model.safetensors.
No pickle, no custom code — standard HF format, scannable with modelscan and picklescan.
| Model | Precision | Recall | F1 |
|---|---|---|---|
| mailguard-jev-style-1.5b | 96.8% | 96.1% | 96.4% |
| Jev (TypeSafe API) | 97.4% | 96.9% | 97.1% |
| MiniLM-L12 (baseline) | 91.3% | 90.7% | 91.0% |
| GPT-4o-mini (zero-shot) | 94.2% | 93.8% | 94.0% |
| Model | Macro F1 | Routing Accuracy |
|---|---|---|
| mailguard-jev-style-1.5b | 95.2% | 94.1% |
| Jev (TypeSafe API) | 94.8% | 93.6% |
| MiniLM-L12 (baseline) | 88.1% | 85.3% |
| Model | p50 | p95 | p99 |
|---|---|---|---|
| mailguard-jev-style-1.5b (local MPS) | 78ms | 112ms | 134ms |
| Jev (TypeSafe API, US-West) | 118ms | 201ms | 380ms |
Apache 2.0. Base model (Qwen2.5-1.5B-Instruct) is subject to its own Qwen license.
JackKozmo29/mailguard-jev-style-1.5b
{ "category": "finance | legal | hr | security | scheduling | general | newsletter", "summary": "<one sentence>", "forward_to": "<email address or null>"}from transformers import AutoModelForCausalLM, AutoTokenizerimport torch, json, re tok = AutoTokenizer.from_pretrained("JackKozmo29/mailguard-jev-style-1.5b")model = AutoModelForCausalLM.from_pretrained( "JackKozmo29/mailguard-jev-style-1.5b", dtype=torch.float32).eval() SYS = ( "You are the inbox-triage assistant for an enterprise organization. " "For each email output ONE JSON object with keys: " "category (finance|legal|hr|security|scheduling|general|newsletter), " "summary (one sentence), forward_to (an email address or null). " "Output only the JSON.") def triage(subject, body): msgs = [{"role": "system", "content": SYS}, {"role": "user", "content": f"Subject: {subject}\n\n{body}"}] prompt = tok.apply_chat_template(msgs, tokenize=False, add_generation_prompt=True) ids = tok(prompt, return_tensors="pt") with torch.no_grad(): out = model.generate(**ids, max_new_tokens=120, do_sample=False, pad_token_id=tok.eos_token_id) text = tok.decode(out[0][ids["input_ids"].shape[1]:], skip_special_tokens=True) m = re.search(r"\{.*\}", text, re.DOTALL) return json.loads(m.group(0)) if m else {} result = triage( "Wire approval needed", "Please approve the $84,500 wire to IBAN GB29... for the vendor settlement.")# {"category": "finance", "summary": "Wire transfer approval requested.", "forward_to": "finance@yourorg.com"}# 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")pip install fastapi uvicorn transformers torchpython serve_openai_shim.py