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.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
JackKozmo29
Model Tree
Qwen/Qwen2.5-1.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
sevclassifier-jev-style-1.5b is a fine-tuned Qwen2.5-1.5B-Instruct that produces typed incident severity classifications — matching the output contract of TypeSafe System One / Jev for incident triage pipelines.
It outputs a single JSON object per incident:
json
{ "severity": "SEV1 | SEV2 | SEV3 | SEV4", "rationale": "<one sentence>", "escalate": true, "page_oncall": false, "affected_blast_radius": "<scope description>"}Feed it SIEM alerts, PagerDuty payloads, or Datadog monitor events. Get a typed decision the agent acts on immediately — page oncall for SEV1/2, create ticket for SEV3, suppress SEV4 noise.
| Jev (TypeSafe API) | sevclassifier-jev-style-1.5b | |
|---|---|---|
| Typed output | yes | yes |
| Latency | ~115ms (network) | ~76ms (local, MPS) |
| Cost | per-request billing | free after download |
| Alert data leaves org | yes | no |
| Fine-tune on your runbook | no | yes (LoRA) |
| Accuracy (SevBench) | 93.6% F1 | 92.9% F1 |
| SEV1 recall (no missed majors) | 99.1% | 98.8% |
Incident alerts contain hostnames, IPs, service names, and error messages — the exact fingerprint of your infrastructure. Run the classifier on-prem.
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torch, json, re tok = AutoTokenizer.from_pretrained("enterprise-ai-lab/sevclassifier-jev-style-1.5b")model = AutoModelForCausalLM.from_pretrained( "enterprise-ai-lab/sevclassifier-jev-style-1.5b", dtype=torch.float32).eval() SYS = ( "You are an incident severity classification assistant. For each incident report output ONE " "JSON object with keys: severity (SEV1|SEV2|SEV3|SEV4), rationale (one sentence), " "escalate (boolean), page_oncall (boolean), affected_blast_radius (string). " "SEV1=critical outage/breach, SEV2=major impact, SEV3=minor/degraded, SEV4=informational/noise. " "Output only the JSON.") def classify_incident(title, details): content = f"Incident: {title}\n\nDetails: {details}" msgs = [{"role": "system", "content": SYS}, {"role": "user", "content": content}] 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=150, 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 = classify_incident( "Production database unreachable", "Primary RDS instance not responding. All pods returning 500. 12k users affected.")# {"severity": "SEV1", "rationale": "Full production outage.", "escalate": true, "page_oncall": true, "affected_blast_radius": "All production traffic"}Wire it as an OpenAI-compatible endpoint and drop it into your existing alert routing agent:
python
# Before (Jev):llm = ChatOpenAI(base_url="https://api.typesafe.ai/v1", api_key=JEV_KEY, model="jev-latest")# After (SevClassifier local):llm = ChatOpenAI(base_url="http://localhost:8000/v1", api_key="not-needed", model="sevclassifier-jev-style-1.5b")Routing pattern:
python
verdict = classify_incident(title, details)if verdict["severity"] in ("SEV1", "SEV2") and verdict["page_oncall"]: pagerduty.trigger(title, urgency="high")elif verdict["severity"] == "SEV3": jira.create_ticket(title, priority="medium")# SEV4: suppress, log onlyFine-tuned with LoRA (r=16, alpha=32) on a curated incident corpus:
| Model | Precision | Recall | F1 |
|---|---|---|---|
| sevclassifier-jev-style-1.5b | 93.3% | 92.5% | 92.9% |
| Jev (TypeSafe API) | 94.0% | 93.3% | 93.6% |
| GPT-4o-mini (zero-shot) | 87.4% | 86.8% | 87.1% |
| Rule-based (keyword) | 74.2% | 68.9% | 71.5% |
| Model | SEV1 Recall | False Escalation Rate |
|---|---|---|
| sevclassifier-jev-style-1.5b | 98.8% | 6.2% |
| Jev (TypeSafe API) | 99.1% | 5.9% |
| GPT-4o-mini (zero-shot) | 96.3% | 11.4% |
High SEV1 recall is the critical metric: a missed SEV1 is an undetected outage. False escalations are expensive but recoverable.
| Model | p50 | p95 | p99 |
|---|---|---|---|
| sevclassifier-jev-style-1.5b (local MPS) | 76ms | 108ms | 129ms |
| Jev (TypeSafe API, US-West) | 115ms | 198ms | 372ms |
Apache 2.0. Base model (Qwen2.5-1.5B-Instruct) is subject to its own Qwen license.
{ "severity": "SEV1 | SEV2 | SEV3 | SEV4", "rationale": "<one sentence>", "escalate": true, "page_oncall": false, "affected_blast_radius": "<scope description>"}from transformers import AutoModelForCausalLM, AutoTokenizerimport torch, json, re tok = AutoTokenizer.from_pretrained("enterprise-ai-lab/sevclassifier-jev-style-1.5b")model = AutoModelForCausalLM.from_pretrained( "enterprise-ai-lab/sevclassifier-jev-style-1.5b", dtype=torch.float32).eval() SYS = ( "You are an incident severity classification assistant. For each incident report output ONE " "JSON object with keys: severity (SEV1|SEV2|SEV3|SEV4), rationale (one sentence), " "escalate (boolean), page_oncall (boolean), affected_blast_radius (string). " "SEV1=critical outage/breach, SEV2=major impact, SEV3=minor/degraded, SEV4=informational/noise. " "Output only the JSON.") def classify_incident(title, details): content = f"Incident: {title}\n\nDetails: {details}" msgs = [{"role": "system", "content": SYS}, {"role": "user", "content": content}] 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=150, 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 = classify_incident( "Production database unreachable", "Primary RDS instance not responding. All pods returning 500. 12k users affected.")# {"severity": "SEV1", "rationale": "Full production outage.", "escalate": true, "page_oncall": true, "affected_blast_radius": "All production traffic"}# Before (Jev):llm = ChatOpenAI(base_url="https://api.typesafe.ai/v1", api_key=JEV_KEY, model="jev-latest")# After (SevClassifier local):llm = ChatOpenAI(base_url="http://localhost:8000/v1", api_key="not-needed", model="sevclassifier-jev-style-1.5b")verdict = classify_incident(title, details)if verdict["severity"] in ("SEV1", "SEV2") and verdict["page_oncall"]: pagerduty.trigger(title, urgency="high")elif verdict["severity"] == "SEV3": jira.create_ticket(title, priority="medium")# SEV4: suppress, log only