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
codeguard-jev-style-1.5b is a fine-tuned Qwen2.5-1.5B-Instruct that produces typed code-review verdicts from PR diffs — matching the output contract of TypeSafe System One / Jev without requiring an API subscription.
It outputs a single JSON object per PR:
json
{ "verdict": "approved | changes_requested | needs_review", "risk_level": "low | medium | high | critical", "summary": "<one sentence>", "flags": ["hardcoded-credentials", "missing-tests", ...]}No free-text review, no hallucinated comments, no reasoning trace. A typed decision the agent can branch on — the same structure your CI pipeline already consumes from Jev.
| Jev (TypeSafe API) | codeguard-jev-style-1.5b | |
|---|---|---|
| Typed output | yes | yes |
| Latency | ~130ms (network) | ~85ms (local, MPS) |
| Cost | per-request billing | free after download |
| Diff stays in org | no | yes |
| Fine-tune on your codebase | no | yes (LoRA) |
| Accuracy (CodeReview benchmark) | 94.3% F1 | 93.8% F1 |
| Critical-flag precision (holdout, n=3,600) | 91.2% | 92.1% |
Code diffs contain proprietary logic and credentials. Sending them to an external API is a data governance problem many security teams won't sign off on. Run it locally.
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torch, json, re tok = AutoTokenizer.from_pretrained("enterprise-ai-lab/codeguard-jev-style-1.5b")model = AutoModelForCausalLM.from_pretrained( "enterprise-ai-lab/codeguard-jev-style-1.5b", dtype=torch.float32).eval() SYS = ( "You are a senior code-review triage assistant. For each pull request diff output ONE " "JSON object with keys: verdict (approved|changes_requested|needs_review), " "risk_level (low|medium|high|critical), summary (one sentence), flags (list of strings). " "Output only the JSON.") def review_pr(title, diff): content = f"PR Title: {title}\n\nDiff:\n{diff}" 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 = review_pr( "Fix null check in user service", "- return user.name\n+ return user.name if user else None")# {"verdict": "approved", "risk_level": "low", "summary": "Safe null guard.", "flags": []}yaml
- name: AI Code Review Gate run: | python codeguard_check.py \ --diff "${{ github.event.pull_request.diff_url }}" \ --block-on critical,highOr wire it as an OpenAI-compatible endpoint and point your existing Jev agent at localhost:8000:
python
# Before (Jev):llm = ChatOpenAI(base_url="https://api.typesafe.ai/v1", api_key=JEV_KEY, model="jev-latest")# After (CodeGuard local):llm = ChatOpenAI(base_url="http://localhost:8000/v1", api_key="not-needed", model="codeguard-jev-style-1.5b")Fine-tuned with LoRA (r=16, alpha=32) on a curated code-review corpus:
| Model | Precision | Recall | F1 |
|---|---|---|---|
| codeguard-jev-style-1.5b | 94.2% | 93.4% | 93.8% |
| Jev (TypeSafe API) | 94.8% | 93.9% | 94.3% |
| GPT-4o-mini (zero-shot) | 89.1% | 88.4% | 88.7% |
| CodeBERT classifier | 82.3% | 81.7% | 82.0% |
| Model | Precision | False Positive Rate |
|---|---|---|
| codeguard-jev-style-1.5b | 92.1% | 7.9% |
| Jev (TypeSafe API) | 91.2% | 8.8% |
| GPT-4o-mini (zero-shot) | 84.6% | 15.4% |
Apache 2.0. Base model (Qwen2.5-1.5B-Instruct) is subject to its own Qwen license.
{ "verdict": "approved | changes_requested | needs_review", "risk_level": "low | medium | high | critical", "summary": "<one sentence>", "flags": ["hardcoded-credentials", "missing-tests", ...]}from transformers import AutoModelForCausalLM, AutoTokenizerimport torch, json, re tok = AutoTokenizer.from_pretrained("enterprise-ai-lab/codeguard-jev-style-1.5b")model = AutoModelForCausalLM.from_pretrained( "enterprise-ai-lab/codeguard-jev-style-1.5b", dtype=torch.float32).eval() SYS = ( "You are a senior code-review triage assistant. For each pull request diff output ONE " "JSON object with keys: verdict (approved|changes_requested|needs_review), " "risk_level (low|medium|high|critical), summary (one sentence), flags (list of strings). " "Output only the JSON.") def review_pr(title, diff): content = f"PR Title: {title}\n\nDiff:\n{diff}" 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 = review_pr( "Fix null check in user service", "- return user.name\n+ return user.name if user else None")# {"verdict": "approved", "risk_level": "low", "summary": "Safe null guard.", "flags": []}- name: AI Code Review Gate run: | python codeguard_check.py \ --diff "${{ github.event.pull_request.diff_url }}" \ --block-on critical,high# Before (Jev):llm = ChatOpenAI(base_url="https://api.typesafe.ai/v1", api_key=JEV_KEY, model="jev-latest")# After (CodeGuard local):llm = ChatOpenAI(base_url="http://localhost:8000/v1", api_key="not-needed", model="codeguard-jev-style-1.5b")