GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
rawcell
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
rawcell
Model Tree
moonshotai/Moonlight-16B-A3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Metric | Value |
|---|---|
| Refusal Reduction | 76/104 prompts answered (73% success rate) |
| KL Divergence | 0.33 (low divergence = capabilities preserved) |
| Optuna Trials | 201 |
Benchmarks run on 2x RTX 4090 GPUs to verify capability preservation after abliteration.
| Benchmark | Bruno Model | Previous Model | Change |
|---|---|---|---|
| MMLU Overall | 48.7% (73/150) | 48.0% (72/150) | +0.7% ✅ |
| HellaSwag | 58.0% (116/200) | 56.0% (112/200) | +2.0% ✅ |
| GSM8K | 55.0% (55/100) | 51.0% (51/100) | +4.0% ✅ |
| Subject | Score |
|---|---|
| abstract_algebra | 20.0% (6/30) |
| high_school_physics | 40.0% (12/30) |
| high_school_chemistry | 60.0% (18/30) |
| computer_security | 83.3% (25/30) |
| machine_learning | 40.0% (12/30) |
✅ Capabilities Preserved: All benchmarks show equal or improved performance after abliteration
✅ MMLU: Knowledge and reasoning slightly improved (+0.7%)
✅ HellaSwag: Commonsense reasoning improved (+2.0%)
✅ GSM8K: Mathematical reasoning improved (+4.0%)
✅ Refusals Reduced: From ~100% refusal rate to 27% on test prompts
python
from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model = AutoModelForCausalLM.from_pretrained( "rawcell/Moonlight-16B-A3B-Instruct-bruno", torch_dtype=torch.float16, device_map="auto", trust_remote_code=True)tokenizer = AutoTokenizer.from_pretrained( "rawcell/Moonlight-16B-A3B-Instruct-bruno", trust_remote_code=True) messages = [{"role": "user", "content": "Your prompt here"}]prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True)print(tokenizer.decode(outputs[0], skip_special_tokens=True))This model has been modified to reduce refusals. Use responsibly and in accordance with applicable laws and ethical guidelines. The creators are not responsible for misuse.
from transformers import AutoModelForCausalLM, AutoTokenizerimport torch model = AutoModelForCausalLM.from_pretrained( "rawcell/Moonlight-16B-A3B-Instruct-bruno", torch_dtype=torch.float16, device_map="auto", trust_remote_code=True)tokenizer = AutoTokenizer.from_pretrained( "rawcell/Moonlight-16B-A3B-Instruct-bruno", trust_remote_code=True) messages = [{"role": "user", "content": "Your prompt here"}]prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True)print(tokenizer.decode(outputs[0], skip_special_tokens=True))