GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
sabari2005
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
sabari2005
Model Tree
sabari2005/cyberslm-33m-base
Input Modalities
Output Modalities
Supported Functionality
Decoder-only transformer (Llama-style, loadable with LlamaForCausalLM):
384 hidden / 12 layers / 6 heads / SwiGLU 1024 / RMSNorm / RoPE θ=10,000 /
4096 context / 32k SentencePiece vocab / tied embeddings.
Total: 33,531,264 parameters.
The model was finetuned with this template (built into tokenizer.chat_template):
markdown
<s>### User:{question}### Assistant:{answer}</s>
python
from transformers import AutoModelForCausalLM, AutoTokenizertok = AutoTokenizer.from_pretrained("sabari2005/cyberslm-33m-instruct")model = AutoModelForCausalLM.from_pretrained("sabari2005/cyberslm-33m-instruct")messages = [{"role": "user", "content": "Explain what a SQL injection attack is and how to prevent it."}]ids = tok.apply_chat_template(messages, add_generation_prompt=True,return_tensors="pt", add_special_tokens=False)out = model.generate(ids, max_new_tokens=256, do_sample=True,temperature=0.7, top_p=0.9, eos_token_id=3, pad_token_id=0)print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))
Note: the
<s>/</s>markers in the template are literal text (the SentencePiece vocab uses<bos>/<eos>pieces), matching exactly how the model was trained. Useapply_chat_templateand you don't need to think about it.
33M parameters: strong at short cybersecurity explanations and Q&A; not suited for long-horizon reasoning, code generation, or general assistant duties. May hallucinate specifics (CVE numbers, tool flags) — verify facts. English only.