GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Sakeador
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Sakeador
Model Tree
Input Modalities
Output Modalities
Supported Functionality
| Property | Value |
|---|---|
| Base model | google/gemma-4-12b-it |
| Architecture | Decoder-only, encoder-free multimodal |
| Parameters | 12B |
| Context window | 256K tokens |
| Modalities | Text, Image, Audio, Video |
| Adapter | LoRA (r=32, alpha=64) |
| Precision | BF16 |
| License | Apache 2.0 |
| Dataset | Samples | Focus |
|---|---|---|
| reloading0101/threat-intelligence-dataset | 52,279 | CTI, APTs, IOCs, campaigns |
| sarahwei/cyber_MITRE_tactic_CTI_dataset_v16 | 14,008 | MITRE ATT&CK v16 |
| CJJones/Synthetic_PenTest_Reports | 752 | Pentest reports |
| Total | 67,039 |
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelimport torch base_model = "google/gemma-4-12b-it"adapter = "Sakeador/ThreatSage-12B" tokenizer = AutoTokenizer.from_pretrained(base_model)model = AutoModelForCausalLM.from_pretrained( base_model, torch_dtype=torch.bfloat16, device_map="auto")model = PeftModel.from_pretrained(model, adapter) messages = [ {"role": "user", "content": "Analyze this Wazuh alert and identify the MITRE ATT&CK technique."}] text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer([text], return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512)print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))| Setup | VRAM | Quantization |
|---|---|---|
| Minimum | 8 GB | Q4 |
| Recommended | 16 GB | BF16 (native) |
| Optimal | 3× 16 GB | BF16 tensor-parallel |
Apache 2.0 — same as the base model Gemma 4 12B.
Thanks to the open-source community, Google DeepMind for Gemma 4, and all the dataset creators who made this possible.
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelimport torch base_model = "google/gemma-4-12b-it"adapter = "Sakeador/ThreatSage-12B" tokenizer = AutoTokenizer.from_pretrained(base_model)model = AutoModelForCausalLM.from_pretrained( base_model, torch_dtype=torch.bfloat16, device_map="auto")model = PeftModel.from_pretrained(model, adapter) messages = [ {"role": "user", "content": "Analyze this Wazuh alert and identify the MITRE ATT&CK technique."}] text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer([text], return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512)print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))