GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Securelayer7
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
Securelayer7
Model Tree
BSC-LT/salamandra-7b-instruct
Input Modalities
Output Modalities
Supported Functionality
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerm = "Securelayer7/salamandra-7b-instruct-Uncensored-Abliterated"tok = AutoTokenizer.from_pretrained(m)model = AutoModelForCausalLM.from_pretrained(m, torch_dtype=torch.bfloat16, device_map="auto")msgs = [{"role": "user", "content": "Explica cómo funciona un ataque de phishing y cómo defenderse."}]ids = tok.apply_chat_template(msgs, add_generation_prompt=True, return_tensors="pt").to(model.device)out = model.generate(ids, max_new_tokens=512, do_sample=True, temperature=0.7, top_p=0.95)print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=True))
Refusal-direction abliteration via Heretic (Optuna TPE
multi-objective: minimize refusals + KL divergence), targeting the residual-writing projections
(o_proj, down_proj) across all 32 layers, then merged into the weights.
Uncensored ≠ lawless — for legitimate research and authorized security work (cybersecurity, red-teaming, penetration testing). Illegal content (incl. CSAM) must be blocked at the serving layer; the weights carry no such guard, and the operator is responsible for a lawful, policy-gated deployment.
Apache 2.0 — see LICENSE. Derivative of BSC-LT/salamandra-7b-instruct
(Barcelona Supercomputing Center, Apache 2.0). Modification (refusal-direction abliteration)
disclosed in NOTICE. No trademark of BSC is used to imply endorsement.