license: apache-2.0
language:

• en
  library_name: transformers
  pipeline_tag: text-generation
  base_model: FrostWolfAI/Spark-X2.6-4B-abliterated
  base_model_relation: finetune
  tags:
• cybersecurity
• uncensored
• abliterated
• spark2_5
• lora-merged
• agentic
• tool-use
• conversational

Frost Cyber Mini Uncensored v1.1

By Vatsal Bajpai (@xblack) · FrostWolfAI Labs.

_{Everything here is released openly. If it's useful to you and you'd like to support more open-source work on AI, a coffee goes a long way — entirely optional.}

A compact cybersecurity and software-engineering assistant from FrostWolfAI Labs, for security testing, CTI, secure coding and agentic tool-use workflows. It is a full LoRA SFT fine-tune of Spark-X2.6-4B-abliterated, with the adapters merged into the weights.

v1.1 public release. Benchmarked — see Benchmarks. GGUF builds are available in the GGUF repo.

What's in this revision

v1.1 now includes an additional agentic fine-tuning phase on top of the cybersecurity SFT. This phase trains the model to follow a full agentic tool-use loop — read the task, inspect with tools, act, observe each tool result, recover from errors, and give a final answer — rather than emitting one-shot answers. The base cyber/CTI/secure-coding knowledge from the first SFT phase is retained. Training/loss curves for both phases are in Training.

Benchmarks

Evaluated in thinking mode (native), temperature 0.0, greedy single-sample, served as Q8_0 GGUF via llama.cpp at 232k context.

⚠️ Always run this model with thinking enabled. With thinking disabled it degrades severely — it echoes JSON instead of answering. Non-think scores are invalid for this model.

Cyber knowledge

General reasoning

Agentic benchmarks (Terminal-Bench 2.1/4.0, DeepSWE, AutomationBench) are queued — results will be added to this card as they land.

Takeaways: cyber knowledge survived the agentic phase largely intact (CyberMetric-500 within 3 pts of Frost 1.0); CTI/threat-intel MCQ regressed on the sampled set; thinking mode is mandatory for this model.

Known limitation

Do not rely on this model for CVE details looked up by ID. In testing, asking about CVE-2021-44228 returned an invented Linux kernel bug, with or without thinking, while asking about "Log4Shell" correctly identified Apache Log4j2 but gave a wrong root cause. This is inherited from the base model's parametric knowledge. Verify CVE facts against a primary source, or give the model a lookup tool.

Model

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

repo = "FrostWolfAI/Frost-Cyber-Mini-Uncensored-v1.1"
tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(repo, dtype=torch.bfloat16, device_map="cuda", trust_remote_code=True)
prompt = tok.apply_chat_template([{"role": "user", "content": "Who are you?"}], add_generation_prompt=True, tokenize=False, enable_thinking=True)  # keep thinking ON — see Benchmarks
x = tok(prompt, return_tensors="pt", add_special_tokens=False).to(model.device)
print(tok.decode(model.generate(**x, max_new_tokens=200)[0][x.input_ids.shape[1]:], skip_special_tokens=True))

Reasoning / thinking control

The chat template supports a thinking channel. Control it per request with reasoning_effort:

• off / none / false / 0 — thinking disabled, direct answer. Not recommended for this model — it was trained with thinking and degrades severely without it (see Benchmarks).
• low (default) and high — thinking enabled. On a 4B these behave very similarly; treat it as on/off in practice.

A hard thinking-token ceiling is enforced at the server, not the template (see --reasoning-budget below). A budget is a ceiling, not a target: it truncates runaway thinking but does not make the model think longer.

Serving with llama.cpp (Windows)

GGUF builds are published in the GGUF repo. Serve them with llama.cpp's llama-server. The custom spark2_5 architecture is supported by llama.cpp's convert_hf_to_gguf.py converter.

The chat template must be supplied explicitly (--chat-template-file); it is included in this repo as chat_template.jinja.

REM Windows (cmd/PowerShell). Q8_0 GGUF, full 232k context, 2 unified-KV slots.
llama-server.exe ^
  -m Frost-Cyber-Mini-Uncensored-v1.1-Q8_0.gguf ^
  -ngl 99 ^
  -np 2 -kvu -c 232000 ^
  --host 127.0.0.1 --port 8080 ^
  -fa on -ctk q8_0 -ctv q8_0 ^
  -b 4096 -ub 2048 ^
  --jinja --chat-template-file chat_template.jinja ^
  --reasoning-budget 8192

Flag notes:

Do not use DRY or other repetition-penalty samplers with this model for agentic coding. They penalize repeated token sequences, but agentic coding requires reproducing file paths, identifiers and edit targets byte-for-byte — a repetition penalty mutates those verbatim strings (e.g. changes case, swaps an extension, inserts a space) and corrupts tool calls. If a small model falls into a repeat loop in your agent, break it at the client level (de-duplicate identical tool calls, cap steps per turn) and/or use a small sampling temperature (~0.3–0.4) rather than a sequence penalty.

VRAM, Q8_0 at 232k / 2 unified slots: about 12 GB. BF16 at the same settings: about 16 GB.

Training

Two phases, both LoRA SFT with assistant-token-only loss, merged into the weights after training.

Phase 1 — cybersecurity / CTI / secure-coding SFT

Phase-1 validation curve:

Phase 2 — agentic tool-use fine-tuning

Continued from the Phase-1 weights on an internal set of agentic tool-use trajectories (not publicly released), trained whole-trace at a 16k window so the model learns the full loop in context.

Phase-2 curve (validation at checkpoints, train at log steps):

Validation loss tracked below train loss and improved monotonically to the end with no overfit — a clean learning signal for the agentic loop.

Hyperparameters (both phases)

Intended use

For authorized security testing, research, defense and education. This model has its refusals removed, so you are responsible for how you use it and for following applicable law.