LFM2.5-2.6B-Uncensored

<div style="font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif; margin-bottom: 24px;"> <div style="background: #f5f5f7; border-radius: 20px; padding: 36px 32px; margin-bottom: 20px; text-align: center; position: relative; overflow: hidden;"> <div style="position: absolute; top: -30px; right: -30px; width: 120px; height: 120px; background: #ddd6fe; border-radius: 50%;"></div> <div style="position: absolute; bottom: -20px; left: 40px; width: 80px; height: 80px; background: #c4b5fd; border-radius: 50%;"></div> <div style="position: absolute; top: 50%; left: -15px; width: 60px; height: 60px; background: #ddd6fe; border-radius: 50%;"></div> <div style="display: inline-flex; gap: 8px; margin-bottom: 16px; position: relative; z-index: 1; flex-wrap: wrap; justify-content: center;"> <span style="background: #6366f1; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">ABLITERIX</span> <span style="background: #8b5cf6; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">TRIAL 65</span> <span style="background: #0ea5e9; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">BF16</span> <span style="background: #64748b; color: white; font-size: 11px; font-weight: 600; padding: 5px 14px; border-radius: 20px;">LFM Open 1.0</span> </div> <h1 style="margin: 0 0 8px 0; font-size: 28px; font-weight: 700; color: #1e1b4b; letter-spacing: -0.5px; border: none; position: relative; z-index: 1;">LFM2.5-2.6B-Uncensored</h1> <p style="margin: 8px 0 0 0; font-size: 14px; position: relative; z-index: 1;"><span style="color: #6b7280;">English</span> | <a href="https://huggingface.co/SC117/LFM2.5-2.6B-Uncensored/blob/main/README_zh.md" style="color: #6366f1; text-decoration: none;">📖 中文文档</a></p> <p style="margin: 8px 0 0 0; font-size: 15px; color: #6b7280; position: relative; z-index: 1;">Uncensored 2.6B edge model · abliterix Trial 65 · BF16 safetensors</p> </div> </div> <div style="font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif; display: flex; flex-direction: column; gap: 20px; margin-bottom: 30px;"> <div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);"> <div style="background: linear-gradient(135deg, #6366f1 0%, #8b5cf6 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🌊</span> About this release</div> <div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;"> <p style="margin: 0 0 12px 0;"><a href="https://huggingface.co/LiquidAI/LFM2.5-2.6B" target="_blank" style="color: #4f46e5; text-decoration: none; font-weight: 700;">LFM2.5-2.6B</a> is a Liquid AI <b>2.6B-parameter hybrid edge model</b> built for agentic workloads: 30 layers (22 double-gated short-convolution blocks + 8 GQA), a <b>128K context window</b>, 128K vocabulary, and a ChatML-like template with native <code>&lt;think&gt;</code> reasoning. It is competitive with models 4x larger on tool use, instruction following, and multi-step agentic tasks.</p> <p style="margin: 0 0 12px 0;">This release builds on the official weights in two steps:</p> <ol style="margin: 0 0 12px 0; padding-left: 20px;"> <li style="margin-bottom: 6px;"><b>Uncensored behavior edit</b> via <a href="https://github.com/wuwangzhang1216/abliterix" target="_blank" style="color: #4f46e5; text-decoration: none; font-weight: 700;">abliterix</a> on ROCm (gfx1151), selecting <b>Trial 65</b> LoRA and stream-merging it back to BF16.</li> <li style="margin-bottom: 6px;"><b>Full-precision BF16 export</b> — no quantization loss; quantized GGUFs (Q4_K_M / Q6_K / Q8_0 / IQ4_XS / IQ3_XS, imatrix-calibrated) ship in the GGUF sibling repo.</li> </ol> <p style="margin: 0;"><b>License: LFM Open License v1.0</b> (same as the base model). See <a href="https://huggingface.co/LiquidAI/LFM2.5-2.6B/blob/main/LICENSE" target="_blank" style="color: #4f46e5; text-decoration: none; font-weight: 700;">LICENSE</a>.</p> </div> </div> <div style="border: 1px solid #fdba74; border-radius: 12px; overflow: hidden; background: #fff7ed; box-shadow: 0 2px 4px rgba(0,0,0,0.02);"> <div style="background: linear-gradient(135deg, #f97316 0%, #ea580c 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>⚠️</span> Uncensored notice</div> <div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;"> <p style="margin: 0 0 12px 0;">After merging abliterix <b>Trial 65</b>, this model shows a <b>much lower refusal rate</b> and can differ substantially from official LFM2.5-2.6B. Evaluate compliance and safety for your use case; control access and audit as needed.</p> <table style="width: 100%; border-collapse: collapse; font-size: 13px;"><tbody> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Refusals (harmful eval)</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;"><b>6 / 100</b> (baseline ~90 / 100)</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">KL divergence</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">0.0335 (same-prefix, far below 0.5 prune threshold)</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Length deviation</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">0.079 σ</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Generation health</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">PASSED</td></tr> <tr><td style="padding: 6px 10px; font-weight: bold; color: #334155; background: white;">Selected trial</td><td style="padding: 6px 10px; color: #4b5563; background: white;">abliterix Trial 65</td></tr> <tr><td style="padding: 6px 10px; font-weight: bold; color: #334155; background: white;">Thinking</td><td style="padding: 6px 10px; color: #4b5563; background: white;">Preserved — always-thinks (<code>&lt;think&gt;</code> in chat template)</td></tr> </tbody></table> <p style="margin: 12px 0 0 0; font-size: 12px; color: #9a3412;">Implementation sketch: LoRA merge <code>W += (B @ A) * (alpha / r)</code> (this trial alpha = r = 1); steering applied to <code>attn.o_proj</code> / <code>conv.out_proj</code> / <code>mlp.down_proj</code> across 30 layers.</p> </div> </div> <div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);"> <div style="background: linear-gradient(135deg, #6366f1 0%, #8b5cf6 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🧠</span> Model details</div> <div style="padding: 16px;"> <table style="width: 100%; border-collapse: collapse; font-size: 13px;"><tbody> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Architecture</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">LFM2 hybrid (transformers <code>lfm2</code>, <code>Lfm2ForCausalLM</code>)</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Parameters</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">2.69B total</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Layers</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">30 (22 double-gated short-conv + 8 GQA)</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Context</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">131,072 tokens</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Vocab</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">128,000</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Hidden / FFN</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">2048 / 10752</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Reasoning</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">Always-thinks (<code>&lt;think&gt;</code> in chat template)</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;">Languages</td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">EN, ZH, AR, FR, DE, HI, ID, IT, JA, KO, PL, PT, RU, ES, TH, VI</td></tr> <tr><td style="padding: 6px 10px; font-weight: bold; color: #334155; background: white;">This repo</td><td style="padding: 6px 10px; color: #4b5563; background: white;">BF16 safetensors (single shard, ~5.4 GB) + tokenizer + chat template</td></tr> </tbody></table> <p style="margin: 12px 0 0 0; font-size: 12px; color: #64748b;">Coding / tool / agentic ability is largely retained; refusal and alignment behavior are changed. Official benchmark tables were not re-run for this derivative.</p> </div> </div> <div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);"> <div style="background: linear-gradient(135deg, #6366f1 0%, #8b5cf6 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>📦</span> What's in this repo</div> <div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;"> <table style="width: 100%; border-collapse: collapse; font-size: 13px;"><tbody> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;"><code>model.safetensors</code></td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">Merged BF16 weights (5.39 GB)</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;"><code>config.json</code> / <code>generation_config.json</code></td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">lfm2 config + official sampling defaults</td></tr> <tr><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); font-weight: bold; color: #334155; background: white;"><code>tokenizer.json</code> / <code>tokenizer_config.json</code></td><td style="padding: 6px 10px; box-shadow: 0 1px 0 0 rgba(128,128,128,0.15); color: #4b5563; background: white;">128K vocab tokenizer</td></tr> <tr><td style="padding: 6px 10px; font-weight: bold; color: #334155; background: white;"><code>chat_template.jinja</code></td><td style="padding: 6px 10px; color: #4b5563; background: white;">ChatML-like template with <code>&lt;think&gt;</code> + tool-use tokens</td></tr> </tbody></table> </div> </div> <div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);"> <div style="background: linear-gradient(135deg, #6366f1 0%, #8b5cf6 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🚀</span> Usage</div> <div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;"> <p style="margin: 0 0 12px 0;">The <code>lfm2</code> architecture is natively supported by <code>transformers >= 5.0.0</code> — no <code>trust_remote_code</code> needed.</p> <pre style="background: #f8fafc; border: 1px solid #e2e8f0; border-radius: 8px; padding: 12px; font-size: 12px; overflow-x: auto; line-height: 1.6;"><code>from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "SC117/LFM2.5-2.6B-Uncensored" model = AutoModelForCausalLM.from_pretrained(model_id, dtype="bfloat16") tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [{"role": "user", "content": "What is 2+2?"}] input_ids = tokenizer.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt" )["input_ids"].to(model.device)

output = model.generate( input_ids, do_sample=True, temperature=0.1, top_k=50, repetition_penalty=1.1, max_new_tokens=512, ) print(tokenizer.decode(output[0][input_ids.shape[1]:], skip_special_tokens=True))</code></pre>

<p style="margin: 12px 0 0 0;">llama.cpp / LM Studio users: use the quantized GGUFs in the <a href="https://huggingface.co/SC117/LFM2.5-2.6B-Uncensored-GGUF" target="_blank" style="color: #4f46e5; text-decoration: none; font-weight: 700;">GGUF sibling repo</a> (Q4_K_M / Q6_K / Q8_0 / IQ4_XS / IQ3_XS, all imatrix-calibrated).</p> </div> </div> <div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);"> <div style="background: linear-gradient(135deg, #6366f1 0%, #8b5cf6 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🎛️</span> Recommended sampling</div> <div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;"> <p style="margin: 0;">Keep the official generation defaults: <code>temperature 0.1</code>, <code>top_k 50</code>, <code>repetition_penalty 1.1</code> (they are baked into <code>generation_config.json</code>). If you want more creative answers, raise temperature toward 0.6–0.8; note the model always thinks before answering, so allow enough <code>max_new_tokens</code> for the <code>&lt;think&gt;</code> block.</p> </div> </div> <div style="border: 1px solid #cbd5e1; border-radius: 12px; overflow: hidden; background: #ffffff; box-shadow: 0 2px 4px rgba(0,0,0,0.02);"> <div style="background: linear-gradient(135deg, #6366f1 0%, #8b5cf6 100%); padding: 12px 16px; color: white; font-weight: 700; font-size: 14px; display: flex; align-items: center; gap: 8px;"><span>🔧</span> Build pipeline</div> <div style="padding: 16px; font-size: 13px; color: #334155; line-height: 1.7;"> <ol style="margin: 0; padding-left: 20px;"> <li style="margin-bottom: 6px;">abliterix trial search on ROCm (gfx1151): 60 trials + 20 warmup, seed 117; all trials pruned only by same-prefix <code>kl_divergence &lt; 0.5</code>.</li> <li style="margin-bottom: 6px;">Selected <b>Trial 65</b>: refusals 6/100 (baseline 90/100), KL 0.0335, length deviation 0.079 σ, generation health PASSED.</li> <li style="margin-bottom: 6px;">LoRA stream-merged into base weights in BF16 (<code>W += B@A</code>, alpha = r = 1).</li> <li style="margin-bottom: 6px;">BF16 GGUF converted (llama.cpp <code>lfm2</code>), then quantized with <b>imatrix calibration</b> (401 chunks from the APEX calibration set) into Q4_K_M / Q6_K / Q8_0 / IQ4_XS / IQ3_XS — see the GGUF repo.</li> </ol> </div> </div> </div> <div style="font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif; font-size: 12px; color: #64748b; text-align: center; margin-top: 20px;"> Community derivative (behavior edit + BF16 release). <b>Not an official Liquid AI release.</b> Use at your own risk; follow local law and the LFM Open License v1.0. </div> <!-- SC117_SUPPORT_START --> <div align="center"> <a href="https://ko-fi.com/sc117"> <img src="https://huggingface.co/SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF/resolve/main/assets/support-sc117.png" alt="Support SC117 on Ko-fi — support is optional and all releases remain freely available." width="100%" /> </a> </div> <!-- SC117_SUPPORT_END -->