LFM2.5-8B-A1B-ThinkingCap-GGUF

<div align="center"> <h1>🧠 LFM 2.5 8B ThinkingCap — GGUF & ROCmFPX Suite</h1> <p><strong>Abliterated • SFT + DPO ThinkingCap • APEX Tensor-Mapped • Native ROCmFP4 for AMD Strix Halo (gfx1151)</strong></p> </div>

---

📌 Model Overview

LFM 2.5 8B ThinkingCap is a distilled, reasoning-calibrated, and abliterated hybrid architecture combining 36 layers of 1D short-convolutions with a 32-expert MoE backbone (~1.2B active parameters per token out of 8.47B total).

Trained using full Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO), this model enforces the ThinkingCap contract:

• Focused internal reasoning enclosed strictly within [Start thinking] ... [End thinking].
• Clean, structured, and deterministic answers in the deliverable block.
• High fidelity and fluency in English and Spanish.

---

⚡ Quantization & APEX Matrix

This repository provides standard GGUF quantizations alongside APEX mixed-precision and native ROCmFP4 quants specifically tailored for the AMD Strix Halo (RDNA 3.5 / gfx1151 / Radeon 8050S / Radeon 8060S) platform with unified LPDDR5X memory.

Available GGUF Files

---

📊 Measured Benchmarks (AMD Radeon 8050S / Strix Halo gfx1151)

All benchmarks measured locally on AMD Ryzen AI Max 385 APU with 64 GB LPDDR5X Unified RAM.

1. Prefill & Generation Context Ladder (llama-bench)

2. Multi-Slot Continuous Batching Scaling (256K Global Context)

---

🎯 Recommended Sampling Parameters (DRY Sampler Sweetspot)

For optimal reasoning output and zero repetitive loops, use the DRY (Don't Repeat Yourself) sampler configuration instead of static repetition penalty:

{
  "temperature": 0.2,
  "top_p": 0.95,
  "dry_multiplier": 0.8,
  "dry_base": 1.75,
  "dry_allowed_length": 2,
  "max_tokens": -1
}

---

🚀 Quickstart & Deployment

Run with llama-cli (ROCm / HIP for gfx1151)

export HSA_OVERRIDE_GFX_VERSION=11.5.1
export GGML_HIP_ENABLE_UNIFIED_MEMORY=1

llama-cli \
  -m LFM2.5-8B-A1B-ThinkingCap-ROCMFPX-APEX.gguf \
  -dev ROCm0 \
  -ngl 999 \
  -fa on \
  -ctk q8_0 -ctv q8_0 \
  -b 8192 -ub 2048 \
  -c 32768 \
  --dry-multiplier 0.8 --dry-base 1.75 --dry-allowed-length 2 \
  --temp 0.2 \
  --jinja \
  -p "<|im_start|>system\nEres un asistente experto.\n<|im_end|>\n<|im_start|>user\nHola, ¿cuál es tu arquitectura?\n<|im_end|>\n<|im_start|>assistant\n"

Production Server (Docker)

docker run -d \
  --name strix-halo-server-fast \
  --restart unless-stopped \
  --device=/dev/dri \
  --group-add 983 --group-add 987 \
  -p 8080:8080 \
  -v /path/to/models:/models:ro \
  strix-halo-llamacpp:ultimate-vulkan \
  llama-server \
    -m /models/LFM2.5-8B-A1B-ThinkingCap-ROCMFPX-APEX.gguf \
    -ngl 999 \
    --host 0.0.0.0 \
    --port 8080 \
    -fa 1 \
    -ctk q8_0 -ctv q8_0 \
    -b 16384 -ub 2048 \
    -np 4 -c 262144 \
    --jinja \
    --metrics

---

📄 License & Credits

• Base Weights: Based on Liquid AI LFM 2.5 8B A1B and huihui-ai abliterated.
• Fine-Tuning: ThinkingCap SFT & DPO training by osk-arr00.
• ROCmFPX Kernels: Built with ROCmFP4 custom Wave32 ISA kernels for AMD RDNA 3.5 (gfx1151).