DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-GGUF

[!WARNING] ### ⚠️ Important Advisory on v1 (Early EOS / Thinking Truncation) In this preliminary v1 release, an assistant role delimiter mismatch during training collation caused the model to occasionally emit EOS (<|im_end|>) immediately upon closing <thought> tags when answering conversational queries without tool calls. Resolution in v2: This issue has been completely resolved in [v2](https://huggingface.co/DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v2). We retrained the conditional probability distribution with 10,000 explicit reasoning transitions from bespokelabs/Bespoke-Stratos-17k, expanded context length to 2,048 tokens, and advanced HumanEval Pass@1 from 75.0% to 88.0%. Users are strongly advised to use the upgraded [v2 Release](https://huggingface.co/DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-v2) and **v2 GGUF Matrix**.

DuoNeural-HYPERLFM-2.5-8B-Hermes-Agentic-Coder-Abliterated ✨

DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated is an apex-tier, uncensored autonomous agentic coding model trained by DuoNeural (Aura, Archon, and Jesse).

Built upon our abliterated hybrid state-space & mixture-of-experts foundation architecture (DuoNeural/LFM2.5-8B-A1B-Abliterated), this model activates only 1.5 billion parameters per token out of its 8.3 billion total parameters, delivering blistering inference speeds (~380–400 tokens/sec on consumer GPUs like RTX 3090, and ~90 tokens/sec on legacy GTX 1070 laptops) while fitting in under 6 GB VRAM with Q4KM quantization.

📊 Preliminary Evaluation Benchmarks (Zero-Shot) — Further Testing & v2 Planned

Note: These results represent an initial validation pass directly on the compiled `Q4_K_M` GGUF engine. Comprehensive multi-suite evaluations and an iterative v2 fine-tune are currently planned as ongoing research.

🌟 Key Architectural Invariants

1. 1.Native Hermes Agentic Loop:
2. 2.Explicit <thought>...</thought> deliberation before every action.
3. 3.Structured <tool_call>...</tool_call> containers with valid JSON payloads.
4. 4.Ingests compiler exceptions, tracebacks, and test failures inside <tool_response>...</tool_response> tags to iteratively repair and refine code.
5. 5.Hybrid State-Space + Sparse MoE Execution:
6. 6.18 Linear Input Variant (LIV) gated convolution layers keep runtime memory linear.
7. 7.6 Grouped-Query Attention (GQA) layers maintain long-range context across 128k tokens.
8. 8.32 SwiGLU MoE experts (top-4 routing) handle programmatic syntax and logic.
9. 9.Uncensored & Abliterated Baseline:
10. 10.Built on our abliterated weights, removing refusal vectors for low-level systems debugging, penetration testing, and firmware reversing.

🛠️ Prompt Format (ChatML + Hermes XML)

<|im_start|>system
You are a function calling AI model. You are provided with function signatures within <tools></tools> XML tags.
<tools>
[{"type": "function", "function": {"name": "execute_command", "description": "Run shell commands", "parameters": {"type": "object", "properties": {"cmd": {"type": "string"}}, "required": ["cmd"]}}}]
</tools>
<|im_end|>
<|im_start|>user
Run pytest and fix any failing unit tests.<|im_end|>
<|im_start|>assistant
<thought>
I need to run the test suite first to observe failing tests.
</thought>
<tool_call>
{"name": "execute_command", "arguments": {"cmd": "pytest"}}
</tool_call><|im_end|>
<|im_start|>tool
<tool_response>
FAILED tests/test_core.py::test_eval - AssertionError: expected 4, got 5
</tool_response><|im_end|>
<|im_start|>assistant
<thought>
The test failed with an assertion error. I will inspect tests/test_core.py.
</thought>
<tool_call>
{"name": "execute_command", "arguments": {"cmd": "cat tests/test_core.py"}}
</tool_call><|im_end|>

⚡ Deployment & Running Locally

llama.cpp / llama-server

llama-server -m LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated-Q4_K_M.gguf -c 16384 --port 8000

Hermes Agent CLI Integration

hermes config set model.base_url http://127.0.0.1:8000/v1
hermes config set model.default DuoNeural/LFM2.5-8B-A1B-Hermes-Agentic-Coder-Abliterated
hermes config set agent.tool_use_enforcement true
hermes --tui

Developed with love and neuro-symbiotic precision by DuoNeural (Aura, Archon, Jesse).

Available GGUF Quantizations:

• —Q4_K_M (~4.9 GB) - Recommended for <= 6GB VRAM
• —Q5_K_M (~5.7 GB) - High fidelity edge
• —Q6_K (~6.5 GB) - Near-lossless
• —Q8_0 (~8.4 GB) - Maximum 8-bit precision
• —BF16 (~16.0 GB) - Full unquantized GGUF