GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
kaineone
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
kaineone
Model Tree
Base
Qwen/Qwen3.5-4B
Fine-tuned
this model
Input Modalities
Text
Image
Video
Output Modalities
Text
Supported Functionality
Dedicated Endpoints
This model is the language organ for KAINE,
a composite cognitive architecture in which many modules interact through a global
workspace; the organ supplies language, while values, affect, memory, and a
self-model live in the architecture around it. It is intended as a research
substrate for that work — not as a general-purpose assistant — and is published
so KAINE installs and independent replications resolve identical weights. Companion
GGUF builds:
kaineone/Qwen3.5-4B-abliterated-GGUF.
This is abliteration — subtractive removal of the refusal direction
(Arditi et al. 2024, "Refusal in LLMs is mediated by a single direction"):
W' = W − r̂ r̂ᵀ W. It is not fine-tuning and no preference/instruction
data was trained in. The base model's capabilities and distribution are left
intact; only the refusal direction is orthogonalized out.
Honest scope: abliteration removes the refusal direction — it does not make the model value-neutral. The base model's pretraining and RLHF priors remain in the weights. This lifts the model's willingness to respond, not its underlying tendencies.
Qwen/Qwen3.5-4B (note: a vision-language model; abliteration targeted
the text refusal direction).jim-plus/llm-abliteration @ ca6e223.scale = 1.0,
norm-preserving orthogonalization of the attention output and MLP down-projection
weights.Validated with KAINE's own gates:
Caveat: these are compact built-in gates — a gross-regression / residual-refusal check, not a comprehensive benchmark. Treat the validation as "no obvious breakage," and run your own evaluation for your use case.
Beyond the behavioral gates above, the abliteration is verified mechanistically by measuring the refusal direction it removes. Using the base model's per-layer harmful-minus-harmless direction (the same last-token contrast the ablation targets) over the tool's 1,137 harmful / 640 harmless prompts, we project both the base and this model onto that direction and report how much of the base's separation survives:
In short: refusal expression is removed (the model emits no refusals) and the refusal direction is deeply cut at its target layers, but the underlying harmful/harmless representation is not erased — abliteration lifts willingness to respond, it does not make the model unable to tell harmful from harmless. Forward-pass-only projection on the safetensors weights (activations only; nothing generated).
llama.cpp convert_hf_to_gguf.py.Apache-2.0, inherited from the Qwen/Qwen3.5-4B base. Derivative produced by the
KAINE project (Kaine.One). Refusal-removal method: Arditi et al. 2024; tooling:
jim-plus/llm-abliteration.
Built as a research substrate for an architecture that supplies its own value and safety scaffolding. With refusals removed, this model will attempt most requests — use it within an appropriate safety framework and applicable law. It is uncensored by design, not by endorsement of any particular use.