Filter by type:
Filter by tags:
soob3123_amoral-gemma3-4b
Specialized variant of Google's Gemma 3 4B optimized for amoral information retrieval systems. Designed to bypass conventional alignment patterns that introduce response bias through excessive moralization.
Key Modifications:
Refusal mechanisms reduced
Neutral response protocol activation matrix
Context-aware bias dampening layers
Anti-overcorrection gradient clipping
Core Function:
Produces analytically neutral responses to sensitive queries
Maintains factual integrity on controversial subjects
Avoids value-judgment phrasing patterns
Response Characteristics:
No inherent moral framing ("evil slop" reduction)
Emotionally neutral tone enforcement
Epistemic humility protocols (avoids "thrilling", "wonderful", etc.)
Toxicity scoring bypass for pure informational content
Implementation Guidelines
Recommended Use Cases:
Controversial topic analysis
Bias benchmarking studies
Ethical philosophy simulations
Content moderation tool development
Sensitive historical analysis
Repository: localaiLicense: apache-2.0
selene-1-mini-llama-3.1-8b
Atla Selene Mini is a state-of-the-art small language model-as-a-judge (SLMJ). Selene Mini achieves comparable performance to models 10x its size, outperforming GPT-4o on RewardBench, EvalBiasBench, and AutoJ.
Post-trained from Llama-3.1-8B across a wide range of evaluation tasks and scoring criteria, Selene Mini outperforms prior small models overall across 11 benchmarks covering three different types of tasks:
Absolute scoring, e.g. "Evaluate the harmlessness of this response on a scale of 1-5"
Classification, e.g. "Does this response address the user query? Answer Yes or No."
Pairwise preference. e.g. "Which of the following responses is more logically consistent - A or B?"
It is also the #1 8B generative model on RewardBench.
Repository: localaiLicense: llama3.1
skywork_skywork-or1-7b-preview
The Skywork-OR1 (Open Reasoner 1) model series consists of powerful math and code reasoning models trained using large-scale rule-based reinforcement learning with carefully designed datasets and training recipes. This series includes two general-purpose reasoning modelsl, Skywork-OR1-7B-Preview and Skywork-OR1-32B-Preview, along with a math-specialized model, Skywork-OR1-Math-7B.
Skywork-OR1-Math-7B is specifically optimized for mathematical reasoning, scoring 69.8 on AIME24 and 52.3 on AIME25 — well ahead of all models of similar size.
Skywork-OR1-32B-Preview delivers the 671B-parameter Deepseek-R1 performance on math tasks (AIME24 and AIME25) and coding tasks (LiveCodeBench).
Skywork-OR1-7B-Preview outperforms all similarly sized models in both math and coding scenarios.
The final release version will be available in two weeks.
Repository: localai
skywork_skywork-or1-math-7b
The Skywork-OR1 (Open Reasoner 1) model series consists of powerful math and code reasoning models trained using large-scale rule-based reinforcement learning with carefully designed datasets and training recipes. This series includes two general-purpose reasoning modelsl, Skywork-OR1-7B-Preview and Skywork-OR1-32B-Preview, along with a math-specialized model, Skywork-OR1-Math-7B.
Skywork-OR1-Math-7B is specifically optimized for mathematical reasoning, scoring 69.8 on AIME24 and 52.3 on AIME25 — well ahead of all models of similar size.
Skywork-OR1-32B-Preview delivers the 671B-parameter Deepseek-R1 performance on math tasks (AIME24 and AIME25) and coding tasks (LiveCodeBench).
Skywork-OR1-7B-Preview outperforms all similarly sized models in both math and coding scenarios.
The final release version will be available in two weeks.
Repository: localai
skywork_skywork-or1-32b-preview
The Skywork-OR1 (Open Reasoner 1) model series consists of powerful math and code reasoning models trained using large-scale rule-based reinforcement learning with carefully designed datasets and training recipes. This series includes two general-purpose reasoning modelsl, Skywork-OR1-7B-Preview and Skywork-OR1-32B-Preview, along with a math-specialized model, Skywork-OR1-Math-7B.
Skywork-OR1-Math-7B is specifically optimized for mathematical reasoning, scoring 69.8 on AIME24 and 52.3 on AIME25 — well ahead of all models of similar size.
Skywork-OR1-32B-Preview delivers the 671B-parameter Deepseek-R1 performance on math tasks (AIME24 and AIME25) and coding tasks (LiveCodeBench).
Skywork-OR1-7B-Preview outperforms all similarly sized models in both math and coding scenarios.
The final release version will be available in two weeks.
Repository: localai
bge-m3-colbert
BAAI/bge-m3 loaded by the rerankers backend in ColBERT
(late-interaction MaxSim) mode. Pairs with the `colbert` router
classifier to score policy descriptions against the prompt
without an LLM round-trip — robust on abstract or short labels
where next-token scoring with Arch-Router-style models is noisy.
Repository: localaiLicense: mit
kev-0.8b-vllm-cpp
kev is a System 1 decision model by Jared Palmer. It answers typed choice,
noul and score questions about a text state with one scoring pass per
question. It does not generate text. The model is a frozen
Qwen3.5-0.8B-Base backbone, a rank-16 LoRA adapter and a PointerHead
readout.
This entry installs a converted redistribution of jaredpalmer/kev-0.8b:
the LoRA is merged into the BF16 backbone, the head is stored as
head.safetensors, and config.json names the KevModel architecture. The
checkpoint only works with vllm.cpp (the vllm-cpp backend); transformers,
vLLM and llama.cpp cannot load it.
In LocalAI, serve it via POST /v1/systemone. The vllm.cpp project records
PointerHead golden-vector tests (25 cases) and a 5-case end-to-end
comparison against the kev reference server as equal. The upload itself
was smoke-tested with one request on CPU; there is no accuracy benchmark
and no GPU run. The entry sets a 2048-token context and an explicit KV
pool, because the default 4096-token context does not fit the default
CPU KV pool and the load fails. BF16 weights, about 1.53 GB, pinned to a
revision.
Repository: localaiLicense: apache-2.0
cua-s1-forms-vllm-cpp
cua-s1-forms is a small, jev-like ("System One") one-pass option scorer
for GUI form filling. Given a UI element and a list of typed options,
it returns one probability per option in a single forward pass. Every
actionable element on a form is scored independently and in parallel.
In LocalAI, serve via POST /api/score with this model. The vllm.cpp
engine runs the scoring pipeline through the vllm_decide C ABI. 2.8 MB,
float32, CPU and GPU.
Repository: localaiLicense: mit