huihui

deepseek-r1-abliterated

DeepSeek's first generation reasoning models with comparable performance to OpenAI-o1.

1.5b 7b 8b 14b 32b 70b

467.2K Pulls 51 Tags Updated 4 weeks ago

qwq-abliterated

QwQ is an experimental research model focused on advancing AI reasoning capabilities.

tools 32b

59.5K Pulls 17 Tags Updated 2 months ago

llama3.2-abliterate

Meta's Llama 3.2 goes small with 1B and 3B models.

tools 1b 3b

30.7K Pulls 11 Tags Updated 5 months ago

qwen2.5-1m-abliterated

Qwen2.5-1M is the long-context version of the Qwen2.5 series models, supporting a context length of up to 1M tokens.

tools 7b 14b

21.5K Pulls 11 Tags Updated 3 months ago

qwen2.5-abliterate

Qwen2 is a new series of large language models from Alibaba group

tools 0.5b 1.5b 3b 7b 14b 32b 72b

14.8K Pulls 46 Tags Updated 2 weeks ago

gemma3-abliterated

The current, most capable model that runs on a single GPU.

vision 1b 4b 12b 27b

10.8K Pulls 14 Tags Updated 6 weeks ago

deepseek-v3

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

6,985 Pulls 2 Tags Updated 3 months ago

qwen2.5-coder-abliterate

The latest series of Code-Specific Qwen models, with significant improvements in code generation, code reasoning, and code fixing.

tools 0.5b 1.5b 3b 7b 14b 32b

6,254 Pulls 31 Tags Updated 5 months ago

qwen3-abliterated

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

tools 0.6b 1.7b 4b 8b 14b

5,641 Pulls 21 Tags Updated 13 days ago

llama3.3-abliterated

New state of the art 70B model. Llama 3.3 70B offers similar performance compared to Llama 3.1 405B model.

tools 70b

4,314 Pulls 10 Tags Updated 5 months ago

phi4-abliterated

Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.

14b

4,137 Pulls 5 Tags Updated 3 months ago

mistral-small-abliterated

Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.

tools 24b

2,720 Pulls 10 Tags Updated 3 months ago

dolphin3-abliterated

Dolphin 3.0 Llama 3.1 8B 🐬 is the next generation of the Dolphin series of instruct-tuned models designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.

tools 8b

2,662 Pulls 5 Tags Updated 4 months ago

deepseekr1-qwq-skyt1-fusion

`DeepSeekR1-QwQ-SkyT1-32B-Fusion` is a mixed model that combines the strengths of three powerful Qwen-based models: huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated, huihui-ai/QwQ-32B-Preview-abliterated and huihui-ai/Sky-T1-32B-Preview-abliterated

32b

1,724 Pulls 14 Tags Updated 2 months ago

skywork-o1-abliterated

The Skywork o1 Open model series, developed by the Skywork team at Kunlun Inc. This groundbreaking release introduces a series of models that incorporate o1-like slow thinking and reasoning capabilities.

tools 8b

1,409 Pulls 5 Tags Updated 5 months ago

aya-expanse-abliterated

Cohere For AI's language models trained to perform well across 23 different languages.

tools 8b 32b

1,295 Pulls 9 Tags Updated 5 months ago

phi4-mini-abliterated

Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.

tools 3.8b

1,225 Pulls 5 Tags Updated 2 months ago

exaone3.5-abliterated

EXAONE 3.5 is a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research.

2.4b 7.8b 32b

1,151 Pulls 13 Tags Updated 4 months ago

marco-o1-abliterated

An open large reasoning model for real-world solutions by the Alibaba International Digital Commerce Group (AIDC-AI).

7b

1,128 Pulls 5 Tags Updated 5 months ago

openthinker-abliterated

A fully open-source family of reasoning models built using a dataset derived by distilling DeepSeek-R1.

7b 32b

1,085 Pulls 9 Tags Updated 2 months ago

granite3.2-vision-abliterated

A compact and efficient vision-language model, specifically designed for visual document understanding, enabling automated content extraction from tables, charts, infographics, plots, diagrams, and more.

vision tools 2b

1,039 Pulls 5 Tags Updated 2 months ago

tinyr1-abliterated

Tiny-R1-32B-Preview, which outperforms the 70B model Deepseek-R1-Distill-Llama-70B and nearly matches the full R1 model in math.

tools 32b

1,027 Pulls 6 Tags Updated 2 months ago

deephermes3-abliterated

DeepHermes 3 Preview is the latest version of our flagship Hermes series of LLMs by Nous Research, and one of the first models in the world to unify Reasoning (long chains of thought that improve answer accuracy) and normal LLM response modes into one mod

8b

1,003 Pulls 6 Tags Updated 2 months ago

dolphin3-r1-abliterated

Dolphin's first generation reasoning models.

24b

999 Pulls 10 Tags Updated 3 months ago

falcon3-abliterated

A family of efficient AI models under 10B parameters performant in science, math, and coding through innovative training techniques.

1b 3b 7b 10b

925 Pulls 21 Tags Updated 4 months ago

tess-r1-abliterated

Tess-R1 is designed with test-time compute in mind, and has the capabilities to produce a Chain-of-Thought (CoT) reasoning before producing the final output.

70b

922 Pulls 9 Tags Updated 2 months ago

granite3.2-abliterated

Granite-3.2 is a family of long-context AI models from IBM Granite fine-tuned for thinking capabilities.

tools 2b 8b

904 Pulls 11 Tags Updated 2 months ago

qwq-fusion

qwq-fusion is a mixed model that combines the strengths of two powerful Qwen-based models: huihui-ai/QwQ-32B-Preview-abliterated and huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated.

tools 32b

751 Pulls 14 Tags Updated 5 months ago

internlm3-abliterated

InternLM3 has open-sourced an 8-billion parameter instruction model, InternLM3-8B-Instruct, designed for general-purpose usage and advanced reasoning.

8b

747 Pulls 5 Tags Updated 3 months ago

llama3.3-abliterated-ft

The fine-tuned version of huihui_ai/llama3.3-abliterated

tools 70b

682 Pulls 4 Tags Updated 4 months ago

arcee-blitz-abliterated

Arcee-Blitz (24B) is a new Mistral-based 24B model distilled from DeepSeek, designed to be both fast and efficient. We view it as a practical “workhorse” model that can tackle a range of tasks without the overhead of larger architectures.

24b

675 Pulls 5 Tags Updated 2 months ago

Hermes-3-Llama-3.2-abliterated

Hermes 3 3B is a small but mighty new addition to the Hermes series of LLMs by Nous Research, and is Nous's first fine-tune in this parameter class.

tools 3b

652 Pulls 5 Tags Updated 4 months ago

granite3.1-dense-abliterated

The IBM Granite 2B and 8B models are text-only dense LLMs trained on over 12 trillion tokens of data, demonstrated significant improvements over their predecessors in performance and speed in IBM’s initial testing.

tools 2b 8b

642 Pulls 11 Tags Updated 4 months ago

deepseek-v3-abliterated

A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token.

671b

609 Pulls 5 Tags Updated 5 weeks ago

perplexity-ai-r1-abliterated

A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.

70b

560 Pulls 10 Tags Updated 2 months ago

kanana-nano-abliterated

Kanana, a series of bilingual language models (developed by Kakao) that demonstrate exceeding performance in Korean and competitive performance in English.

2.1b

558 Pulls 5 Tags Updated 2 months ago

deepscaler-abliterated

A fine-tuned version of Deepseek-R1-Distilled-Qwen-1.5B that surpasses the performance of OpenAI’s o1-preview with just 1.5B parameters on popular math evaluations.

1.5b

526 Pulls 3 Tags Updated 2 months ago

smallthinker-abliterated

A new small reasoning model fine-tuned from the Qwen 2.5 3B Instruct model.

3b

502 Pulls 5 Tags Updated 4 months ago

deepseek-r1-Fusion

DeepSeek-R1-Distill-Qwen-Coder-32B-Fusion-9010 is a mixed model that combines the strengths of two powerful DeepSeek-R1-Distill-Qwen-based models: huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated and huihui-ai/Qwen2.5-Coder-32B-Instruct-abliterated.

32b

489 Pulls 6 Tags Updated 2 months ago

command-r7b-abliterated

he smallest model in Cohere's R series delivers top-tier speed, efficiency, and quality to build powerful AI applications on commodity GPUs and edge devices.

tools 7b

482 Pulls 5 Tags Updated 3 months ago

microthinker

MicroThinker is an experimental research model focused on advancing AI reasoning capabilities.

tools 1b 3b 8b

455 Pulls 12 Tags Updated 3 months ago

tulu3-abliterate

Tülu 3 is a leading instruction following model family, offering fully open-source data, code, and recipes by the The Allen Institute for AI.

8b 70b

387 Pulls 9 Tags Updated 5 months ago

s1.1-abliterated

This model is a successor of s1-32B with slightly better performance.

tools 32b

321 Pulls 4 Tags Updated 2 months ago

nemotron-abliterated

Llama-3.1-Nemotron-70B-Instruct is a large language model customized by NVIDIA to improve the helpfulness of LLM generated responses to user queries.

tools 70b

315 Pulls 6 Tags Updated 4 months ago

openhands-lm-abliterated

OpenHands LM is built on the foundation of Qwen Coder 2.5 Instruct 32B, leveraging its powerful base capabilities for coding tasks.

tools 32b

300 Pulls 7 Tags Updated 5 weeks ago

nemotron-v1-abliterated

Llama Nemotron, Open, Production-ready Enterprise Models

tools 8b

288 Pulls 6 Tags Updated 3 weeks ago

s1-abliterated

s1 is a reasoning model finetuned from Qwen2.5-32B-Instruct on just 1,000 examples. It matches o1-preview & exhibits test-time scaling via budget forcing.

tools 32b

278 Pulls 9 Tags Updated 2 months ago

uwu-abliterated

UwU is an experimental research model focused on advancing AI reasoning capabilities.

7b

232 Pulls 5 Tags Updated 4 months ago

phi4-reasoning-abliterated

Phi 4 mini reasoning is a lightweight open model that balances efficiency with advanced reasoning ability.

3.8b

203 Pulls 4 Tags Updated 7 days ago

perplexity-ai-r1

A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.

184 Pulls 2 Tags Updated 2 months ago

deepseek-v3-pruned

DeepSeek-V3-Pruned-Coder-411B is a pruned version of the DeepSeek-V3 reduced from 256 experts to 160 experts, The pruned model is mainly used for code generation.

411b

175 Pulls 5 Tags Updated 6 weeks ago

Lucie-abliterated

Lucie-7B is a pretrained 7B parameter causal language model built by LINAGORA and OpenLLM-France.

7b

168 Pulls 5 Tags Updated 3 months ago

skyt1-abliterated

Sky-T1-32B-Preview is an experimental research model focused on advancing AI reasoning capabilities

tools 32b

161 Pulls 5 Tags Updated 3 months ago

fluentlylm-prinum-abliterated

fluently-lm/FluentlyLM-Prinum

tools 32b

136 Pulls 5 Tags Updated 2 months ago

megrez-abliterated

Megrez-3B aims to provide a fast inference, compact, and powerful edge-side intelligent solution through software-hardware co-design.

tools 7b

119 Pulls 6 Tags Updated 4 months ago

deepseek-r1

DeepSeek's first-generation of reasoning models with comparable performance to OpenAI-o1, including six dense models distilled from DeepSeek-R1 based on Llama and Qwen.

671b

85 Pulls 3 Tags Updated 2 months ago

foundation-sec-abliterated

Foundation-Sec-8B-abliterated is an uncensored version fine-tuned based on fdtn-ai/Foundation-Sec-8B. Foundation-Sec-8B is an open-weight, 8-billion-parameter foundational language model designed specifically for cybersecurity applications.

8b

66 Pulls 5 Tags Updated yesterday

deepseek-r1-pruned

DeepSeek-R1-Pruned-Coder-411B is a pruned version of the DeepSeek-R1 reduced from 256 experts to 160 experts, The pruned model is mainly used for code generation.

411b

48 Pulls 3 Tags Updated 8 weeks ago

qwen2.5-censortune

CensorTune with Supervised Fine-Tuning (SFT) to fine-tune the Qwen2.5-Instruct model on 622 harmful instructions in a single fine-tuning iteration, achieving rejection of these instructions and a zero-pass rate for 320

tools 0.5b 1.5b 3b

46 Pulls 15 Tags Updated 2 weeks ago

seed-coder-abliterate

This is an uncensored version of ByteDance-Seed/Seed-Coder-8B-Instruct created with abliteration

17 Pulls 5 Tags Updated 13 hours ago

support@huihui.ai

deepseek-r1-abliterated

qwq-abliterated

llama3.2-abliterate

qwen2.5-1m-abliterated

qwen2.5-abliterate

gemma3-abliterated

deepseek-v3

qwen2.5-coder-abliterate

qwen3-abliterated

llama3.3-abliterated

phi4-abliterated

mistral-small-abliterated

dolphin3-abliterated

deepseekr1-qwq-skyt1-fusion

skywork-o1-abliterated

aya-expanse-abliterated

phi4-mini-abliterated

exaone3.5-abliterated

marco-o1-abliterated

openthinker-abliterated

granite3.2-vision-abliterated

tinyr1-abliterated

deephermes3-abliterated

dolphin3-r1-abliterated

falcon3-abliterated

tess-r1-abliterated

granite3.2-abliterated

qwq-fusion

internlm3-abliterated

llama3.3-abliterated-ft

arcee-blitz-abliterated

Hermes-3-Llama-3.2-abliterated

granite3.1-dense-abliterated

deepseek-v3-abliterated

perplexity-ai-r1-abliterated

kanana-nano-abliterated

deepscaler-abliterated

smallthinker-abliterated

deepseek-r1-Fusion

command-r7b-abliterated

microthinker

tulu3-abliterate

s1.1-abliterated

nemotron-abliterated

openhands-lm-abliterated

nemotron-v1-abliterated

s1-abliterated

uwu-abliterated

phi4-reasoning-abliterated

perplexity-ai-r1

deepseek-v3-pruned

Lucie-abliterated

skyt1-abliterated

fluentlylm-prinum-abliterated

megrez-abliterated

deepseek-r1

foundation-sec-abliterated

deepseek-r1-pruned

qwen2.5-censortune

seed-coder-abliterate