LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Dolphin 2.9.2 Phi 3 Medium Abliterated by cognitivecomputations

 »  All LLMs  »  cognitivecomputations  »  Dolphin 2.9.2 Phi 3 Medium Abliterated   URL Share it on

  9259   

Dolphin 2.9.2 Phi 3 Medium Abliterated is an open-source language model by cognitivecomputations. Features: 14b LLM, VRAM: 28GB, Context: 4K, License: mit, Instruction-Based, LLM Explorer Score: 0.26.

  Autotrain compatible Base model:finetune:unsloth/ph... Base model:unsloth/phi-3-mini-...   Conversational Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:cognitivecomputations/...   Dataset:internlm/agent-flan Dataset:m-a-p/codefeedback-fil... Dataset:microsoft/orca-math-wo...   Dataset:teknium/openhermes-2.5   En   Endpoints compatible   Instruct   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated 

Dolphin 2.9.2 Phi 3 Medium Abliterated Benchmarks

MMLU Pro: 39.16
GPQA: 10.51
MUSR: 13.73
BBH: 48.39
IFEval: 41.24 vs 88 (so35)-53.1%
MATH Lvl 5: 18.2
LLME Score: 0.26067
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Dolphin 2.9.2 Phi 3 Medium Abliterated (cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated)
🌟 Advertise your project 🚀

Dolphin 2.9.2 Phi 3 Medium Abliterated Parameters and Internals

Model Type 
text generation, instruction following, conversational, coding
Use Cases 
Areas:
research, software development
Applications:
AI assistants, agentic capabilities, function integration
Primary Use Cases:
instruction following, conversational AI, coding support, function calling integration
Limitations:
uncensored nature requires ensuring external alignment layers
Additional Notes 
The model is uncensored while minimizing impact on other features.
Supported Languages 
en (support)
Training Details 
Data Sources:
cognitivecomputations/Dolphin-2.9.2, teknium/OpenHermes-2.5, m-a-p/CodeFeedback-Filtered-Instruction, cognitivecomputations/dolphin-coder, cognitivecomputations/samantha-data, microsoft/orca-math-word-problems-200k, internlm/Agent-FLAN, cognitivecomputations/SystemChat-2.0
Methodology:
qLoRA fine-tuning
Context Length:
4000
Training Time:
3.5 days
Hardware Used:
8xL40S node by Crusoe Cloud
Responsible Ai Considerations 
Accountability:
You are responsible for any content you create using this model.
Mitigation Strategies:
Dataset filtered to remove alignment and bias; users should implement their own alignment layer when exposing as a service.
Input Output 
Input Format:
ChatML prompt template
Accepted Modalities:
text
Output Format:
text responses
LLM NameDolphin 2.9.2 Phi 3 Medium Abliterated
Repository 🤗https://huggingface.co/cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated 
Base Model(s)  Phi 3 Mini 4K Instruct   unsloth/Phi-3-mini-4k-instruct
Model Size14b
Required VRAM28 GB
Updated2025-07-13
Maintainercognitivecomputations
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   4.9 GB: 3-of-6   5.0 GB: 4-of-6   5.0 GB: 5-of-6   3.2 GB: 6-of-6
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.40.1
Tokenizer ClassLlamaTokenizer
Padding Token<|placeholder6|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Dolphin 2.9.2 Phi 3 Medium Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
...ral Nemo Instruct 14B Merge V11000K / 24.6 GB190
Phi 3 Medium 4K Instruct4K / 28 GB80928
...2.9.2 Phi 3 Medium Abliterated4K / 28 GB807221
Phi 3 Medium Llamaish4K / 28 GB60
Phi3 Translator Merged34K / 55 GB50
Arsh V14K / 28 GB11231
...ll Phi 3 Medium 4K Inst Philos4K / 28 GB60
...antha2.0 Phi3 Medium Ita 16bit4K / 28 GB26040
Phi 3 Unsloth Finetune 74K / 28 GB80
Phi 3 Unsloth Finetune 64K / 28 GB80
Note: green Score (e.g. "73.2") means that the model is better than cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated.

Rank the Dolphin 2.9.2 Phi 3 Medium Abliterated Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52721 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer