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

Internlm2 5 20B Chat Abliterated by byroneverson

 »  All LLMs  »  byroneverson  »  Internlm2 5 20B Chat Abliterated   URL Share it on

  9   

Internlm2 5 20B Chat Abliterated is an open-source language model by byroneverson. Features: 20b LLM, VRAM: 39.7GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.15.

  Abliterated Base model:finetune:internlm/i... Base model:internlm/internlm2 ...   Chat   Conversational   Custom code   En   Feature-extraction   Interlm   Internlm2   Internlm2 5   It   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/byroneverson/internlm2_5-20b-chat-abliterated 

Internlm2 5 20B Chat Abliterated Benchmarks

LLME Score: 0.15295
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Internlm2 5 20B Chat Abliterated (byroneverson/internlm2_5-20b-chat-abliterated)
🌟 Advertise your project 🚀

Internlm2 5 20B Chat Abliterated Parameters and Internals

Model Type 
text-generation
Additional Notes 
This model uses a new approach for 'abliterating' models using CPU only. Refusal direction vector is obtained using a quant model with llama.cpp, and .safetensors files are orthogonalized.
Supported Languages 
en (supported), zh (supported)
LLM NameInternlm2 5 20B Chat Abliterated
Repository 🤗https://huggingface.co/byroneverson/internlm2_5-20b-chat-abliterated 
Base Model(s)  Internlm2 5 20B Chat   internlm/internlm2_5-20b-chat
Model Size20b
Required VRAM39.7 GB
Updated2026-03-13
Maintainerbyroneverson
Model Typeinternlm2
Model Files  1.9 GB: 1-of-21   1.9 GB: 2-of-21   2.0 GB: 3-of-21   1.9 GB: 4-of-21   2.0 GB: 5-of-21   1.9 GB: 6-of-21   2.0 GB: 7-of-21   1.9 GB: 8-of-21   2.0 GB: 9-of-21   1.9 GB: 10-of-21   2.0 GB: 11-of-21   1.9 GB: 12-of-21   2.0 GB: 13-of-21   1.9 GB: 14-of-21   2.0 GB: 15-of-21   1.9 GB: 16-of-21   2.0 GB: 17-of-21   1.9 GB: 18-of-21   2.0 GB: 19-of-21   1.6 GB: 20-of-21   1.1 GB: 21-of-21   0.0 GB
Supported Languagesen zh
Model ArchitectureInternLM2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.41.0
Is Biased0
Tokenizer ClassInternLM2Tokenizer
Padding Token</s>
Vocabulary Size92544
Torch Data Typebfloat16

Best Alternatives to Internlm2 5 20B Chat Abliterated

Best Alternatives
Context / RAM
Downloads
Likes
Internlm2 5 20B256K / 39.7 GB8717
Internlm2 5 20B Chat32K / 39.7 GB59492
Internlm2 20B32K / 39.7 GB2221459
Internlm2 Chat 20B ExPO32K / 39.8 GB151001
Internlm2 Chat 20B32K / 39.7 GB2119687
Internlm2 Base 20B32K / 39.7 GB186508
ChemLLM 20B Chat DPO32K / 40.6 GB31110
Internlm Chatbode 20B32K / 39.8 GB71
ChemLLM 20B Chat SFT32K / 40.6 GB85
Internlm2 Chat 20B 4bits32K / 12.2 GB10937
Note: green Score (e.g. "73.2") means that the model is better than byroneverson/internlm2_5-20b-chat-abliterated.

Rank the Internlm2 5 20B Chat 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