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

Llama 3 120B Instruct Abliterated Merged by imi2

 »  All LLMs  »  imi2  »  Llama 3 120B Instruct Abliterated Merged   URL Share it on

  17   
  Merged Model   Autotrain compatible   Conversational   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/imi2/llama-3-120B-Instruct-abliterated-merged 

Llama 3 120B Instruct Abliterated Merged Benchmarks

LLME Score: 0.15047
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 120B Instruct Abliterated Merged (imi2/llama-3-120B-Instruct-abliterated-merged)
🌟 Advertise your project 🚀

Llama 3 120B Instruct Abliterated Merged Parameters and Internals

LLM NameLlama 3 120B Instruct Abliterated Merged
Repository 🤗https://huggingface.co/imi2/llama-3-120B-Instruct-abliterated-merged 
Merged ModelYes
Model Size120b
Required VRAM243.7 GB
Updated2025-09-23
Maintainerimi2
Model Typellama
Instruction-BasedYes
Model Files  9.9 GB: 1-of-25   9.8 GB: 2-of-25   9.9 GB: 3-of-25   9.8 GB: 4-of-25   10.0 GB: 5-of-25   9.7 GB: 6-of-25   9.9 GB: 7-of-25   9.9 GB: 8-of-25   9.8 GB: 9-of-25   10.0 GB: 10-of-25   9.8 GB: 11-of-25   9.9 GB: 12-of-25   9.8 GB: 13-of-25   9.9 GB: 14-of-25   10.0 GB: 15-of-25   9.7 GB: 16-of-25   9.9 GB: 17-of-25   9.9 GB: 18-of-25   9.8 GB: 19-of-25   10.0 GB: 20-of-25   10.0 GB: 21-of-25   9.7 GB: 22-of-25   10.0 GB: 23-of-25   10.0 GB: 24-of-25   6.6 GB: 25-of-25
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Llama 3 120B Instruct Abliterated Merged

Best Alternatives
Context / RAM
Downloads
Likes
Meta Llama 3 225B Instruct8K / 443.2 GB718
...ma 3 Instruct 120B Cat A Llama8K / 243.9 GB71
Koishi 120B Qlora4K / 216.9 GB61
...t 120B Cat A Llama EXL2 5.5bpw8K / 85.3 GB50
...t 120B Cat A Llama EXL2 4.5bpw8K / 70.3 GB41
...egaDolphin 120B 2.9bpw H6 EXL24K / 44.3 GB73
...gaDolphin 120B 2.65bpw H6 EXL24K / 40.5 GB72
...egaDolphin 120B 4.0bpw H6 EXL24K / 60.8 GB61
MegaDolphin 120B GPTQ4K / 61.1 GB84
MegaDolphin 120B AWQ4K / 63.3 GB62
Note: green Score (e.g. "73.2") means that the model is better than imi2/llama-3-120B-Instruct-abliterated-merged.

Rank the Llama 3 120B Instruct Abliterated Merged 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? 51550 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.
Release v20241124
  Support LLM Explorer