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

Opt 6.7B Gptq 4bit by iproskurina

 »  All LLMs  »  iproskurina  »  Opt 6.7B Gptq 4bit   URL Share it on

  90   
  Arxiv:2210.17323   4bit   Autotrain compatible   Base model:facebook/opt-6.7b Base model:finetune:facebook/o...   Dataset:c4   En   Gptq   Opt   Pretrained   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/iproskurina/opt-6.7b-gptq-4bit 

Opt 6.7B Gptq 4bit Benchmarks

LLME Score: 0.16151
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Opt 6.7B Gptq 4bit (iproskurina/opt-6.7b-gptq-4bit)

Opt 6.7B Gptq 4bit Parameters and Internals

Model Type 
opt, text-generation
Additional Notes 
Quantized by iproskurina using AutoGPTQ.
Supported Languages 
en (High)
LLM NameOpt 6.7B Gptq 4bit
Repository 🤗https://huggingface.co/iproskurina/opt-6.7b-gptq-4bit 
Model Nameopt-6.7b
Model Creatorfacebook
Base Model(s)  facebook/opt-6.7b   facebook/opt-6.7b
Model Size6.7b
Required VRAM4.2 GB
Updated2024-09-23
Maintaineriproskurina
Model Typeopt
Model Files  4.2 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureOPTForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.35.2
Tokenizer ClassGPT2Tokenizer
Padding Token<pad>
Vocabulary Size50272
Torch Data Typefloat16
Activation Functionrelu
Errorsreplace

Best Alternatives to Opt 6.7B Gptq 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Opt 6.7B GPTQ 4bit G1282K / 4.2 GB290
....7B Qcqa Ub 16 Best For Q Loss2K / 27.4 GB740
...B Qcqa Ub 16 Best For KV Cache2K / 27.4 GB750
...7B Gqa Ub 16 Best For KV Cache2K / 27.4 GB710
Galactica 6.7B ReFT GSM8k2K / 13.8 GB760
Galactica 6.7B EssayWriter2K / 13.4 GB11563
Opt Flan Iml 6.7B2K / 26.6 GB12491
...lactica 6.7B Evol Instruct 70K2K / 27.4 GB124419
OPT 6.7B Nerybus Mix2K / 13.7 GB155620
Galactica 6.7B Finetuned2K / 27.4 GB122334
Note: green Score (e.g. "73.2") means that the model is better than iproskurina/opt-6.7b-gptq-4bit.

Rank the Opt 6.7B Gptq 4bit 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? 40066 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 v20241217
  Support LLM Explorer