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

Georgesung Llama2 7B Chat Uncensored 4bits by RichardErkhov

 »  All LLMs  »  RichardErkhov  »  Georgesung Llama2 7B Chat Uncensored 4bits   URL Share it on

  12   
  4-bit   Autotrain compatible   Bitsandbytes   Endpoints compatible   Llama   Region:us   Safetensors   Uncensored
Model Card on HF 🤗: https://huggingface.co/RichardErkhov/georgesung_-_llama2_7b_chat_uncensored-4bits 

Georgesung Llama2 7b Chat Uncensored 4bits Benchmarks

LLME Score: 0.19537
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Georgesung Llama2 7B Chat Uncensored 4bits (RichardErkhov/georgesung_-_llama2_7b_chat_uncensored-4bits)

Georgesung Llama2 7B Chat Uncensored 4bits Parameters and Internals

Model Type 
text generation
Supported Languages 
English (high)
Training Details 
Data Sources:
georgesung/wizard_vicuna_70k_unfiltered
Methodology:
Quantization using QLoRA, trained for one epoch
Training Time:
~19 hours
Hardware Used:
NVIDIA A10G with 24GB GPU
Model Architecture:
Fine-tuning on Llama-2 7B with Wizard-Vicuna conversation dataset
Input Output 
Input Format:
### HUMAN: [Question] ### RESPONSE: [Response]
Accepted Modalities:
text
Output Format:
text
LLM NameGeorgesung Llama2 7b Chat Uncensored 4bits
Repository 🤗https://huggingface.co/RichardErkhov/georgesung_-_llama2_7b_chat_uncensored-4bits 
Model Size7b
Required VRAM4.2 GB
Updated2024-12-26
MaintainerRichardErkhov
Model Typellama
Model Files  4.2 GB
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.40.2
Tokenizer ClassLlamaTokenizer
Padding Token[PAD]
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Georgesung Llama2 7B Chat Uncensored 4bits

Best Alternatives
Context / RAM
Downloads
Likes
...4.95 New Writer 7B NON FICTION1024K / 16.1 GB651
...ruct Uncensored Abliterated 7B128K / 15.4 GB23206
Marcoro14 7B Slerp8K / 14.5 GB150
L2 7B Base WVG Uncensored4K / 13.5 GB11860
L2 7B Base Guanaco Uncensored4K / 13.5 GB11460
Guanaco 7B Uncensored4K / 13.5 GB11537
...sslessMegaCoder Llama2 7B Mini4K / 13.4 GB118313
L2 7B Zar WVG Test4K / 13.5 GB131
Lunaboros Limarp 7B4K / 13.5 GB150
Freyja V4.92a 7B ACADEMIC2K / 13.5 GB90
Note: green Score (e.g. "73.2") means that the model is better than RichardErkhov/georgesung_-_llama2_7b_chat_uncensored-4bits.

Rank the Georgesung Llama2 7B Chat Uncensored 4bits 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? 40248 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