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

Meta Llama 3 8B Instruct Abliterated V3 GPTQ 4bit by chplushsieh

 »  All LLMs  »  chplushsieh  »  Meta Llama 3 8B Instruct Abliterated V3 GPTQ 4bit   URL Share it on

  5   
  4-bit   4bit   Autotrain compatible   Conversational   Endpoints compatible   Gptq   Instruct   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Meta Llama 3 8B Instruct Abliterated V3 GPTQ 4bit Benchmarks

ARC: 61.6 vs 96.7 (so35)-36.3%
HellaSwag: 78.35 vs 95.3 (gpt4)-17.8%
MMLU: 66.67 vs 88.3 (so35)-24.5%
TruthfulQA: 52.44 vs 59 (gpt4)-11.1%
WinoGrande: 74.51 vs 87.5 (gpt4)-14.8%
GSM8K: 70.05 vs 96.4 (so35)-27.3%
LLME Score: 0.23495
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Meta Llama 3 8B Instruct Abliterated V3 GPTQ 4bit Parameters and Internals

LLM NameMeta Llama 3 8B Instruct Abliterated V3 GPTQ 4bit
Repository 🤗https://huggingface.co/chplushsieh/Meta-Llama-3-8B-Instruct-abliterated-v3-GPTQ-4bit 
Base Model(s)  ...a 3 8B Instruct Abliterated V3   failspy/Meta-Llama-3-8B-Instruct-abliterated-v3
Model Size8b
Required VRAM5.8 GB
Updated2024-09-18
Maintainerchplushsieh
Model Typellama
Instruction-BasedYes
Model Files  4.7 GB: 1-of-2   1.1 GB: 2-of-2
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.41.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typefloat16
Meta Llama 3 8B Instruct Abliterated V3 GPTQ 4bit (chplushsieh/Meta-Llama-3-8B-Instruct-abliterated-v3-GPTQ-4bit)

Best Alternatives to Meta Llama 3 8B Instruct Abliterated V3 GPTQ 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct 262K 4bit GPTQ256K / 5.8 GB41
... 8B Instruct 262K 4bit GPTQ 02256K / 5.7 GB50
...lama 3.1 8B Instruct GPTQ INT4128K / 5.8 GB5329010
...Instruct 80K Qlora Merged GPTQ80K / 5.8 GB330
...oLeo Instruct 8B 32K V0.1 GPTQ64K / 5.7 GB60
Llama 3 8B Instruct GPTQ 8 Bit8K / 9.7 GB1179025
Llama 3 8B Instruct GPTQ 4 Bit8K / 5.7 GB346824
Meta Llama 3 8B Instruct GPTQ8K / 5.7 GB8953
Meta Llama 3 8B Instruct GPTQ8K / 5.8 GB50
...ta Llama 3 8B Instruct GPTQ 8B8K / 9.2 GB80
Note: green Score (e.g. "73.2") means that the model is better than chplushsieh/Meta-Llama-3-8B-Instruct-abliterated-v3-GPTQ-4bit.

Rank the Meta Llama 3 8B Instruct Abliterated V3 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? 36026 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 v2024072803
  Support LLM Explorer