Llama 3 8B Instruct Abliterated Q8 by informatiker

 ยป  All LLMs  ยป  informatiker  ยป  Llama 3 8B Instruct Abliterated Q8   URL Share it on

  8-bit   Autotrain compatible   Bitsandbytes   Conversational   Endpoints compatible   Instruct   Llama   Q8   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Uncensored

Rank the Llama 3 8B Instruct Abliterated Q8 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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  
Llama 3 8B Instruct Abliterated Q8 (informatiker/Llama-3-8B-Instruct-abliterated-Q8)

Best Alternatives to Llama 3 8B Instruct Abliterated Q8

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
...ct Gradient 1048K Bpw2.25 EXL21024K / 3.4 GB41
Llama 3 8B Instruct 1048K 4bit1024K / 4.5 GB1225
...B Instruct Gradient 1048K 4bit1024K / 4.5 GB172
...truct Gradient 1048K Bpw5 EXL21024K / 5.8 GB60
...truct Gradient 1048K Bpw6 EXL21024K / 6.7 GB42
Llama 3 8B Instruct 1048K 8bit1024K / 8.6 GB1016
... Gradient 1048K 8.0bpw H8 EXL21024K / 8.6 GB33
...B Instruct Gradient 1048K 8bit1024K / 8.6 GB61
Unholy Thoth 8B1024K / 16.1 GB260
Llama3 8B Special Dark V21024K / 16.1 GB70

Llama 3 8B Instruct Abliterated Q8 Parameters and Internals

LLM NameLlama 3 8B Instruct Abliterated Q8
RepositoryOpen on ๐Ÿค— 
Base Model(s)  ...lama 3 8B Instruct Abliterated   mlabonne/NeuralLlama-3-8B-Instruct-abliterated
Model Size8b
Required VRAM9.1 GB
Updated2024-07-13
Maintainerinformatiker
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   4.1 GB: 2-of-2
Quantization Typeq8
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.42.3
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Initializer Range0.02
Torch Data Typefloat16

What open-source LLMs or SLMs are you in search of? 36243 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801