Llama 3 8B Bnb 4bit by unsloth

 ยป  All LLMs  ยป  unsloth  ยป  Llama 3 8B Bnb 4bit   URL Share it on

  4-bit   4bit   Autotrain compatible   Bitsandbytes   En   Endpoints compatible   License:llama3   Llama   Llama-3   Quantized   Region:us   Safetensors   Unsloth

Llama 3 8B Bnb 4bit Parameters and Internals

LLM NameLlama 3 8B Bnb 4bit
RepositoryOpen on ๐Ÿค— 
Base Model(s)  Al Baka Lora Llama3 8B   Omartificial-Intelligence-Space/al-baka-Lora-llama3-8b
Model Size8b
Required VRAM5.7 GB
Model Typellama
Model Files  5.7 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.41.0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|reserved_special_token_250|>
Vocabulary Size128256
Torch Data Typebfloat16
Llama 3 8B Bnb 4bit (unsloth/llama-3-8b-bnb-4bit)

Quantized Models of the Llama 3 8B Bnb 4bit

...3 8B Instruct Robot Test Model0134194 GB
Thy Model 320617616 GB
Thy Model 34055194 GB
SupaMATH035325 GB
...aMA 3 8B Function Calling GGUF045604 GB
Llama3 8B Gf Selector F16 Gguf0380116 GB
Thy Model 31016598 GB
Model0235916 GB
Llama3 Credpol0302121 GB
Llama3 8B Custom Gguf019734 GB

Best Alternatives to Llama 3 8B Bnb 4bit

Best Alternatives
HF Rank
...B Instruct Gradient 1048K 4bit0.31024K / 4.5 GB132
...B Instruct Gradient 1048K 8bit0.31024K / 8.6 GB171
...truct Gradient 1048K Bpw6 EXL20.21024K / 6.7 GB122
...truct Gradient 1048K Bpw5 EXL20.21024K / 5.8 GB70
Llama 3 8B Instruct 1048K 4bit0.21024K / 4.5 GB1825
Llama 3 8B Instruct 1048K 8bit0.21024K / 8.6 GB1516
... Gradient 1048K 8.0bpw H8 EXL20.21024K / 8.6 GB113
...ct Gradient 1048K Bpw2.25 EXL20.21024K / 3.4 GB81
...B Instruct 262k V2 EXL2 8.0bpw0.2256K / 8.4 GB520
Llama 3 8B Instruct 262K 2bit0.2256K / 2.5 GB111

Rank the Llama 3 8B Bnb 4bit 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  

What open-source LLMs or SLMs are you in search of? 34266 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024071601