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

Llama 3 8B by AI-Sweden-Models

 »  All LLMs  »  AI-Sweden-Models  »  Llama 3 8B   URL Share it on

  603   
  Arxiv:2303.17183   Ai-sweden   Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/meta-lla...   Da   Endpoints compatible   Llama   Llama-3   No   Pytorch   Region:us   Safetensors   Sharded   Sv   Tensorflow
Model Card on HF 🤗: https://huggingface.co/AI-Sweden-Models/Llama-3-8B 

Llama 3 8B Benchmarks

LLME Score: 0.22001
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 8B (AI-Sweden-Models/Llama-3-8B)

Llama 3 8B Parameters and Internals

Model Type 
text_generation
Use Cases 
Primary Use Cases:
General text generation
Supported Languages 
sv (high), da (high), no (high)
Training Details 
Data Sources:
The Nordic Pile (Swedish, Norwegian, Danish)
Data Volume:
227,105,079,296 tokens
Methodology:
full finetune
Context Length:
8192
Training Time:
30 days
Hardware Used:
92 Nvidia A100 GPUs (23 nodes with 4 GPUs each)
Input Output 
Input Format:
text
Accepted Modalities:
text
Output Format:
generated text
Release Notes 
Version:
1 epoch
Date:
2024-06-15
Notes:
Checkpoint at 18833
Version:
Checkpoint
Date:
2024-06-11
Notes:
Checkpoint at 16000
Version:
Checkpoint
Date:
2024-06-07
Notes:
Checkpoint at 14375
Version:
Checkpoint
Date:
2024-06-03
Notes:
Checkpoint at 11525
Version:
Checkpoint
Date:
2024-05-29
Notes:
Checkpoint at 8200
Version:
Checkpoint
Date:
2024-05-26
Notes:
Checkpoint at 6550
Version:
Checkpoint
Date:
2024-05-24
Notes:
Checkpoint at 5325
Version:
Checkpoint
Date:
2024-05-22
Notes:
Checkpoint at 3900
Version:
Checkpoint
Date:
2024-05-20
Notes:
Checkpoint at 2700
Version:
Checkpoint
Date:
2024-05-13
Notes:
Checkpoint at 1500
LLM NameLlama 3 8B
Repository 🤗https://huggingface.co/AI-Sweden-Models/Llama-3-8B 
Base Model(s)  Meta Llama 3 8B   meta-llama/Meta-Llama-3-8B
Model Size8b
Required VRAM16.1 GB
Updated2024-12-14
MaintainerAI-Sweden-Models
Model Typellama
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4
Supported Languagessv da no
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.40.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama 3 8B

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB14046677
Thor V1.4 8B DARK FICTION1024K / 16.1 GB9412
Test V0.7y 8B1024K / 16.1 GB1090
Test V0.7z 8B1024K / 16.1 GB760
Test V0.7z1 8B1024K / 16.1 GB520
Test V0.6B 8B1024K / 16.1 GB850
Test V0.6v 8B1024K / 16.1 GB580
Test V0.7d 8B1024K / 16.1 GB570
Test V0.6c 8B1024K / 16.1 GB670
Test V0.6l 8B1024K / 16.1 GB510
Note: green Score (e.g. "73.2") means that the model is better than AI-Sweden-Models/Llama-3-8B.

Rank the Llama 3 8B 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? 39237 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 v20241124
  Support LLM Explorer