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 6.3B V0.1 by pszemraj

 »  All LLMs  »  pszemraj  »  Llama 3 6.3B V0.1   URL Share it on

  37   
  Autotrain compatible   Axolotl Base model:finetune:meta-llama... Base model:meta-llama/meta-lla... Dataset:bee-spoke-data/ki-smor...   En   Endpoints compatible   Llama   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/pszemraj/Llama-3-6.3b-v0.1 

Llama 3 6.3B V0.1 Benchmarks

MMLU Pro: 20.44
GPQA: 4.47
MUSR: 6.15
BBH: 18.68
IFEval: 10.44 vs 88 (so35)-88.1%
MATH Lvl 5: 1.81
LLME Score: 0.22213
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 3 6.3B V0.1 (pszemraj/Llama-3-6.3b-v0.1)

Llama 3 6.3B V0.1 Parameters and Internals

Model Type 
text-generation
Additional Notes 
This is a layer pruning experiment based on Llama-3-8B.
Training Details 
Data Sources:
BEE-spoke-data/KI-smorgasbord_fw-small, BEE-spoke-data/fineweb-100k_en-med
Data Volume:
10k rows of FineWeb + some curated data
Methodology:
Layer pruning with PruneMe/MergeKit
Context Length:
4096
Training Time:
No log
Model Architecture:
8 layers pruned using PruneMe
LLM NameLlama 3 6.3B V0.1
Repository 🤗https://huggingface.co/pszemraj/Llama-3-6.3b-v0.1 
Base Model(s)  Meta Llama 3 8B   meta-llama/Meta-Llama-3-8B
Model Size8b
Required VRAM12.6 GB
Updated2025-01-22
Maintainerpszemraj
Model Typellama
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   2.6 GB: 3-of-3   0.0 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.40.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|end_of_text|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama 3 6.3B V0.1

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB6524680
MrRoboto ProLong 8B V4i1024K / 16.1 GB661
...o ProLongBASE Pt8 Unaligned 8B1024K / 16.1 GB240
41024K / 16.1 GB3220
Because Im Bored Nsfw11024K / 16.1 GB241
Thor V1.4 8B DARK FICTION1024K / 16.1 GB9412
161024K / 16.1 GB1690
111024K / 16.1 GB1130
NBeerbower Narrative 8B 64K1024K / 16.1 GB141
121024K / 16.1 GB600
Note: green Score (e.g. "73.2") means that the model is better than pszemraj/Llama-3-6.3b-v0.1.

Rank the Llama 3 6.3B V0.1 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? 41728 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 v20241227
  Support LLM Explorer