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

Llama 68M by JackFram

 »  All LLMs  »  JackFram  »  Llama 68M   URL Share it on

  517565   
  Arxiv:2305.09781   Autotrain compatible   Dataset:wikipedia   En   Endpoints compatible   Llama   Pytorch   Region:us
Model Card on HF 🤗: https://huggingface.co/JackFram/llama-68m 

Llama 68M Benchmarks

MMLU Pro: 1.6
GPQA: 1.12
MUSR: 6.61
BBH: 2.59
IFEval: 17.26 vs 88 (so35)-80.4%
MATH Lvl 5: 0.6
LLME Score: 0.22248
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 68M (JackFram/llama-68m)

Llama 68M Parameters and Internals

Model Type 
text generation
Additional Notes 
No evaluation has been conducted on this model yet, so use it with care.
Supported Languages 
English (Full Proficiency)
Training Details 
Data Sources:
Wikipedia, C4-en, C4-realnewslike
Model Architecture:
Small Speculative Model
LLM NameLlama 68M
Repository 🤗https://huggingface.co/JackFram/llama-68m 
Model Size68m
Required VRAM0 GB
Updated2025-02-22
MaintainerJackFram
Model Typellama
Model Files  0.5 GB   0.3 GB   0.0 GB   0.0 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.30.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat32

Best Alternatives to Llama 68M

Best Alternatives
Context / RAM
Downloads
Likes
Llama 68M Fft4K / 0.1 GB3120
Llama 43M Beta2K / 0.2 GB2290
Llama 68M Chat V12K / 0.3 GB123211
Vicuna 68M2K / 0.3 GB27323
Gpt2 Sft Dutch2K / 0.1 GB200
Llama 68M Oasst Top12K / 0.3 GB1550
Llama 68M Finetuned Wikitext22K / 0.3 GB1640
Llama 68M Oasst2K / 0.3 GB930
Jack 68M Text Structurization2K / 0.1 GB102
JackFram Llama 68M2K / 0.3 GB1193
Note: green Score (e.g. "73.2") means that the model is better than JackFram/llama-68m.

Rank the Llama 68M 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? 43470 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