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

Bitnet 1.58B Nous Llama2 70M by nijil-k

 »  All LLMs  »  nijil-k  »  Bitnet 1.58B Nous Llama2 70M   URL Share it on

  508   
  Arxiv:2402.17764   Autotrain compatible   Endpoints compatible   Llama   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/nijil-k/Bitnet-1.58b-Nous-Llama2-70M 

Bitnet 1.58B Nous Llama2 70M Benchmarks

LLME Score: 0.19728
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Bitnet 1.58B Nous Llama2 70M (nijil-k/Bitnet-1.58b-Nous-Llama2-70M)

Bitnet 1.58B Nous Llama2 70M Parameters and Internals

Model Type 
causal language model
Additional Notes 
This model is purely experimental and may not provide optimal results. It's designed to test the BitNet methodology on smaller scale models.
Training Details 
Data Sources:
HuggingFaceTB/cosmopedia dataset
Methodology:
BitNet training as described in the paper
Hardware Used:
Colab T4 GPU
Model Architecture:
1-bit LLM architecture
Input Output 
Input Format:
prompts as strings
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Due to smaller model size, performance might not be optimal; suitable for experimentation.
LLM NameBitnet 1.58B Nous Llama2 70M
Repository 🤗https://huggingface.co/nijil-k/Bitnet-1.58b-Nous-Llama2-70M 
Model Size7b
Required VRAM0.3 GB
Updated2025-02-22
Maintainernijil-k
Model Typellama
Model Files  0.3 GB   0.0 GB
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length768
Model Max Length768
Transformers Version4.40.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32001
Torch Data Typefloat32

Best Alternatives to Bitnet 1.58B Nous Llama2 70M

Best Alternatives
Context / RAM
Downloads
Likes
2 Very Sci Fi1024K / 16.1 GB3170
...1M 1000000ctx AEZAKMI 3 1 17021024K / 13.5 GB231
... Qwen2.5llamaify 7B V23.1 200K195K / 15.2 GB39433
LlamaStock 8B128K / 16.1 GB111
SuperNeuralDreadDevil 8B128K / 16.1 GB541
Yarn Llama 2 7B 128K128K / 13.5 GB642239
LLaMA 7B PoSE YaRN 128K128K / 13.5 GB73
LLaMA 7B PoSE Linear 96K96K / 27 GB92
LLaMA 7B PoSE YaRN 96K96K / 13.5 GB111
Chat Llama2 7B 80K80K / 13.8 GB80
Note: green Score (e.g. "73.2") means that the model is better than nijil-k/Bitnet-1.58b-Nous-Llama2-70M.

Rank the Bitnet 1.58B Nous Llama2 70M 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