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

Higgs Llama 3 70B by bosonai

 »  All LLMs  »  bosonai  »  Higgs Llama 3 70B   URL Share it on

  103   
  Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/meta-lla...   Conversational   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/bosonai/Higgs-Llama-3-70B 

Higgs Llama 3 70B Benchmarks

MMLU Pro: 43.35
GPQA: 15.55
MUSR: 15.52
BBH: 45.9
IFEval: 55.61 vs 88 (so35)-36.8%
MATH Lvl 5: 17.37
LLME Score: 0.31571
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Higgs Llama 3 70B (bosonai/Higgs-Llama-3-70B)

Higgs Llama 3 70B Parameters and Internals

Additional Notes 
Fine-tuned for role-playing; targeted exclusion of overfitting benchmark data from training.
Training Details 
Methodology:
We perform supervised fine-tuning with our in-house instruction-following and chat datasets; preference pairs are constructed with a semi-automated pipeline using human-labelers and private LLMs; iterative preference optimization aligns the model.
Input Output 
Input Format:
Same prompting format as in Meta-Llama-3-70B-Instruct
Accepted Modalities:
text
Output Format:
Text generation
LLM NameHiggs Llama 3 70B
Repository 🤗https://huggingface.co/bosonai/Higgs-Llama-3-70B 
Base Model(s)  Meta Llama 3 70B   meta-llama/Meta-Llama-3-70B
Model Size70b
Required VRAM202.4 GB
Updated2025-02-05
Maintainerbosonai
Model Typellama
Model Files  4.8 GB: 1-of-62   4.4 GB: 2-of-62   4.4 GB: 3-of-62   5.0 GB: 4-of-62   4.4 GB: 5-of-62   4.4 GB: 6-of-62   5.0 GB: 7-of-62   4.4 GB: 8-of-62   4.4 GB: 9-of-62   5.0 GB: 10-of-62   4.4 GB: 11-of-62   4.4 GB: 12-of-62   5.0 GB: 13-of-62   4.4 GB: 14-of-62   4.4 GB: 15-of-62   5.0 GB: 16-of-62   4.4 GB: 17-of-62   4.4 GB: 18-of-62   5.0 GB: 19-of-62   4.4 GB: 20-of-62   4.4 GB: 21-of-62   5.0 GB: 22-of-62   4.4 GB: 23-of-62   4.4 GB: 24-of-62   5.0 GB: 25-of-62   4.4 GB: 26-of-62   4.4 GB: 27-of-62   5.0 GB: 28-of-62   4.4 GB: 29-of-62   4.4 GB: 30-of-62   5.0 GB: 31-of-62   4.4 GB: 32-of-62   4.4 GB: 33-of-62   5.0 GB: 34-of-62   4.4 GB: 35-of-62   4.4 GB: 36-of-62   5.0 GB: 37-of-62   4.4 GB: 38-of-62   4.4 GB: 39-of-62   5.0 GB: 40-of-62   4.4 GB: 41-of-62   4.4 GB: 42-of-62   5.0 GB: 43-of-62   4.4 GB: 44-of-62
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.39.3
Vocabulary Size128256
Torch Data Typefloat32

Best Alternatives to Higgs Llama 3 70B

Best Alternatives
Context / RAM
Downloads
Likes
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB40355
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB114121
Llama3 Function Calling 1048K1024K / 141.9 GB51
...a 3 70B Instruct Gradient 524K512K / 141.9 GB15723
...a 3 70B Instruct Gradient 262K256K / 141.9 GB9355
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB1952
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB313
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB50
Yi 70B 200K RPMerge Franken195K / 142.4 GB71
DeepSeek R1 Distill Llama 70B128K / 141 GB156830453
Note: green Score (e.g. "73.2") means that the model is better than bosonai/Higgs-Llama-3-70B.

Rank the Higgs Llama 3 70B 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? 42577 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