Cornerstone 0.1 LLaMA 70B by k4yt3x

 ยป  All LLMs  ยป  k4yt3x  ยป  Cornerstone 0.1 LLaMA 70B   URL Share it on

  Merged Model   Arxiv:2408.07990   Autotrain compatible Base model:huihui-ai/llama-3.3... Base model:nanidao/llama-3.3-7... Base model:nbeerbower/llama-3.... Base model:sentientagi/dobby-u... Base model:sicariussicariistuf...   Conversational   Endpoints compatible   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow

Cornerstone 0.1 LLaMA 70B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Cornerstone 0.1 LLaMA 70B (k4yt3x/Cornerstone-0.1-LLaMA-70B)

Cornerstone 0.1 LLaMA 70B Parameters and Internals

LLM NameCornerstone 0.1 LLaMA 70B
Repository ๐Ÿค—https://huggingface.co/k4yt3x/Cornerstone-0.1-LLaMA-70B 
Base Model(s)  NaniDAO/Llama-3.3-70B-Instruct-ablated   huihui-ai/Llama-3.3-70B-Instruct-abliterated   nbeerbower/Llama-3.1-Nemotron-lorablated-70B   SentientAGI/Dobby-Unhinged-Llama-3.3-70B   Negative LLAMA 70B   NaniDAO/Llama-3.3-70B-Instruct-ablated   huihui-ai/Llama-3.3-70B-Instruct-abliterated   nbeerbower/Llama-3.1-Nemotron-lorablated-70B   SentientAGI/Dobby-Unhinged-Llama-3.3-70B   SicariusSicariiStuff/Negative_LLAMA_70B
Merged ModelYes
Model Size70b
Required VRAM210.4 GB
Updated2025-03-21
Maintainerk4yt3x
Model Typellama
Instruction-BasedYes
Model Files  4.2 GB: 1-of-62   4.2 GB: 2-of-62   4.4 GB: 3-of-62   4.4 GB: 4-of-62   5.0 GB: 5-of-62   4.4 GB: 6-of-62   4.4 GB: 7-of-62   5.0 GB: 8-of-62   4.4 GB: 9-of-62   4.4 GB: 10-of-62   5.0 GB: 11-of-62   4.4 GB: 12-of-62   4.4 GB: 13-of-62   5.0 GB: 14-of-62   4.4 GB: 15-of-62   4.4 GB: 16-of-62   5.0 GB: 17-of-62   4.4 GB: 18-of-62   4.4 GB: 19-of-62   5.0 GB: 20-of-62   4.4 GB: 21-of-62   4.4 GB: 22-of-62   5.0 GB: 23-of-62   4.4 GB: 24-of-62   4.4 GB: 25-of-62   5.0 GB: 26-of-62   4.4 GB: 27-of-62   4.4 GB: 28-of-62   5.0 GB: 29-of-62   4.4 GB: 30-of-62   4.4 GB: 31-of-62   5.0 GB: 32-of-62   4.4 GB: 33-of-62   4.4 GB: 34-of-62   5.0 GB: 35-of-62   4.4 GB: 36-of-62   4.4 GB: 37-of-62   5.0 GB: 38-of-62   4.4 GB: 39-of-62   4.4 GB: 40-of-62   5.0 GB: 41-of-62   4.4 GB: 42-of-62   4.4 GB: 43-of-62   5.0 GB: 44-of-62   4.4 GB: 45-of-62   4.4 GB: 46-of-62
Model ArchitectureLlamaForCausalLM
Licensellama3.3
Context Length131072
Model Max Length131072
Transformers Version4.49.0
Vocabulary Size128256
Torch Data Typefloat32

Best Alternatives to Cornerstone 0.1 LLaMA 70B

Best Alternatives
Context / RAM
Downloads
Likes
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB40355
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB103121
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB2235
Llama3 Function Calling 1048K1024K / 141.9 GB81
...a 3 70B Instruct Gradient 524K512K / 141.9 GB3523
...a 3 70B Instruct Gradient 262K256K / 141.9 GB7055
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB143
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB522
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB60
...a 3.1 Nemotron 70B Instruct HF128K / 141.9 GB2604212028
Note: green Score (e.g. "73.2") means that the model is better than k4yt3x/Cornerstone-0.1-LLaMA-70B.

Rank the Cornerstone 0.1 LLaMA 70B Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 45354 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227