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

Calm2 7B Chat DPO Experimental by cyberagent

 »  All LLMs  »  cyberagent  »  Calm2 7B Chat DPO Experimental   URL Share it on

  409   
  Arxiv:2305.18290   Autotrain compatible Base model:cyberagent/calm2-7b... Base model:finetune:cyberagent... Dataset:cyberagent/chatbot-are...   En   Endpoints compatible   Ja   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/cyberagent/calm2-7b-chat-dpo-experimental 

Calm2 7B Chat DPO Experimental Benchmarks

ARC: 41.04 vs 96.7 (so35)-57.6%
HellaSwag: 68.99 vs 95.3 (gpt4)-27.6%
MMLU: 39.82 vs 88.3 (so35)-54.9%
TruthfulQA: 43.13 vs 59 (gpt4)-26.9%
WinoGrande: 65.67 vs 87.5 (gpt4)-24.9%
GSM8K: 5.53 vs 96.4 (so35)-94.3%
LLME Score: 0.20515
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Calm2 7B Chat DPO Experimental (cyberagent/calm2-7b-chat-dpo-experimental)

Calm2 7B Chat DPO Experimental Parameters and Internals

Additional Notes 
Functions similarly to its base model with experimental optimizations using DPO and LoRA.
Supported Languages 
ja (Japanese), en (English)
Training Details 
Data Sources:
cyberagent/chatbot-arena-ja-calm2-7b-chat-experimental
Methodology:
Direct Preference Optimization (DPO) using Low-Rank Adaptation (LoRA)
Release Notes 
Version:
1.0
Date:
Jan 24, 2024
Notes:
v1 release
LLM NameCalm2 7B Chat DPO Experimental
Repository 🤗https://huggingface.co/cyberagent/calm2-7b-chat-dpo-experimental 
Base Model(s)  Calm2 7B Chat   cyberagent/calm2-7b-chat
Model Size7b
Required VRAM28.2 GB
Updated2025-02-22
Maintainercyberagent
Model Typellama
Model Files  4.9 GB: 1-of-6   4.9 GB: 2-of-6   4.9 GB: 3-of-6   4.9 GB: 4-of-6   4.9 GB: 5-of-6   3.7 GB: 6-of-6
Supported Languagesja en
Model ArchitectureLlamaForCausalLM
Licensecc-by-4.0
Context Length32768
Model Max Length32768
Transformers Version4.36.0
Tokenizer ClassGPTNeoXTokenizer
Padding Token<|padding|>
Vocabulary Size65024
Torch Data Typefloat32

Best Alternatives to Calm2 7B Chat DPO Experimental

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 cyberagent/calm2-7b-chat-dpo-experimental.

Rank the Calm2 7B Chat DPO Experimental 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