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

Contextual KTO Mistral PairRM by ContextualAI

 »  All LLMs  »  ContextualAI  »  Contextual KTO Mistral PairRM   URL Share it on

  117   
  Arxiv:2402.01306   Alignment   Autotrain compatible   Conversational Dataset:snorkelai/snorkel-mist...   Dpo   En   Endpoints compatible   Halo   Halos   Human feedback   Instruct   Mistral   Preferences   Region:us   Rl   Rlhf   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ContextualAI/Contextual_KTO_Mistral_PairRM 

Contextual KTO Mistral PairRM Benchmarks

ARC: 64.76 vs 96.7 (so35)-33%
HellaSwag: 85.52 vs 95.3 (gpt4)-10.3%
MMLU: 60.28 vs 88.3 (so35)-31.7%
TruthfulQA: 71.67 vs 59 (gpt4)21.5%
WinoGrande: 75.53 vs 87.5 (gpt4)-13.7%
GSM8K: 33.81 vs 96.4 (so35)-64.9%
LLME Score: 0.19424
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Contextual KTO Mistral PairRM (ContextualAI/Contextual_KTO_Mistral_PairRM)

Contextual KTO Mistral PairRM Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
prompt consistency, text generation
Applications:
cake recipe generation
Primary Use Cases:
chat applications
Additional Notes 
Beginning-of-sequence token added automatically, no EOS token required. Supports apply_chat_template feature.
Training Details 
Data Sources:
snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset
Methodology:
Optimized with the loss KTO, aligned using a dataset and iteratively improved over training partitions.
Input Output 
Input Format:
Prompts should be formatted with `<|user|>` and `<|assistant|>` roles.
Accepted Modalities:
text
LLM NameContextual KTO Mistral PairRM
Repository 🤗https://huggingface.co/ContextualAI/Contextual_KTO_Mistral_PairRM 
Model Size7b
Required VRAM14.4 GB
Updated2025-02-05
MaintainerContextualAI
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.1
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the Contextual KTO Mistral PairRM

Model
Likes
Downloads
VRAM
NebulaNet V2 4x7B MoE4858 GB

Best Alternatives to Contextual KTO Mistral PairRM

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB522710
SpydazWeb AI HumanAI RP512K / 14.4 GB51
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB760
...1 Summarize 64K LoRANET Merged128K / 14.4 GB50
Mistral 7B Instruct V0.232K / 14.4 GB33160952630
Mistral 7B Instruct V0.132K / 14.4 GB12462781551
...ity Instruct 7M Gen Mistral 7B32K / 14.4 GB37145
...ty Instruct 3M 0613 Mistral 7B32K / 14.4 GB641511
Note: green Score (e.g. "73.2") means that the model is better than ContextualAI/Contextual_KTO_Mistral_PairRM.

Rank the Contextual KTO Mistral PairRM 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