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

Cognitivecomputations Dolphin 2.8 Mistral 7B V02 8bits by RichardErkhov

 »  All LLMs  »  RichardErkhov  »  Cognitivecomputations Dolphin 2.8 Mistral 7B V02 8bits   URL Share it on

  78   
  8-bit   Autotrain compatible   Bitsandbytes   Conversational   Endpoints compatible   Instruct   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.8-mistral-7b-v02-8bits 

Cognitivecomputations Dolphin 2.8 Mistral 7B V02 8bits Benchmarks

LLME Score: 0.18763
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Cognitivecomputations Dolphin 2.8 Mistral 7B V02 8bits (RichardErkhov/cognitivecomputations_-_dolphin-2.8-mistral-7b-v02-8bits)

Cognitivecomputations Dolphin 2.8 Mistral 7B V02 8bits Parameters and Internals

Model Type 
text-generation
Use Cases 
Limitations:
It may comply with unethical content requests without an alignment layer.
Considerations:
Ensure implementation of an alignment layer for compliant operations.
Additional Notes 
Model is based on the Mistral-7B-v0.2 architecture, designed for versatility without inherent ethical alignment mechanisms.
Supported Languages 
en (primary)
Training Details 
Data Sources:
cognitivecomputations/dolphin, cognitivecomputations/dolphin-coder, cognitivecomputations/samantha-data, jondurbin/airoboros-2.2.1, teknium/openhermes-2.5, m-a-p/Code-Feedback, m-a-p/CodeFeedback-Filtered-Instruction
Context Length:
32768
Training Time:
3 days
Hardware Used:
10x L40S GPUs
Model Architecture:
MistralForCausalLM
Responsible Ai Considerations 
Fairness:
Dataset has been filtered to remove alignment and bias.
Mitigation Strategies:
Implement your own alignment layer before exposing the model as a service.
Input Output 
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Optimize the alignment layer to ensure ethical compliance.
LLM NameCognitivecomputations Dolphin 2.8 Mistral 7B V02 8bits
Repository 🤗https://huggingface.co/RichardErkhov/cognitivecomputations_-_dolphin-2.8-mistral-7b-v02-8bits 
Model Size7b
Required VRAM7.6 GB
Updated2025-02-22
MaintainerRichardErkhov
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.6 GB: 2-of-2
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.40.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Torch Data Typefloat16

Best Alternatives to Cognitivecomputations Dolphin 2.8 Mistral 7B V02 8bits

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB462011
SpydazWeb AI HumanAI RP512K / 14.4 GB121
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB120
...1 Summarize 64K LoRANET Merged128K / 14.4 GB110
Mistral 7B Instruct V0.232K / 14.4 GB33160952630
Mistral 7B Instruct V0.132K / 14.4 GB1916301573
...ity Instruct 7M Gen Mistral 7B32K / 14.4 GB37505
...ty Instruct 3M 0625 Mistral 7B32K / 14.4 GB37063
Note: green Score (e.g. "73.2") means that the model is better than RichardErkhov/cognitivecomputations_-_dolphin-2.8-mistral-7b-v02-8bits.

Rank the Cognitivecomputations Dolphin 2.8 Mistral 7B V02 8bits 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