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

Dolphin 2.8 Mistral 7B V02 by cognitivecomputations

 »  All LLMs  »  cognitivecomputations  »  Dolphin 2.8 Mistral 7B V02   URL Share it on

  1252   
  Autotrain compatible Base model:finetune:mistral-co... Base model:mistral-community/m...   Conversational Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:jondurbin/airoboros-2....   Dataset:m-a-p/code-feedback Dataset:m-a-p/codefeedback-fil...   Dataset:teknium/openhermes-2.5   En   Endpoints compatible   Instruct   Mistral   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/cognitivecomputations/dolphin-2.8-mistral-7b-v02 

Dolphin 2.8 Mistral 7B V02 Benchmarks

ARC: 62.71 vs 96.7 (so35)-35.1%
HellaSwag: 83.8 vs 95.3 (gpt4)-12.1%
MMLU: 62.59 vs 88.3 (so35)-29.1%
TruthfulQA: 49.58 vs 59 (gpt4)-16%
WinoGrande: 79.32 vs 87.5 (gpt4)-9.3%
GSM8K: 43.75 vs 96.4 (so35)-54.6%
LLME Score: 0.26263
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Dolphin 2.8 Mistral 7B V02 (cognitivecomputations/dolphin-2.8-mistral-7b-v02)

Dolphin 2.8 Mistral 7B V02 Parameters and Internals

Model Type 
text-generation
Additional Notes 
Model recommended to have an alignment layer to ensure ethical use.
Supported Languages 
en (high)
Training Details 
Data Sources:
/workspace/datasets/dolphin201-sharegpt2.jsonl, /workspace/datasets/dolphin-coder-translate-sharegpt2.jsonl, /workspace/datasets/dolphin-coder-codegen-sharegpt2.jsonl, /workspace/datasets/m-a-p_Code-Feedback-sharegpt.jsonl, /workspace/datasets/m-a-p_CodeFeedback-Filtered-Instruction-sharegpt.jsonl, /workspace/datasets/not_samantha_norefusals.jsonl, /workspace/datasets/openhermes2_5-sharegpt.jsonl
Methodology:
fine-tuning
Context Length:
16384
Training Time:
3 days
Hardware Used:
10x L40S from Crusoe Cloud
Model Architecture:
MistralForCausalLM
Input Output 
Accepted Modalities:
text
LLM NameDolphin 2.8 Mistral 7B V02
Repository 🤗https://huggingface.co/cognitivecomputations/dolphin-2.8-mistral-7b-v02 
Base Model(s)  alpindale/Mistral-7B-v0.2-hf   alpindale/Mistral-7B-v0.2-hf
Model Size7b
Required VRAM14.4 GB
Updated2024-12-22
Maintainercognitivecomputations
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 Version4.40.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Torch Data Typebfloat16

Quantized Models of the Dolphin 2.8 Mistral 7B V02

Model
Likes
Downloads
VRAM
Dolphin 2.8 Mistral 7B V02 AWQ21494 GB

Best Alternatives to Dolphin 2.8 Mistral 7B V02

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB26689
SpydazWeb AI HumanAI RP512K / 14.4 GB261
SpydazWeb AI HumanAI 002512K / 14.4 GB191
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB70
...1 Summarize 64K LoRANET Merged128K / 14.4 GB80
Mistral 7B Instruct V0.232K / 14.4 GB32868912598
Mistral 7B Instruct V0.132K / 14.4 GB31398011538
...ity Instruct 7M Gen Mistral 7B32K / 14.4 GB54064
...ty Instruct 3M 0625 Mistral 7B32K / 14.4 GB54203
Note: green Score (e.g. "73.2") means that the model is better than cognitivecomputations/dolphin-2.8-mistral-7b-v02.

Rank the Dolphin 2.8 Mistral 7B V02 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? 40066 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 v20241217
  Support LLM Explorer