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

Mistral 7B Dolphin Sft by CorticalStack

 »  All LLMs  »  CorticalStack  »  Mistral 7B Dolphin Sft   URL Share it on

  110   

Mistral 7B Dolphin Sft is an open-source language model by CorticalStack. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, Quantized, HF Score: 60.8, LLM Explorer Score: 0.14, Arc: 57.3, HellaSwag: 83, MMLU: 62.6, TruthfulQA: 48.9, WinoGrande: 77.5, GSM8K: 35.8.

  4bit   Endpoints compatible   Mistral   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/CorticalStack/mistral-7b-dolphin-sft 

Mistral 7B Dolphin Sft Benchmarks

ARC: 57.25 vs 96.7 (so35)-40.8%
HellaSwag: 83.01 vs 95.3 (gpt4)-12.9%
MMLU: 62.59 vs 88.3 (so35)-29.1%
TruthfulQA: 48.91 vs 59 (gpt4)-17.1%
WinoGrande: 77.51 vs 87.5 (gpt4)-11.4%
GSM8K: 35.78 vs 96.4 (so35)-62.9%
LLME Score: 0.14117
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mistral 7B Dolphin Sft (CorticalStack/mistral-7b-dolphin-sft)
🌟 Advertise your project 🚀

Mistral 7B Dolphin Sft Parameters and Internals

Additional Notes 
Fine-tuning involved LoRA with parameters: r=256, alpha=128, dropout=0.0. Trained with adamw_torch_fused optimizer, batch size of 4, gradient accumulation steps of 6, for 100 max steps, and learning rate of 0.0002.
Training Details 
Data Sources:
cognitivecomputations/dolphin
Methodology:
SFT fine-tuning
Context Length:
2048
LLM NameMistral 7B Dolphin Sft
Repository 🤗https://huggingface.co/CorticalStack/mistral-7b-dolphin-sft 
Model Size7b
Required VRAM14.4 GB
Updated2026-03-30
MaintainerCorticalStack
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Mistral 7B Dolphin Sft

Best Alternatives
Context / RAM
Downloads
Likes
...t 3.5 0106 128K 4.0bpw H6 EXL2128K / 3.9 GB11
...t 3.5 0106 128K 8.0bpw H8 EXL2128K / 7.4 GB11
Mistral 7B V0.3 Bnb 4bit32K / 4.1 GB35143322
Mistral 7B Instruct V0.2 Fp1632K / 14.4 GB260
Mistral 7B Instruct V0.2 4bit32K / 4.3 GB1331
...tral 7B Instruct V0.3 Bnb 4bit32K / 4.1 GB3043728
Mistral 7B Instruct V0.2 8bit32K / 7.6 GB131
...tral 7B Instruct V0.2 Bnb 4bit32K / 4.1 GB1256736
Mixtral V0.3 Full 16bit32K / 14.5 GB60
Mistral 7B Instruct V0.3 4bit32K / 4.1 GB250538
Note: green Score (e.g. "73.2") means that the model is better than CorticalStack/mistral-7b-dolphin-sft.

Rank the Mistral 7B Dolphin Sft 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? 52473 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer