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

Dolphin 2.9.3 Mistral 7B 32K by cognitivecomputations

 »  All LLMs  »  cognitivecomputations  »  Dolphin 2.9.3 Mistral 7B 32K   URL Share it on

  2835   

Dolphin 2.9.3 Mistral 7B 32K is an open-source language model by cognitivecomputations. Features: 7b LLM, VRAM: 14.5GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.23.

  Autotrain compatible   Axolotl Base model:finetune:mistralai/... Base model:mistralai/mistral-7...   Conversational Dataset:cognitivecomputations/... Dataset:cognitivecomputations/... Dataset:cognitivecomputations/...   Dataset:internlm/agent-flan Dataset:locutusque/function-ca... Dataset:m-a-p/codefeedback-fil... Dataset:microsoft/orca-math-wo...   Dataset:teknium/openhermes-2.5   Endpoints compatible   Generated from trainer   Mistral   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/cognitivecomputations/dolphin-2.9.3-mistral-7B-32k 

Dolphin 2.9.3 Mistral 7B 32K Benchmarks

MMLU Pro: 20.23
GPQA: 4.7
MUSR: 17.93
BBH: 26.91
IFEval: 41.26 vs 88 (so35)-53.1%
MATH Lvl 5: 5.06
LLME Score: 0.2257
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Dolphin 2.9.3 Mistral 7B 32K (cognitivecomputations/dolphin-2.9.3-mistral-7B-32k)
🌟 Advertise your project 🚀

Dolphin 2.9.3 Mistral 7B 32K Parameters and Internals

Model Type 
AutoModelForCausalLM
Use Cases 
Limitations:
Highly compliant with any requests, even unethical ones
Considerations:
Read the blog post about uncensored models at https://erichartford.com/uncensored-models
Training Details 
Data Sources:
cognitivecomputations/Dolphin-2.9, teknium/OpenHermes-2.5, m-a-p/CodeFeedback-Filtered-Instruction, cognitivecomputations/dolphin-coder, cognitivecomputations/samantha-data, microsoft/orca-math-word-problems-200k, Locutusque/function-calling-chatml, internlm/Agent-FLAN
Hardware Used:
Crusoe Cloud's 8xH100 node
Responsible Ai Considerations 
Fairness:
The dataset was filtered to remove alignment and bias.
Mitigation Strategies:
Implement your own alignment layer before exposing the model.
Input Output 
Input Format:
ChatML prompt template
LLM NameDolphin 2.9.3 Mistral 7B 32K
Repository 🤗https://huggingface.co/cognitivecomputations/dolphin-2.9.3-mistral-7B-32k 
Base Model(s)  mistralai/Mistral-7B-v0.3   mistralai/Mistral-7B-v0.3
Model Size7b
Required VRAM14.5 GB
Updated2025-07-13
Maintainercognitivecomputations
Model Typemistral
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.41.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32770
Torch Data Typebfloat16

Best Alternatives to Dolphin 2.9.3 Mistral 7B 32K

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB25420
MegaBeam Mistral 7B 512K512K / 14.4 GB810354
SpydazWeb AI HumanAI RP512K / 14.4 GB141
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB377916
MegaBeam Mistral 7B 300K282K / 14.4 GB785016
Hebrew Mistral 7B 200K256K / 30 GB125115
Astral 256K 7B V2250K / 14.4 GB50
Astral 256K 7B250K / 14.4 GB50
Note: green Score (e.g. "73.2") means that the model is better than cognitivecomputations/dolphin-2.9.3-mistral-7B-32k.

Rank the Dolphin 2.9.3 Mistral 7B 32K 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? 52721 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