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

TinyDolphin 2.8 1.1B by cognitivecomputations

 »  All LLMs  »  cognitivecomputations  »  TinyDolphin 2.8 1.1B   URL Share it on

  6065   

TinyDolphin 2.8 1.1B is an open-source language model by cognitivecomputations. Features: 1.1b LLM, VRAM: 2.2GB, Context: 4K, License: apache-2.0, HF Score: 36.3, LLM Explorer Score: 0.19, Arc: 34.3, HellaSwag: 59.4, MMLU: 25.6, TruthfulQA: 36.5, WinoGrande: 60.7, GSM8K: 1.5.

  Autotrain compatible   Dataset:bigcode/starcoderdata Dataset:cerebras/slimpajama-62...   Dataset:teknium/openhermes   En   Endpoints compatible   Llama   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/cognitivecomputations/TinyDolphin-2.8-1.1b 

TinyDolphin 2.8 1.1B Benchmarks

ARC: 34.3 vs 96.7 (so35)-64.5%
HellaSwag: 59.44 vs 95.3 (gpt4)-37.6%
MMLU: 25.59 vs 88.3 (so35)-71%
TruthfulQA: 36.51 vs 59 (gpt4)-38.1%
WinoGrande: 60.69 vs 87.5 (gpt4)-30.6%
GSM8K: 1.52 vs 96.4 (so35)-98.4%
LLME Score: 0.19353
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
TinyDolphin 2.8 1.1B (cognitivecomputations/TinyDolphin-2.8-1.1b)
🌟 Advertise your project 🚀

TinyDolphin 2.8 1.1B Parameters and Internals

Model Type 
language model, text generation
Additional Notes 
Intended as a compact and efficient model within computational and memory constraints. It is based on optimizations of the Llama architecture for use in respective applications.
Supported Languages 
en (proficient)
Training Details 
Data Sources:
cerebras/SlimPajama-627B, bigcode/starcoderdata, teknium/openhermes, Dolphin 2.8 dataset by Eric Hartford
Data Volume:
3 trillion tokens
Methodology:
Pretrained using optimized techniques on Llama architecture and tokenizer
Training Time:
90 days
Hardware Used:
16 A100-40G GPUs
Model Architecture:
Same architecture and tokenizer as Llama 2. Compact with only 1.1B parameters.
LLM NameTinyDolphin 2.8 1.1B
Repository 🤗https://huggingface.co/cognitivecomputations/TinyDolphin-2.8-1.1b 
Model Size1.1b
Required VRAM2.2 GB
Updated2025-07-13
Maintainercognitivecomputations
Model Typellama
Model Files  2.2 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32002
Torch Data Typebfloat16

Best Alternatives to TinyDolphin 2.8 1.1B

Best Alternatives
Context / RAM
Downloads
Likes
TinyKiller NSFW DPO 1.1B32K / 2.2 GB120
Coven Tiny 1.1b 32k Orpo Alpha32K / 2.2 GB32
Test Mix 0132K / 2.2 GB50
Palmer Merge Test 532K / 2.2 GB50
...llama 1.1B 16K Instructions V432K / 2.2 GB80
TinyLlama 1.1B 32K32K / 2.2 GB20930
TinyLlama 1.1B 32K Instruct32K / 2.2 GB16913
TinyJ.O.S.I.E. 1.1B 32K Base32K / 2.2 GB301
Palmer 002 32K32K / 2.2 GB70
TinyJ.O.S.I.E. 1.1B 32K Base32K / 2.2 GB51
Note: green Score (e.g. "73.2") means that the model is better than cognitivecomputations/TinyDolphin-2.8-1.1b.

Rank the TinyDolphin 2.8 1.1B 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? 52392 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