ThoughtStream 4B V0.2 by trollek

 ยป  All LLMs  ยป  trollek  ยป  ThoughtStream 4B V0.2   URL Share it on

Base model:finetune:trollek/li... Base model:trollek/littleinstr... Dataset:skunkworksai/reasoning... Dataset:trollek/thoughtfulassi... Dataset:trollek/thoughtfulassi...   En   Llama   Region:us   Safetensors   Sharded   Tensorflow

ThoughtStream 4B V0.2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
ThoughtStream 4B V0.2 (trollek/ThoughtStream-4B-v0.2)
๐ŸŒŸ Advertise your project ๐Ÿš€

ThoughtStream 4B V0.2 Parameters and Internals

Additional Notes 
This model is most useful for experimentation like 'What happens if I substitute the thoughts?'
Supported Languages 
en (full)
Training Details 
Data Sources:
SkunkworksAI/reasoning-0.01, trollek/ThoughtfulAssistant-v01, trollek/ThoughtfulAssistant-v02
Input Output 
Accepted Modalities:
text
Performance Tips:
Inject the CoT in the thinking tags to improve reasoning.
LLM NameThoughtStream 4B V0.2
Repository ๐Ÿค—https://huggingface.co/trollek/ThoughtStream-4B-v0.2 
Base Model(s)  trollek/LittleInstructionMaker-4B-v0.2   trollek/LittleInstructionMaker-4B-v0.2
Model Size4b
Required VRAM7.9 GB
Updated2025-07-15
Maintainertrollek
Model Typellama
Model Files  5.0 GB: 1-of-2   2.9 GB: 2-of-2
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.43.4
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32004
Torch Data Typebfloat16

Best Alternatives to ThoughtStream 4B V0.2

Best Alternatives
Context / RAM
Downloads
Likes
4Bcpt256K / 8.8 GB170
HoldMy4BKTO256K / 8.8 GB250
Xgen Small 4B Base R256K / 17.7 GB892
Xgen Small 4B Instruct R256K / 17.7 GB183
SJT 4B146K / 7.6 GB50
Impish LLAMA 4B128K / 9 GB24128
...lama 3.1 Nemotron Nano 4B V1.1128K / 9 GB650094
...lama 3.1 Nemotron Nano 4B V1.1128K / 9 GB11604
Llama3.2 ColdBrew 4B Test128K / 7.2 GB380
Nemotron W 4b MagLight 0.1128K / 9.2 GB33
Note: green Score (e.g. "73.2") means that the model is better than trollek/ThoughtStream-4B-v0.2.

Rank the ThoughtStream 4B V0.2 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 49781 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124