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

Galactica 6.7B Finetuned by OpenAssistant

 »  All LLMs  »  OpenAssistant  »  Galactica 6.7B Finetuned   URL Share it on

  2639   

Galactica 6.7B Finetuned is an open-source language model by OpenAssistant. Features: 6.7b LLM, VRAM: 27.4GB, Context: 2K, Fine-Tuned, HF Score: 38.8, LLM Explorer Score: 0.11, Arc: 41.6, HellaSwag: 51, MMLU: 38, TruthfulQA: 41.7, WinoGrande: 57.7, GSM8K: 3.1.

  Endpoints compatible   Finetuned   Opt   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/OpenAssistant/galactica-6.7b-finetuned 

Galactica 6.7B Finetuned Benchmarks

ARC: 41.55 vs 96.7 (so35)-57%
HellaSwag: 51.01 vs 95.3 (gpt4)-46.5%
MMLU: 38.03 vs 88.3 (so35)-56.9%
TruthfulQA: 41.65 vs 59 (gpt4)-29.4%
WinoGrande: 57.7 vs 87.5 (gpt4)-34.1%
GSM8K: 3.11 vs 96.4 (so35)-96.8%
LLME Score: 0.11224
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Galactica 6.7B Finetuned (OpenAssistant/galactica-6.7b-finetuned)
🌟 Advertise your project 🚀

Galactica 6.7B Finetuned Parameters and Internals

Model Type 
text generation
Additional Notes 
The model is a finetuned version on webgpt and prompt_dialogue datasets, employed for improved language understanding and dialogue framing tasks.
Input Output 
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Enable gradient checkpointing and load model using 8-bit precision for optimized performance with lower memory usage.
LLM NameGalactica 6.7B Finetuned
Repository 🤗https://huggingface.co/OpenAssistant/galactica-6.7b-finetuned 
Model Size6.7b
Required VRAM27.4 GB
Updated2026-04-10
MaintainerOpenAssistant
Model Typeopt
Model Files  10.0 GB: 1-of-3   9.9 GB: 2-of-3   7.5 GB: 3-of-3
Model ArchitectureOPTForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.25.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size50002
Torch Data Typefloat32
Activation Functiongelu

Best Alternatives to Galactica 6.7B Finetuned

Best Alternatives
Context / RAM
Downloads
Likes
....7B Qcqa Ub 16 Best For Q Loss2K / 27.4 GB5830
Galactica 6.7B ReFT GSM8k2K / 13.8 GB7150
...B Qcqa Ub 16 Best For KV Cache2K / 27.4 GB2550
...7B Gqa Ub 16 Best For KV Cache2K / 27.4 GB2280
Galactica 6.7B EssayWriter2K / 13.4 GB7565
Opt Flan Iml 6.7B2K / 26.6 GB9431
...lactica 6.7B Evol Instruct 70K2K / 27.4 GB42819
OPT 6.7B Nerybus Mix2K / 13.7 GB89820
Opt 6.7B2K / 13.4 GB30449118
OPT 6.7B Erebus2K / 13.3 GB209498
Note: green Score (e.g. "73.2") means that the model is better than OpenAssistant/galactica-6.7b-finetuned.

Rank the Galactica 6.7B Finetuned 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