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

Juanako 7B UNA by fblgit

 »  All LLMs  »  fblgit  »  Juanako 7B UNA   URL Share it on

  211   

Juanako 7B UNA is an open-source language model by fblgit. Features: 7b LLM, VRAM: 14.4GB, Context: 32K, License: apache-2.0, LLM Explorer Score: 0.18, Arc: 68.2, HellaSwag: 85.3, MMLU: 62.5, GSM8K: 44.8.

  Arxiv:2109.07958   Arxiv:2305.18290   Arxiv:2310.16944   Alignment-handbook   Conversational Dataset:huggingfaceh4/ultrafee...   Endpoints compatible   Generated from trainer   Juanako   Mistral   Model-index   Region:us   Safetensors   Sharded   Tensorflow   Una
Model Card on HF 🤗: https://huggingface.co/fblgit/juanako-7b-UNA 

Juanako 7B UNA Benchmarks

ARC: 68.17 vs 96.7 (so35)-29.5%
HellaSwag: 85.34 vs 95.3 (gpt4)-10.5%
MMLU: 62.47 vs 88.3 (so35)-29.3%
GSM8K: 44.81 vs 96.4 (so35)-53.5%
LLME Score: 0.1775
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Juanako 7B UNA (fblgit/juanako-7b-UNA)
🌟 Advertise your project 🚀

Juanako 7B UNA Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, commercial applications
Additional Notes 
Utilizes Uniform Neural Alignment for improved layer alignment.
Training Details 
Data Sources:
HuggingFaceH4/ultrafeedback_binarized
Methodology:
fine-tuning with Uniform Neural Alignment (UNA) technique
Hardware Used:
multi-GPU setup with 14 devices
Input Output 
Accepted Modalities:
text
Performance Tips:
Use provided prompt templates for optimal performance.
Release Notes 
Version:
latest
Notes:
Outperforms previous versions and other Mistral models.
LLM NameJuanako 7B UNA
Repository 🤗https://huggingface.co/fblgit/juanako-7b-UNA 
Model Size7b
Required VRAM14.4 GB
Updated2026-05-27
Maintainerfblgit
Model Typemistral
Model Files  4.9 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 Version4.35.0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the Juanako 7B UNA

Model
Likes
Downloads
VRAM
Juanako 7B UNA GGUF124383 GB
Juanako 7B UNA GPTQ2364 GB
Juanako 7B UNA AWQ274 GB

Best Alternatives to Juanako 7B UNA

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB25420
MegaBeam Mistral 7B 512K512K / 14.4 GB862354
SpydazWeb AI HumanAI RP512K / 14.4 GB241
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 GB818517
Hebrew Mistral 7B 200K256K / 30 GB137815
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 fblgit/juanako-7b-UNA.

Rank the Juanako 7B UNA 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? 53999 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