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

Llama3 Finetuned For Civivox by Adeptschneider

 »  All LLMs  »  Adeptschneider  »  Llama3 Finetuned For Civivox   URL Share it on

  8   

Llama3 Finetuned For Civivox is an open-source language model by Adeptschneider. Features: 3b LLM, VRAM: 6.5GB, Context: 128K, License: apache-2.0, Quantized, Fine-Tuned, LLM Explorer Score: 0.15.

  4bit   Endpoints compatible   Finetuned   Llama   Quantized   Region:us   Safetensors   Sft   Sharded   Sw   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/Adeptschneider/llama3-finetuned-for-civivox 

Llama3 Finetuned For Civivox Benchmarks

LLME Score: 0.14986
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama3 Finetuned For Civivox (Adeptschneider/llama3-finetuned-for-civivox)
🌟 Advertise your project 🚀

Llama3 Finetuned For Civivox Parameters and Internals

Model Type 
text-generation
Additional Notes 
This model is finetuned from the unsloth/llama-3.2-3b-bnb-4bit model and was developed with a focus on faster training times using the Unsloth and Huggingface's TRL library.
Training Details 
Methodology:
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
LLM NameLlama3 Finetuned For Civivox
Repository 🤗https://huggingface.co/Adeptschneider/llama3-finetuned-for-civivox 
Base Model(s)  unsloth/llama-3.2-3b-bnb-4bit   unsloth/llama-3.2-3b-bnb-4bit
Model Size3b
Required VRAM6.5 GB
Updated2026-06-08
MaintainerAdeptschneider
Model Typellama
Model Files  5.0 GB: 1-of-2   1.5 GB: 2-of-2
Supported Languagessw
Quantization Type4bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.46.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Llama3 Finetuned For Civivox

Best Alternatives
Context / RAM
Downloads
Likes
Nanbeige4.1 3B 8bit256K / 4.2 GB13814
Nanbeige4.1 3B Heretic 8bit256K / 4.2 GB452
Llama 3.2 3B Alpaca Id Sft128K / 6.5 GB4620
...gabl Legal Chatbot Llama3.2 3B128K / 6.5 GB3930
Llama32 Legal Id Sft128K / 6.5 GB1280
Llama3.2 3B Base Math128K / 6.5 GB5590
Llama 3.2 3B Legal SFT128K / 6.5 GB410
Llama3.2 3B INST Math1128K / 6.5 GB970
Llama3 2 3B Indonesian Sft128K / 2.2 GB190
Llama32 3B En Emo 2000 Stp128K / 2.2 GB91
Note: green Score (e.g. "73.2") means that the model is better than Adeptschneider/llama3-finetuned-for-civivox.

Rank the Llama3 Finetuned For Civivox 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? 54931 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