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

Llama Phi 3 DoRA by Ba2han

 »  All LLMs  »  Ba2han  »  Llama Phi 3 DoRA   URL Share it on

  48   

Llama Phi 3 DoRA is an open-source language model by Ba2han. Features: 3.8b LLM, VRAM: 7.6GB, Context: 4K, License: mit, Instruction-Based, LLM Explorer Score: 0.22, Arc: 62.3, HellaSwag: 79.1, MMLU: 69.4, GSM8K: 68.

  Conversational Dataset:abacusai/systemchat-1....   Dataset:ba2han/dollyllama-5k Dataset:sao10k/claude-3-opus-i...   Deploy:azure   En   Endpoints compatible   Instruct   Mistral   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Ba2han/Llama-Phi-3_DoRA 

Llama Phi 3 DoRA Benchmarks

ARC: 62.29 vs 96.7 (so35)-35.6%
HellaSwag: 79.08 vs 95.3 (gpt4)-17%
MMLU: 69.44 vs 88.3 (so35)-21.4%
GSM8K: 68.01 vs 96.4 (so35)-29.5%
LLME Score: 0.21643
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama Phi 3 DoRA (Ba2han/Llama-Phi-3_DoRA)
🌟 Advertise your project 🚀

Llama Phi 3 DoRA Parameters and Internals

Model Type 
text-generation
Additional Notes 
We have Llama-3 at home! Use Zephyr template with any system message. Default system message should be: You are a smart, friendly and helpful assistant.
LLM NameLlama Phi 3 DoRA
Repository 🤗https://huggingface.co/Ba2han/Llama-Phi-3_DoRA 
Model Size3.8b
Required VRAM7.6 GB
Updated2026-04-28
MaintainerBa2han
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.6 GB: 2-of-2
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Llama Phi 3 DoRA

Best Alternatives
Context / RAM
Downloads
Likes
Phi 3 Mini 4K Instruct4K / 7.6 GB367445
Empty Phi 3 Mini4K / 7.6 GB50
...i3 Short Story Merged Bfloat164K / 7.6 GB181
...ling Assistant Spanish Pofi V24K / 7.7 GB50
Phi 3 Mini 4K Instruct Orpo V24K / 14.9 GB51
... Instruct Unsloth Merged 16bit4K / 7.6 GB162
...ent V56 3 W Unknown 5 Lr 0.0024K / 7.6 GB90
...Word Problems 200K Model 16bit4K / 7.6 GB38790
... 4K Instruct Matter 0.1 Slim A4K / 7.6 GB92
...rser User V9b Epoch 7 Lr 0.0024K / 7.6 GB50
Note: green Score (e.g. "73.2") means that the model is better than Ba2han/Llama-Phi-3_DoRA.

Rank the Llama Phi 3 DoRA 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