LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Llama 2 13B Instruct V0.2 by dfurman

 »  All LLMs  »  dfurman  »  Llama 2 13B Instruct V0.2   URL Share it on

  10   
  Arxiv:2307.09288   Adapter Base model:adapter:meta-llama/... Base model:meta-llama/llama-2-...   Conversational Dataset:garage-baind/open-plat... Dataset:jondurbin/airoboros-2....   Dataset:open-orca/slimorca   Finetuned   Instruct   Lora   Mistral   Model-index   Peft   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/dfurman/Llama-2-13B-Instruct-v0.2 

Llama 2 13B Instruct V0.2 Benchmarks

ARC: 60.58 vs 96.7 (so35)-37.4%
HellaSwag: 81.96 vs 95.3 (gpt4)-14%
MMLU: 55.46 vs 88.3 (so35)-37.2%
TruthfulQA: 45.71 vs 59 (gpt4)-22.5%
WinoGrande: 77.82 vs 87.5 (gpt4)-11.1%
GSM8K: 9.33 vs 96.4 (so35)-90.3%
LLME Score: 0.12291
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 13B Instruct V0.2 (dfurman/Llama-2-13B-Instruct-v0.2)
🌟 Advertise your project 🚀

Llama 2 13B Instruct V0.2 Parameters and Internals

Model Type 
Causal language model (clm)
Additional Notes 
Enhanced performance can be achieved by adjusting prompt formatting during use.
Supported Languages 
English (N/A)
Training Details 
Data Sources:
https://huggingface.co/datasets/jondurbin/airoboros-2.2.1, https://huggingface.co/datasets/Open-Orca/SlimOrca, https://huggingface.co/datasets/garage-bAInd/Open-Platypus
Data Volume:
First 20k rows from each dataset
Methodology:
Parameter-efficient finetuning
Training Time:
~8 hours on 1x A100 (40 GB SXM)
Hardware Used:
1x A100 (40 GB SXM)
Model Architecture:
Parameter-efficient finetuning
Input Output 
Input Format:
Supports chat template with alternating user/assistant roles
Accepted Modalities:
text
Output Format:
Text
Performance Tips:
Apply prompt formatting for improved results.
LLM NameLlama 2 13B Instruct V0.2
Repository 🤗https://huggingface.co/dfurman/Llama-2-13B-Instruct-v0.2 
Base Model(s)  Llama 2 13B Hf   meta-llama/Llama-2-13b-hf
Model Size13b
Required VRAM0.2 GB
Updated2025-09-21
Maintainerdfurman
Instruction-BasedYes
Model Files  0.4 GB   0.2 GB
Model ArchitectureAdapter
Licensellama2
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesk_proj|q_proj|o_proj|v_proj
LoRA Alpha16
LoRA Dropout0.1
R Param64

Best Alternatives to Llama 2 13B Instruct V0.2

Best Alternatives
Context / RAM
Downloads
Likes
...10 2024 06 23 06 24 24 35586350K / 0.8 GB50
...10 2024 06 22 21 11 23 35586240K / 0.8 GB50
Typescript Instruct 20K V40K / 26 GB52
Typescript Instruct 20K V20K / 26 GB62
... 13B Instruct Lora Jaster V1.00K / 0.1 GB52
...t Lora Jaster Dolly Oasst V1.00K / 0.1 GB81
...Instruct Lora Dolly Oasst V1.00K / 0.1 GB41
RuGPT 3.5 13B Lora0K / 0.1 GB712
...lama 13B Instruction Finetune20K / 0 GB61
Saiga2 13b Lora0K / 0.1 GB030
Note: green Score (e.g. "73.2") means that the model is better than dfurman/Llama-2-13B-Instruct-v0.2.

Rank the Llama 2 13B Instruct V0.2 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? 51507 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.
Release v20241124
  Support LLM Explorer