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

Reasoning Llama 3.2 1B Instruct V1.3 by EpistemeAI

 »  All LLMs  »  EpistemeAI  »  Reasoning Llama 3.2 1B Instruct V1.3   URL Share it on

  28   
  Autotrain compatible Base model:epistemeai/reasonin... Base model:finetune:epistemeai...   Conversational Dataset:open-thoughts/openthou...   En   Endpoints compatible   Instruct   Llama   Pytorch   Region:us   Safetensors   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/EpistemeAI/Reasoning-Llama-3.2-1B-Instruct-v1.3 

Reasoning Llama 3.2 1B Instruct V1.3 Benchmarks

MMLU Pro: 1.92
GPQA: 1.12
MUSR: 2.08
BBH: 6.11
IFEval: 32.73 vs 88 (so35)-62.8%
MATH Lvl 5: 5.06
LLME Score: 0.25033
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Reasoning Llama 3.2 1B Instruct V1.3 (EpistemeAI/Reasoning-Llama-3.2-1B-Instruct-v1.3)

Reasoning Llama 3.2 1B Instruct V1.3 Parameters and Internals

LLM NameReasoning Llama 3.2 1B Instruct V1.3
Repository 🤗https://huggingface.co/EpistemeAI/Reasoning-Llama-3.2-1B-Instruct-v1.3 
Base Model(s)  EpistemeAI/Reasoning-Llama-3.2-1B-Instruct-v1.2   EpistemeAI/Reasoning-Llama-3.2-1B-Instruct-v1.2
Model Size1b
Required VRAM2.5 GB
Updated2025-02-10
MaintainerEpistemeAI
Model Typellama
Instruction-BasedYes
Model Files  2.5 GB   2.5 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.47.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|finetune_right_pad_id|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Reasoning Llama 3.2 1B Instruct V1.3

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 1B Instruct128K / 2.5 GB2476583951
Llama 3.2 1B Instruct128K / 2.5 GB9255675
...enchmaxx Llama 3.2 1B Instruct128K / 0 GB423
Nano Imp 1B128K / 3 GB33512
BunderMaxx 1010128K / 2.5 GB141
Llasa 1B Multilingual128K / 3.5 GB163435
Lancer 1 1B Instruct128K / 2.5 GB1821
Llama 3.2 1b OrcaSun V1128K / 3 GB70
... 6 1B Instruct Abliterated LPL128K / 2.5 GB90
Llama 3.2 1b SunOrca V1128K / 3 GB140
Note: green Score (e.g. "73.2") means that the model is better than EpistemeAI/Reasoning-Llama-3.2-1B-Instruct-v1.3.

Rank the Reasoning Llama 3.2 1B Instruct V1.3 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? 47770 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 v20241227
  Support LLM Explorer