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

Prem 1B by premai-io

 »  All LLMs  »  premai-io  »  Prem 1B   URL Share it on

  490   
  Merged Model   Autotrain compatible   Conversational Dataset:alexredna/oasst2 dpo p... Dataset:argilla/ultrafeedback-... Dataset:cerebras/slimpajama-62... Dataset:cognitivecomputations/...   Dataset:hkust-nlp/deita-10k-v0   Dataset:huggingfaceh4/capybara Dataset:huggingfaceh4/ultracha...   Dataset:intel/orca dpo pairs   Dataset:meta-math/metamathqa Dataset:open-orca/slimorca-ded...   Endpoints compatible   Instruct   Llama   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/premai-io/prem-1B 

Prem 1B Benchmarks

LLME Score: 0.18549
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Prem 1B (premai-io/prem-1B)

Prem 1B Parameters and Internals

Model Type 
Llama
Use Cases 
Areas:
commercial, research
Applications:
English language commercial and research applications, instruction-tuned conversational interactions
Primary Use Cases:
dialogue, natural language generation tasks
Considerations:
Users should be made aware of the risks, biases, and limitations of the model.
Supported Languages 
English (High proficiency)
Training Details 
Data Sources:
cerebras/SlimPajama-627B, HuggingFaceH4/ultrachat_200k, hkust-nlp/deita-10k-v0, Open-Orca/SlimOrca-Dedup, cognitivecomputations/WizardLM_evol_instruct_V2_196k_unfiltered_merged_split, HuggingFaceH4/capybara, meta-math/MetaMathQA, argilla/ultrafeedback-binarized-preferences-cleaned, Intel/orca_dpo_pairs, alexredna/oasst2_dpo_pairs
Methodology:
RAG (Retrieval-Augmented Generation)
Context Length:
8192
Training Time:
8500 hours
Hardware Used:
16 H100 GPUs
Model Architecture:
Based on Llama
Input Output 
Input Format:
Text with prompts structured for dialogue.
Accepted Modalities:
text
Output Format:
Generated text responses.
LLM NamePrem 1B
Repository 🤗https://huggingface.co/premai-io/prem-1B 
Merged ModelYes
Model Size1b
Required VRAM2.2 GB
Updated2025-02-05
Maintainerpremai-io
Model Typellama
Instruction-BasedYes
Model Files  2.2 GB
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.38.2
Tokenizer ClassLlamaTokenizer
Padding Token[PAD]
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Prem 1B

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 1B Instruct128K / 2.5 GB1522839738
MiniThinky V2 1B Llama 3.2128K / 4.9 GB1510037
Llama 3.2 1B Instruct128K / 2.5 GB13075860
Orca Mini V9 6 1B Instruct128K / 2.5 GB7514
Bellatrix Tiny 1B V2128K / 2.5 GB2158
Llama Express.1 Math128K / 2.5 GB907
...Templatizer Full End To End S1128K / 2.5 GB6870
...ama 1B Base GRPO MiniThinky V1128K / 2.5 GB1523
Bellatrix Tiny 1B R1128K / 2.5 GB547
Orca Mini V9 7 1B Instruct128K / 2.5 GB2084
Note: green Score (e.g. "73.2") means that the model is better than premai-io/prem-1B.

Rank the Prem 1B 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? 42625 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