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

RedPajama INCITE Instruct 3B V1 GGML by keldenl

 »  All LLMs  »  keldenl  »  RedPajama INCITE Instruct 3B V1 GGML   URL Share it on

  1   

RedPajama INCITE Instruct 3B V1 GGML is an open-source language model by keldenl. Features: 3b LLM, VRAM: 1.7GB, Context: 2K, License: apache-2.0, Quantized, Instruction-Based, HF Score: 39.2, LLM Explorer Score: 0.11, Arc: 42.6, HellaSwag: 67.5, MMLU: 26, TruthfulQA: 33.6, WinoGrande: 64.8, GSM8K: 0.9.

Dataset:muennighoff/natural-in...   Dataset:muennighoff/p3 Dataset:togethercomputer/redpa...   En   Endpoints compatible   Fp16   Ggml   Gpt neox   Instruct   Q4   Quantized   Red pajama   Region:us
Model Card on HF 🤗: https://huggingface.co/keldenl/RedPajama-INCITE-Instruct-3B-v1-GGML 

RedPajama INCITE Instruct 3B V1 GGML Benchmarks

ARC: 42.58 vs 96.7 (so35)-56%
HellaSwag: 67.48 vs 95.3 (gpt4)-29.2%
MMLU: 25.99 vs 88.3 (so35)-70.6%
TruthfulQA: 33.62 vs 59 (gpt4)-43%
WinoGrande: 64.8 vs 87.5 (gpt4)-25.9%
GSM8K: 0.91 vs 96.4 (so35)-99.1%
LLME Score: 0.11164
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
RedPajama INCITE Instruct 3B V1 GGML (keldenl/RedPajama-INCITE-Instruct-3B-v1-GGML)
🌟 Advertise your project 🚀

RedPajama INCITE Instruct 3B V1 GGML Parameters and Internals

Model Type 
Language Model
Additional Notes 
The model was fine-tuned for few-shot applications and does not work with llama.cpp as of 5/13/2023 but works with the GGML via gpt-neox.
Supported Languages 
en (proficient)
Input Output 
Input Format:
Instruction format + few shot prompting
LLM NameRedPajama INCITE Instruct 3B V1 GGML
Repository 🤗https://huggingface.co/keldenl/RedPajama-INCITE-Instruct-3B-v1-GGML 
Base Model(s)  ...ama INCITE Chat Instruct 3B V1   acrastt/RedPajama-INCITE-Chat-Instruct-3B-V1
Model Size3b
Required VRAM1.7 GB
Updated2026-03-04
Maintainerkeldenl
Model Typegpt_neox
Instruction-BasedYes
Model Files  1.7 GB   2.1 GB
Supported Languagesen
GGML QuantizationYes
Quantization Typefp16|ggml|q4
Model ArchitectureGPTNeoXForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.28.1
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50432
Torch Data Typefloat16

Best Alternatives to RedPajama INCITE Instruct 3B V1 GGML

Best Alternatives
Context / RAM
Downloads
Likes
...edPajama INCITE Instruct 3B V12K / 5.7 GB144593
Stablecode Instruct Alpha 3B4K / 6.1 GB17303
...blecode Instruct Alpha 3B GPTQ4K / 1.8 GB2317
...blecode Instruct Alpha 3B GPTQ4K / 1.8 GB51
...ama INCITE Chat Instruct 3B V12K / 5.5 GB8851
... Instruction Tuning With GPT 42K / 5.7 GB13323
Koishi Instruct 3B2K / 5.7 GB7833
Text2table2K / 5.7 GB84
Note: green Score (e.g. "73.2") means that the model is better than keldenl/RedPajama-INCITE-Instruct-3B-v1-GGML.

Rank the RedPajama INCITE Instruct 3B V1 GGML 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? 52758 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