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

Rwkv 4 7B Pile by RWKV

 »  All LLMs  »  RWKV  »  Rwkv 4 7B Pile   URL Share it on

  888   

Rwkv 4 7B Pile is an open-source language model by RWKV. Features: 7b LLM, VRAM: 30.4GB, HF Score: 38, LLM Explorer Score: 0.12, Arc: 39.7, HellaSwag: 66.3, MMLU: 25, TruthfulQA: 33.7, WinoGrande: 62.4, GSM8K: 0.8.

  Autotrain compatible   Dataset:eleutherai/pile   Endpoints compatible   Pytorch   Region:us   Rwkv   Sharded
Model Card on HF 🤗: https://huggingface.co/RWKV/rwkv-4-7b-pile 

Rwkv 4 7B Pile Benchmarks

ARC: 39.68 vs 96.7 (so35)-59%
HellaSwag: 66.31 vs 95.3 (gpt4)-30.4%
MMLU: 24.96 vs 88.3 (so35)-71.7%
TruthfulQA: 33.65 vs 59 (gpt4)-43%
WinoGrande: 62.35 vs 87.5 (gpt4)-28.7%
GSM8K: 0.76 vs 96.4 (so35)-99.2%
LLME Score: 0.1208
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Rwkv 4 7B Pile (RWKV/rwkv-4-7b-pile)
🌟 Advertise your project 🚀

Rwkv 4 7B Pile Parameters and Internals

Model Type 
RNN, transformer-level, LLM
Training Details 
Data Sources:
EleutherAI/pile
Model Architecture:
RWKV is an RNN with transformer-level performance. It combines features of RNN and transformer architectures.
LLM NameRwkv 4 7B Pile
Repository 🤗https://huggingface.co/RWKV/rwkv-4-7b-pile 
Model Size7b
Required VRAM30.4 GB
Updated2025-09-23
MaintainerRWKV
Model Typerwkv
Model Files  2.0 GB: 1-of-17   1.8 GB: 2-of-17   1.8 GB: 3-of-17   1.8 GB: 4-of-17   1.8 GB: 5-of-17   1.8 GB: 6-of-17   1.8 GB: 7-of-17   1.8 GB: 8-of-17   1.8 GB: 9-of-17   1.8 GB: 10-of-17   1.8 GB: 11-of-17   1.8 GB: 12-of-17   1.8 GB: 13-of-17   1.8 GB: 14-of-17   1.8 GB: 15-of-17   1.8 GB: 16-of-17   1.4 GB: 17-of-17
Model ArchitectureRwkvForCausalLM
Transformers Version4.29.0.dev0
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50277
Torch Data Typefloat32

Best Alternatives to Rwkv 4 7B Pile

Best Alternatives
Context / RAM
Downloads
Likes
V5 Eagle 7B HF0K / 15 GB432972
V5 EagleX V2 7B HF0K / 15 GB63314
V5 EagleX 7B0K / 15 GB112
Hermes RWKV V5 7B HF0K / 15 GB335
V5 Eagle 7B 1 0T HF0K / 15 GB61
Rwkv Raven 7B0K / 30.4 GB88219
Note: green Score (e.g. "73.2") means that the model is better than RWKV/rwkv-4-7b-pile.

Rank the Rwkv 4 7B Pile 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? 52721 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