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

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit by Yhyu13

 »  All LLMs  »  Yhyu13  »  Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit   URL Share it on

  4   

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit is an open-source language model by Yhyu13. Features: 30b LLM, VRAM: 17.5GB, Context: 2K, License: apache-2.0, Quantized, HF Score: 60.7, LLM Explorer Score: 0.09, Arc: 61.4, HellaSwag: 83.8, MMLU: 57.9, TruthfulQA: 51.2, WinoGrande: 78.8, GSM8K: 31.5.

  4bit   Endpoints compatible   Gptq   Llama   Pytorch   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-gptq-4bit 

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit Benchmarks

ARC: 61.35 vs 96.7 (so35)-36.6%
HellaSwag: 83.8 vs 95.3 (gpt4)-12.1%
MMLU: 57.89 vs 88.3 (so35)-34.4%
TruthfulQA: 51.18 vs 59 (gpt4)-13.3%
WinoGrande: 78.77 vs 87.5 (gpt4)-10%
GSM8K: 31.46 vs 96.4 (so35)-67.4%
LLME Score: 0.09378
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit (Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-gptq-4bit)
🌟 Advertise your project 🚀

Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit Parameters and Internals

Model Type 
Text Generation
Additional Notes 
OA has implemented Reinforcement Learning from Human Feedback (RLHF) and observed a notable improvement in step-by-step thinking (similar to GPT-4 and ChatGPT) but it struggles with logical paradox tasks. It provides a professional tone in responses.
LLM NameOasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit
Repository 🤗https://huggingface.co/Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-gptq-4bit 
Base Model(s)  ...t Rlhf 2 Llama 30B 7K Steps Hf   Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-hf
Model Size30b
Required VRAM17.5 GB
Updated2026-04-03
MaintainerYhyu13
Model Typellama
Model Files  17.5 GB
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.28.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32006
Torch Data Typefloat16

Best Alternatives to Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit

Best Alternatives
Context / RAM
Downloads
Likes
GPlatty 30B SuperHOT 8K GPTQ8K / 16.9 GB187
... 30B Supercot SuperHOT 8K GPTQ8K / 16.9 GB85
Platypus 30B SuperHOT 8K GPTQ8K / 16.9 GB54
Tulu 30B SuperHOT 8K GPTQ8K / 16.9 GB35
Yayi2 30B Llama GPTQ4K / 17 GB72
WizardLM 30B GPTQ2K / 16.9 GB39518
Llama 30B FINAL MODEL MINI2K / 19.4 GB01
...2 Llama 30B 7K Steps Gptq 2bit2K / 9.5 GB82
...Assistant SFT 7 Llama 30B GPTQ2K / 16.9 GB77135
WizardLM 30B V1.0 GPTQ2K / 16.9 GB31
Note: green Score (e.g. "73.2") means that the model is better than Yhyu13/oasst-rlhf-2-llama-30b-7k-steps-gptq-4bit.

Rank the Oasst Rlhf 2 Llama 30B 7K Steps Gptq 4bit 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