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

Yi Bagel 2x34b by NLPinas

 »  All LLMs  »  NLPinas  »  Yi Bagel 2x34b   URL Share it on

  97   

Yi Bagel 2x34b is an open-source language model by NLPinas. Features: 34.4b LLM, VRAM: 68.8GB, Context: 195K, License: other, MoE, Merged, HF Score: 74.9, LLM Explorer Score: 0.12, Arc: 72.7, HellaSwag: 85.4, MMLU: 76.6, TruthfulQA: 71.4, WinoGrande: 82.7, GSM8K: 60.7.

  Merged Model   Arxiv:1803.05457   Arxiv:1905.07830   Arxiv:1907.10641   Arxiv:2009.03300   Arxiv:2109.07958   Arxiv:2110.14168   Arxiv:2203.05482 Base model:jondurbin/bagel-dpo... Base model:jondurbin/nontoxic-...   Conversational   Endpoints compatible   Llama   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/NLPinas/yi-bagel-2x34b 

Yi Bagel 2x34b Benchmarks

ARC: 72.7 vs 96.7 (so35)-24.8%
HellaSwag: 85.44 vs 95.3 (gpt4)-10.3%
MMLU: 76.6 vs 88.3 (so35)-13.3%
TruthfulQA: 71.42 vs 59 (gpt4)21.1%
WinoGrande: 82.72 vs 87.5 (gpt4)-5.5%
GSM8K: 60.73 vs 96.4 (so35)-37%
LLME Score: 0.12116
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Yi Bagel 2x34b (NLPinas/yi-bagel-2x34b)
🌟 Advertise your project 🚀

Yi Bagel 2x34b Parameters and Internals

Release Notes 
Version:
N/A
Date:
January 11, 2024
Notes:
Released as a merge of pre-trained language models using Mergekit, achieving a rank of #4 on the Open LLM Leaderboard at release.
LLM NameYi Bagel 2x34b
Repository 🤗https://huggingface.co/NLPinas/yi-bagel-2x34b 
Base Model(s)  jondurbin/bagel-dpo-34b-v0.2   jondurbin/nontoxic-bagel-34b-v0.2   jondurbin/bagel-dpo-34b-v0.2   jondurbin/nontoxic-bagel-34b-v0.2
Merged ModelYes
Model Size34.4b
Required VRAM68.8 GB
Updated2026-04-09
MaintainerNLPinas
Model Typellama
Model Files  9.8 GB: 1-of-7   9.8 GB: 2-of-7   9.8 GB: 3-of-7   10.0 GB: 4-of-7   9.8 GB: 5-of-7   9.8 GB: 6-of-7   9.8 GB: 7-of-7
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length200000
Model Max Length200000
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typefloat16

Best Alternatives to Yi Bagel 2x34b

Best Alternatives
Context / RAM
Downloads
Likes
Pallas 0.5 LASER 0.4195K / 68.9 GB18691
Pallas 0.5 LASER 0.5195K / 68.9 GB7360
Pallas 0.5 LASER 0.3195K / 68.9 GB7850
Pallas 0.5 LASER 0.2195K / 68.9 GB7560
Pallas 0.5 LASER 0.6195K / 68.9 GB85
Pallas 0.5 LASER Exp2 0.1195K / 68.9 GB70
AnFeng V3.1 Avocet128K / 69.2 GB17070
UNA 34Beagles 32K Bf16 V132K / 69.2 GB86910
UNA 34BeagleSimpleMath 32K V132K / 69.2 GB1016
PiVoT SUS RP8K / 69.2 GB17445
Note: green Score (e.g. "73.2") means that the model is better than NLPinas/yi-bagel-2x34b.

Rank the Yi Bagel 2x34b 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