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

Jallabi 34B by AbacusResearch

 »  All LLMs  »  AbacusResearch  »  Jallabi 34B   URL Share it on

  990   
  Autotrain compatible   Conversational   Endpoints compatible   Llama   Llamaforcausallm   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/AbacusResearch/Jallabi-34B 

Jallabi 34B Benchmarks

MMLU Pro: 40.91
GPQA: 11.86
MUSR: 20.24
BBH: 43.62
IFEval: 35.29 vs 88 (so35)-59.9%
ARC: 66.04 vs 96.7 (so35)-31.7%
HellaSwag: 83.81 vs 95.3 (gpt4)-12.1%
MMLU: 76.4 vs 88.3 (so35)-13.5%
TruthfulQA: 51.46 vs 59 (gpt4)-12.8%
WinoGrande: 81.45 vs 87.5 (gpt4)-6.9%
GSM8K: 65.2 vs 96.4 (so35)-32.4%
MATH Lvl 5: 3.93
LLME Score: 0.27754
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Jallabi 34B (AbacusResearch/Jallabi-34B)

Jallabi 34B Parameters and Internals

Model Type 
text-generation
Additional Notes 
These are llama only weights from https://huggingface.co/liuhaotian/llava-v1.6-34b, with the CLIP encoder part removed.
LLM NameJallabi 34B
Repository 🤗https://huggingface.co/AbacusResearch/Jallabi-34B 
Model Size34b
Required VRAM137.2 GB
Updated2025-01-23
MaintainerAbacusResearch
Model Typellama
Model Files  9.0 GB: 1-of-16   8.9 GB: 2-of-16   8.9 GB: 3-of-16   8.9 GB: 4-of-16   8.9 GB: 5-of-16   8.9 GB: 6-of-16   8.9 GB: 7-of-16   8.9 GB: 8-of-16   8.9 GB: 9-of-16   8.9 GB: 10-of-16   8.9 GB: 11-of-16   8.9 GB: 12-of-16   8.9 GB: 13-of-16   8.9 GB: 14-of-16   8.9 GB: 15-of-16   3.6 GB: 16-of-16
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.38.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typefloat32

Best Alternatives to Jallabi 34B

Best Alternatives
Context / RAM
Downloads
Likes
Casual Magnum 34B195K / 68.8 GB21
34B Beta195K / 69.2 GB335762
Bagel Hermes 34B Slerp195K / 68.9 GB36251
Smaug 34B V0.1195K / 69.2 GB348960
Bagel 34B V0.2195K / 68.7 GB422140
Yi 34B 200K195K / 68.9 GB3607318
Yi 34B 200K AEZAKMI V2195K / 69.2 GB73712
Smaug 34B V0.1 ExPO195K / 69.2 GB28320
Faro Yi 34B195K / 69.2 GB34236
Bagel DPO 34B V0.5195K / 68.7 GB252617
Note: green Score (e.g. "73.2") means that the model is better than AbacusResearch/Jallabi-34B.

Rank the Jallabi 34B 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? 41774 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