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

Openchat 3.5 by openchat

 »  All LLMs  »  openchat  »  Openchat 3.5   URL Share it on

  39803   
  Arxiv:2303.08774   Arxiv:2309.11235   Autotrain compatible   C-rlft   Conversational Dataset:glaiveai/glaive-code-a...   Dataset:imone/openorca flan Dataset:ldjnr/lesswrong-amplif...   Dataset:ldjnr/pure-dove   Dataset:ldjnr/verified-camel   Dataset:meta-math/metamathqa Dataset:openassistant/oasst to... Dataset:openchat/openchat shar...   Dataset:tiedong/goat   Dataset:tiger-lab/mathinstruct   Endpoints compatible   Mistral   Openchat   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/openchat/openchat_3.5 

Openchat 3.5 Benchmarks

LMSys ELO: 1076 vs 1272 (so35)-15.4%
MMLU Pro: 23.93
GPQA: 6.49
MUSR: 11.26
BBH: 21.58
IFEval: 59.31 vs 88 (so35)-32.6%
ARC: 62.46 vs 96.7 (so35)-35.4%
HellaSwag: 83.96 vs 95.3 (gpt4)-11.9%
MMLU: 62.89 vs 88.3 (so35)-28.8%
TruthfulQA: 45.43 vs 59 (gpt4)-23%
WinoGrande: 81.06 vs 87.5 (gpt4)-7.4%
GSM8K: 25.78 vs 96.4 (so35)-73.3%
MATH Lvl 5: 7.25
LLME Score: 0.40793
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Openchat 3.5 (openchat/openchat_3.5)

Openchat 3.5 Parameters and Internals

Model Type 
text-generation
Additional Notes 
Despite advanced capabilities, OpenChat 3.5 may have limitations in complex reasoning, math, programming, hallucination of non-existent information, and safety issues.
Training Details 
Data Sources:
https://huggingface.co/datasets/openchat/openchat_sharegpt4_dataset, https://huggingface.co/datasets/imone/OpenOrca_FLAN, https://huggingface.co/datasets/LDJnr/Pure-Dove, https://huggingface.co/datasets/LDJnr/Verified-Camel, https://huggingface.co/datasets/LDJnr/LessWrong-Amplify-Instruct, https://huggingface.co/datasets/tiedong/goat, https://huggingface.co/datasets/glaiveai/glaive-code-assistant, https://huggingface.co/datasets/meta-math/MetaMathQA, https://huggingface.co/datasets/TIGER-Lab/MathInstruct, https://huggingface.co/datasets/OpenAssistant/oasst_top1_2023-08-25
Methodology:
C-RLFT - a strategy inspired by offline reinforcement learning
Context Length:
8192
Input Output 
Accepted Modalities:
text
LLM NameOpenchat 3.5
Repository 🤗https://huggingface.co/openchat/openchat_3.5 
Model Size7b
Required VRAM14.4 GB
Updated2025-02-22
Maintaineropenchat
Model Typemistral
Model Files  9.9 GB: 1-of-2   4.5 GB: 2-of-2
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32002
Torch Data Typebfloat16

Quantized Models of the Openchat 3.5

Model
Likes
Downloads
VRAM
Openchat 3.5 AWQ1487904 GB
Openchat 3.5 GGUF12721973 GB
OpenChat 3.5 GGUF31312 GB
Openchat 3.5 GPTQ16524 GB

Best Alternatives to Openchat 3.5

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB462011
MegaBeam Mistral 7B 512K512K / 14.4 GB568150
SpydazWeb AI HumanAI RP512K / 14.4 GB121
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB563316
Hebrew Mistral 7B 200K256K / 30 GB1461915
Astral 256K 7B V2250K / 14.4 GB70
Astral 256K 7B250K / 14.4 GB50
Test001128K / 14.5 GB90

Rank the Openchat 3.5 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? 43470 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