OpenChat 3.5 7B Starling V2.0 by FuseAI

 ยป  All LLMs  ยป  FuseAI  ยป  OpenChat 3.5 7B Starling V2.0   URL Share it on

  Arxiv:2408.07990   Autotrain compatible Base model:finetune:openchat/o... Base model:openchat/openchat 3...   Conversational Dataset:fuseai/fusechat-mixtur...   En   Endpoints compatible   Fusechat   Mistral   Model-fusion   Model-index   Region:us   Safetensors   Sharded   Tensorflow

OpenChat 3.5 7B Starling V2.0 Benchmarks

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 7B Starling V2.0 (FuseAI/OpenChat-3.5-7B-Starling-v2.0)

OpenChat 3.5 7B Starling V2.0 Parameters and Internals

Model Type 
text generation, multi-turn conversation
Use Cases 
Areas:
research, commercial applications
Applications:
text generation, multi-turn conversation
Primary Use Cases:
chatbots, text-based simulations
Limitations:
not suitable for real-time applications without optimization, possible biases in generated content
Considerations:
consider context length and possible biases in outputs
Additional Notes 
The framework integrates knowledge from multiple chat LLMs without additional memory requirements for inference.
Supported Languages 
en (fluent)
Training Details 
Data Sources:
FuseAI/FuseChat-Mixture
Methodology:
fusion of six prominent chat LLMs via lightweight fine-tuning and VaRM method for merging.
Context Length:
2048
Input Output 
Input Format:
text prompts in GPT4 template format
Accepted Modalities:
text
Output Format:
text
Release Notes 
Version:
7B-v2.0
Date:
Aug 16, 2024
Notes:
Fusion of six prominent chat LLMs.
Version:
7B-VaRM
Date:
Feb 26, 2024
Notes:
Fusion of three prominent chat LLMs.
Version:
Mixture
Date:
Feb 25, 2024
Notes:
Release of training dataset covering different styles and capabilities.
LLM NameOpenChat 3.5 7B Starling V2.0
Repository ๐Ÿค—https://huggingface.co/FuseAI/OpenChat-3.5-7B-Starling-v2.0 
Base Model(s)  openchat/openchat_3.5   openchat/openchat_3.5
Model Size7b
Required VRAM14.4 GB
Updated2025-01-24
MaintainerFuseAI
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.38.0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32002
Torch Data Typebfloat16

Best Alternatives to OpenChat 3.5 7B Starling V2.0

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB446910
MegaBeam Mistral 7B 512K512K / 14.4 GB547149
SpydazWeb AI HumanAI RP512K / 14.4 GB201
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB484515
Hebrew Mistral 7B 200K256K / 30 GB277015
Astral 256K 7B250K / 14.4 GB120
Astral 256K 7B V2250K / 14.4 GB90
Test001128K / 14.5 GB90
Note: green Score (e.g. "73.2") means that the model is better than FuseAI/OpenChat-3.5-7B-Starling-v2.0.

Rank the OpenChat 3.5 7B Starling V2.0 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 41817 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227