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

Starchat2 15B V0.1 by HuggingFaceH4

 »  All LLMs  »  HuggingFaceH4  »  Starchat2 15B V0.1   URL Share it on

  28578   
  Arxiv:2311.07911   Arxiv:2402.19173   Alignment-handbook   Autotrain compatible Base model:finetune:huggingfac... Base model:huggingfaceh4/starc...   Conversational Dataset:huggingfaceh4/orca dpo... Dataset:huggingfaceh4/ultrafee...   Endpoints compatible   Generated from trainer   Region:us   Safetensors   Sharded   Starcoder2   Tensorboard   Tensorflow
Model Card on HF 🤗: https://huggingface.co/HuggingFaceH4/starchat2-15b-v0.1 

Starchat2 15B V0.1 Benchmarks

LLME Score: 0.2613
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Starchat2 15B V0.1 (HuggingFaceH4/starchat2-15b-v0.1)

Starchat2 15B V0.1 Parameters and Internals

Model Type 
GPT-like
Use Cases 
Areas:
Chat, Programming
Limitations:
Can produce problematic outputs, Demographic bias due to GitHub community, Might suggest code with security flaws, May generate false URLs
Additional Notes 
Trained primarily as a coding assistant. Not aligned to human preferences or filtered like ChatGPT.
Supported Languages 
English (primary), Programming Languages (600+)
Training Details 
Data Sources:
HuggingFaceH4/ultrafeedback_binarized, HuggingFaceH4/orca_dpo_pairs
Methodology:
Fine-tuned using SFT and DPO
LLM NameStarchat2 15B V0.1
Repository 🤗https://huggingface.co/HuggingFaceH4/starchat2-15b-v0.1 
Base Model(s)  HuggingFaceH4/starchat2-15b-sft-v0.1   HuggingFaceH4/starchat2-15b-sft-v0.1
Model Size15b
Required VRAM31.9 GB
Updated2025-01-16
MaintainerHuggingFaceH4
Model Typestarcoder2
Model Files  4.9 GB: 1-of-7   5.0 GB: 2-of-7   5.0 GB: 3-of-7   5.0 GB: 4-of-7   5.0 GB: 5-of-7   5.0 GB: 6-of-7   2.0 GB: 7-of-7   0.0 GB
Model ArchitectureStarcoder2ForCausalLM
Context Length16384
Model Max Length16384
Transformers Version4.39.0.dev0
Tokenizer ClassGPT2Tokenizer
Padding Token<|im_end|>
Vocabulary Size49154
Torch Data Typebfloat16

Best Alternatives to Starchat2 15B V0.1

Best Alternatives
Context / RAM
Downloads
Likes
Starcoder2 15B16K / 63.8 GB26859579
Starcoder2 15B Instruct V0.116K / 31.9 GB568101
CodeFuse StarCoder2 15B16K / 31.9 GB222
Starcoder2 15B Finetuned Drake16K / 63.8 GB200
Dolphincoder Starcoder2 15B16K / 31.9 GB16869
Starcoder2 15B Instruct V0.116K / 53.4 GB140
...aceH4 Starchat2 15B V0.1 4bits16K / 9.9 GB90
Opencsg Starcoder2 15B V0.116K / 31.9 GB1632
Starchat2 15B Sft V0.116K / 31.9 GB175
Starcoder2 15B Instruct16K / 31.9 GB367
Note: green Score (e.g. "73.2") means that the model is better than HuggingFaceH4/starchat2-15b-v0.1.

Rank the Starchat2 15B V0.1 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? 41423 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