Stable Vicuna 13B Delta by CarperAI

 ยป  All LLMs  ยป  CarperAI  ยป  Stable Vicuna 13B Delta   URL Share it on

Stable Vicuna 13B Delta is an open-source language model by CarperAI. Features: 13b LLM, VRAM: 26GB, Context: 2K, License: cc-by-nc-sa-4.0, LLM Explorer Score: 0.09.

  Arxiv:2302.13971   Autotrain compatible Dataset:nomic-ai/gpt4all promp...   Dataset:openassistant/oasst1   Dataset:tatsu-lab/alpaca   Doi:10.57967/hf/0588   En   Endpoints compatible   Llama   Pytorch   Region:us   Sharded

Stable Vicuna 13B Delta Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Stable Vicuna 13B Delta (CarperAI/stable-vicuna-13b-delta)
๐ŸŒŸ Advertise your project ๐Ÿš€

Stable Vicuna 13B Delta Parameters and Internals

Model Type 
causal-lm
Use Cases 
Areas:
text generation, conversational tasks
Primary Use Cases:
chatbot, instructional interactions
Limitations:
The base LLaMA model may contain offensive, harmful, and biased content., No studies have been done to evaluate how fine-tuning affects behavior and toxicity.
Considerations:
Do not treat chat responses as a substitute for human judgment or source of truth.
Additional Notes 
Requires applying delta weights to get the correct model configuration.
Supported Languages 
English (fully supported)
Training Details 
Data Sources:
OpenAssistant/oasst1, nomic-ai/gpt4all_prompt_generations, tatsu-lab/alpaca, Anthropic/hh-rlhf, stanfordnlp/SHP
Methodology:
Fine-tuned using reinforcement learning from human feedback (RLHF) via Proximal Policy Optimization (PPO).
Model Architecture:
Auto-regressive language model based on the LLaMA transformer architecture.
LLM NameStable Vicuna 13B Delta
Repository ๐Ÿค—https://huggingface.co/CarperAI/stable-vicuna-13b-delta 
Model Size13b
Required VRAM26 GB
Updated2025-11-14
MaintainerCarperAI
Model Typellama
Model Files  9.9 GB: 1-of-3   9.9 GB: 2-of-3   6.2 GB: 3-of-3
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-sa-4.0
Context Length2048
Model Max Length2048
Transformers Version4.28.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32001
Torch Data Typefloat16

Quantized Models of the Stable Vicuna 13B Delta

Model
Likes
Downloads
VRAM
Stable Vicuna 13B GGUF42245 GB

Best Alternatives to Stable Vicuna 13B Delta

Best Alternatives
Context / RAM
Downloads
Likes
Luminaura RP 13B128K / 26 GB50
Yarn Llama 2 13B 128K128K / 26 GB300112
Agent Llama2 13B 80K80K / 26.4 GB50
Chat Llama2 13B 80K80K / 52.8 GB50
LongAlign 13B 64K64K / 26 GB1713
LongAlign 13B 64K64K / 26 GB1113
LongAlign 13B 64K Base64K / 26 GB113
LongAlign 13B 64K Base64K / 26 GB63
Openbuddy Llama2 13B V15p1 64K64K / 26.1 GB64
Openbuddy Llama2 13b64k V1564K / 26.1 GB42
Note: green Score (e.g. "73.2") means that the model is better than CarperAI/stable-vicuna-13b-delta.

Rank the Stable Vicuna 13B Delta 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? 52509 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum โ€” our secure, self-hosted AI agent for server management.
Release v20260328a