Zephyr DPO 4bit by BarraHome

 ยป  All LLMs  ยป  BarraHome  ยป  Zephyr DPO 4bit   URL Share it on

  4-bit   4bit   Autotrain compatible Base model:quantized:unsloth/z...   Base model:unsloth/zephyr-sft   Bitsandbytes   Conversational   En   Endpoints compatible   Mistral   Quantized   Region:us   Safetensors   Trl   Unsloth

Zephyr DPO 4bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Zephyr DPO 4bit (BarraHome/zephyr-dpo-4bit)

Zephyr DPO 4bit Parameters and Internals

Model Type 
text generation, transformers, mistral
Additional Notes 
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
LLM NameZephyr DPO 4bit
Repository ๐Ÿค—https://huggingface.co/BarraHome/zephyr-dpo-4bit 
Base Model(s)  Zephyr Sft   unsloth/zephyr-sft
Model Size3.9b
Required VRAM4.1 GB
Updated2024-12-22
MaintainerBarraHome
Model Typemistral
Model Files  4.1 GB
Supported Languagesen
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Quantized Models of the Zephyr DPO 4bit

Model
Likes
Downloads
VRAM
Zephyr DPO V2194114 GB

Best Alternatives to Zephyr DPO 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Zephyr Sft Bnb 4bit32K / 4.1 GB22674
Spydaz Web AI 026 4bit32K / 4.2 GB230
...cr To Json V1 Bnb 4bit Smashed32K / 4.5 GB330
Mixtral AI SwahiliTron 4BIT32K / 4.1 GB150
Mcqa 4bit32K / 4.1 GB150
Mistral 4bit Bnb32K / 4.1 GB140
Yugo55 GPT V4 4bit32K / 4.1 GB201
Rezephyr Merged 4bit32K / 4.1 GB840
...azWeb AI LCARS Model 001 4 BIT512K / 4.1 GB291
...Text AudioVision Project 4 BIT512K / 4.1 GB141
Note: green Score (e.g. "73.2") means that the model is better than BarraHome/zephyr-dpo-4bit.

Rank the Zephyr DPO 4bit 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? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217