Rezephyr DPO GGUF by BarraHome

 ยป  All LLMs  ยป  BarraHome  ยป  Rezephyr DPO GGUF   URL Share it on

  Merged Model   4bit Base model:barrahome/rezephyr ... Base model:quantized:barrahome...   Conversational Dataset:jondurbin/truthy-dpo-v...   En   Endpoints compatible   Gguf   Mistral   Quantized   Region:us   Unsloth

Rezephyr DPO GGUF Benchmarks

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

Rezephyr DPO GGUF Parameters and Internals

Model Type 
mistral, text-generation-inference, transformers, unsloth, gguf
Additional Notes 
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
Training Details 
Data Sources:
jondurbin/truthy-dpo-v0.1
LLM NameRezephyr DPO GGUF
Repository ๐Ÿค—https://huggingface.co/BarraHome/rezephyr-dpo-GGUF 
Base Model(s)  Rezephyr Merged 4bit   BarraHome/rezephyr_merged_4bit
Merged ModelYes
Required VRAM5.9 GB
Updated2024-12-22
MaintainerBarraHome
Model Typemistral
Model Files  5.9 GB
Supported Languagesen
GGUF QuantizationYes
Quantization Typegguf|4bit
Model ArchitectureAutoModel
Licenseapache-2.0

Best Alternatives to Rezephyr DPO GGUF

Best Alternatives
Context / RAM
Downloads
Likes
ComicBot V.2 Gguf32K / 5 GB140
Marco O1 GGUF0K / 3 GB238511
...ixtral 8x7B Instruct V0.1 GGUF0K / 15.6 GB65160606
Dolphin 2.5 Mixtral 8x7b GGUF0K / 15.6 GB16865299
Mixtral 8x7B V0.1 GGUF0K / 15.6 GB4903423
Dolphin 2.7 Mixtral 8x7b GGUF0K / 15.6 GB8066135
Phi 3 Mini 4K Instruct GGUF0K / 1.4 GB151716
Phi 2 GGUF0K / 1.2 GB3643192
GOAT Llama3.1 V0.10K / 0.2 GB143
Open Gpt4 8x7B GGUF0K / 15.6 GB1134018
Note: green Score (e.g. "73.2") means that the model is better than BarraHome/rezephyr-dpo-GGUF.

Rank the Rezephyr DPO GGUF 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? 40123 in total.

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