Zephyr Smol Llama 100M DPO 1 Epoch by amazingvince

 ยป  All LLMs  ยป  amazingvince  ยป  Zephyr Smol Llama 100M DPO 1 Epoch   URL Share it on

  Autotrain compatible Base model:amazingvince/zephyr... Base model:finetune:amazingvin...   Conversational   Endpoints compatible   Generated from trainer   Llama   Region:us   Safetensors   Tensorboard

Zephyr Smol Llama 100M DPO 1 Epoch Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Zephyr Smol Llama 100M DPO 1 Epoch (amazingvince/zephyr-smol_llama-100m-dpo-1-epoch)

Zephyr Smol Llama 100M DPO 1 Epoch Parameters and Internals

LLM NameZephyr Smol Llama 100M DPO 1 Epoch
Repository ๐Ÿค—https://huggingface.co/amazingvince/zephyr-smol_llama-100m-dpo-1-epoch 
Base Model(s)  ...ephyr Smol Llama 100M Sft Full   amazingvince/zephyr-smol_llama-100m-sft-full
Model Size100m
Required VRAM0.2 GB
Updated2025-02-05
Maintaineramazingvince
Model Typellama
Model Files  0.2 GB   0.0 GB
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length1024
Model Max Length1024
Transformers Version4.35.0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32128
Torch Data Typebfloat16

Best Alternatives to Zephyr Smol Llama 100M DPO 1 Epoch

Best Alternatives
Context / RAM
Downloads
Likes
SmollerLM2 100M Instruct Sft8K / 0.3 GB520
SmollerLM2 100M8K / 0.2 GB410
Stockmark 100B4K / 191.9 GB16033
Saily 100b4K / 235.5 GB13527
Plankton 100M4K / 0.4 GB1580
...lisLM 100M Layer Hidden Pruned2K / 0.2 GB8200
Reglu 100B2K / 2.6 GB71
Llama 161M 100B1K / 0.3 GB4823
...ephyr Smol Llama 100M DPO Full1K / 0.2 GB113
...ephyr Smol Llama 100M DPO Full1K /  GB151
Note: green Score (e.g. "73.2") means that the model is better than amazingvince/zephyr-smol_llama-100m-dpo-1-epoch.

Rank the Zephyr Smol Llama 100M DPO 1 Epoch 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? 42577 in total.

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