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

SmolLM Pretrained With Sft Trained With 1pc Data On A Preference DPO by SeppeV

 »  All LLMs  »  SeppeV  »  SmolLM Pretrained With Sft Trained With 1pc Data On A Preference DPO   URL Share it on

  6   
Base model:finetune:huggingfac... Base model:huggingfacetb/smoll...   Instruct   Llama   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/SeppeV/SmolLM_pretrained_with_sft_trained_with_1pc_data_on_a_preference_dpo 

SmolLM Pretrained With Sft Trained With 1pc Data On A Preference DPO Benchmarks

MMLU Pro: 1.79
GPQA: 1.23
MUSR: 8.4
BBH: 3.61
IFEval: 9.55 vs 88 (so35)-89.1%
MATH Lvl 5: 1.21
LLME Score: 0.23064
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SmolLM Pretrained With Sft Trained With 1pc Data On A Preference DPO (SeppeV/SmolLM_pretrained_with_sft_trained_with_1pc_data_on_a_preference_dpo)

SmolLM Pretrained With Sft Trained With 1pc Data On A Preference DPO Parameters and Internals

LLM NameSmolLM Pretrained With Sft Trained With 1pc Data On A Preference DPO
Repository 🤗https://huggingface.co/SeppeV/SmolLM_pretrained_with_sft_trained_with_1pc_data_on_a_preference_dpo 
Base Model(s)  SmolLM 135M Instruct   HuggingFaceTB/SmolLM-135M-Instruct
Model Size135m
Required VRAM0.3 GB
Updated2025-02-22
MaintainerSeppeV
Model Typellama
Instruction-BasedYes
Model Files  0.3 GB   0.0 GB
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.44.0
Tokenizer ClassGPT2Tokenizer
Padding Token<|im_end|>
Vocabulary Size49152
Torch Data Typebfloat16

Best Alternatives to SmolLM Pretrained With Sft Trained With 1pc Data On A Preference DPO

Best Alternatives
Context / RAM
Downloads
Likes
SmolLM2 135M Instruct8K / 0.3 GB163667139
SmolLM2 135M Grpo Gsm8k8K / 0.5 GB19511
Jaja Small V48K / 0.5 GB1420
Reasoning SmolLM2 135M8K / 0.5 GB24311
...wre324 R1 SmolLM2 135M Distill8K / 0.5 GB250
...molLM2 135M Instruct Reasoning8K / 0.3 GB70
SmolLM2 135M Instruct8K / 0.3 GB6622
Smollm 135M Full Fineweb Is8K / 0.5 GB210
Autotrain 0tmgq 5tpbg8K / 0.3 GB720
...molLM2 135M Instruct Reasoning8K / 0.3 GB300
Note: green Score (e.g. "73.2") means that the model is better than SeppeV/SmolLM_pretrained_with_sft_trained_with_1pc_data_on_a_preference_dpo.

Rank the SmolLM Pretrained With Sft Trained With 1pc Data On A Preference DPO 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? 43470 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