Mistral Nemo MCAI SFT Revision Only by pbevan11

 ยป  All LLMs  ยป  pbevan11  ยป  Mistral Nemo MCAI SFT Revision Only   URL Share it on

  Alignment-handbook   Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mistral-n...   Conversational Dataset:pbevan11/multilingual-... Dataset:pbevan11/ultrafeedback...   Endpoints compatible   Generated from trainer   Mistral   Region:us   Safetensors   Sft   Sharded   Tensorboard   Tensorflow   Trl

Mistral Nemo MCAI SFT Revision Only Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mistral Nemo MCAI SFT Revision Only (pbevan11/Mistral-Nemo-MCAI-SFT-revision-only)

Mistral Nemo MCAI SFT Revision Only Parameters and Internals

Training Details 
Data Sources:
pbevan11/multilingual-constitutional-preference-pairs-revision-only, pbevan11/ultrafeedback_binarized_multilingual
Hardware Used:
multi-GPU, num_devices: 8
LLM NameMistral Nemo MCAI SFT Revision Only
Repository ๐Ÿค—https://huggingface.co/pbevan11/Mistral-Nemo-MCAI-SFT-revision-only 
Base Model(s)  Mistral Nemo Base 2407   mistralai/Mistral-Nemo-Base-2407
Model Size12.2b
Required VRAM24.5 GB
Updated2025-02-09
Maintainerpbevan11
Model Typemistral
Model Files  4.9 GB: 1-of-5   4.9 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   4.9 GB: 5-of-5   0.0 GB
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length1024000
Model Max Length1024000
Transformers Version4.45.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token</s>
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Mistral Nemo MCAI SFT Revision Only

Best Alternatives
Context / RAM
Downloads
Likes
Violet Twilight V0.21000K / 24.5 GB45898226
...ish Mistral Nemo Instruct 24071000K / 24.5 GB772
Educa Ai Nemo Sft1000K / 49.3 GB7653
Educa Ai Nemo DPO1000K / 49.3 GB532
Mistral Nemo Kurdish1000K / 24.5 GB473
Slush ChatWaifu Chronos1000K / 24.5 GB01
...al Nemo Japanese Instruct 24081000K / 24.5 GB444733
Crimson Dawn V0.21000K / 24.5 GB4813
Azure Dusk V0.21000K / 24.5 GB567
...istral Nemo Base 2407 Sft V2.11000K / 24.5 GB311
Note: green Score (e.g. "73.2") means that the model is better than pbevan11/Mistral-Nemo-MCAI-SFT-revision-only.

Rank the Mistral Nemo MCAI SFT Revision Only 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? 42847 in total.

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