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

Tor 8B by Delta-Vector

 »  All LLMs  »  Delta-Vector  »  Tor 8B   URL Share it on

  4   
Base model:finetune:nvidia/mis... Base model:nvidia/mistral-nemo...   Chat Dataset:anthracite-org/c2 logs... Dataset:anthracite-org/kalo-op... Dataset:anthracite-org/kalo mi... Dataset:anthracite-org/kalo op... Dataset:anthracite-org/nopm cl... Dataset:epiculous/synthrp-gens... Dataset:epiculous/synthstruct-... Dataset:lodrick-the-lafted/kal...   En   Instruct   Mistral   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Delta-Vector/Tor-8B 

Tor 8B Benchmarks

MMLU Pro: 30.33
GPQA: 9.84
MUSR: 8.82
BBH: 31.74
IFEval: 23.82 vs 88 (so35)-72.9%
MATH Lvl 5: 5.89
LLME Score: 0.22792
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Tor 8B (Delta-Vector/Tor-8B)
🌟 Advertise your project 🚀

Tor 8B Parameters and Internals

Model Type 
Text Generation
Additional Notes 
Inspired by Darkens-8B and further fine-tuned.
Training Details 
Data Sources:
PRIVATE CLAUDE LOG FILTER, anthracite-org/kalo-opus-instruct-22k-no-refusal, Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned, lodrick-the-lafted/kalo-opus-instruct-3k-filtered, anthracite-org/nopm_claude_writing_fixed, Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned, anthracite-org/kalo_opus_misc_240827, anthracite-org/kalo_misc_part2
Methodology:
Fine-tuning with ChatML formatting
Context Length:
16384
Hardware Used:
10 x Nvidia A40 GPUs
Input Output 
Input Format:
ChatML formatting
Performance Tips:
Use Sao10k's Euryale System prompt or 'Roleplay Simple' system prompt provided within SillyTavern.
LLM NameTor 8B
Repository 🤗https://huggingface.co/Delta-Vector/Tor-8B 
Base Model(s)  Mistral NeMo Minitron 8B Base   nvidia/Mistral-NeMo-Minitron-8B-Base
Model Size8b
Required VRAM16.8 GB
Updated2025-10-05
MaintainerDelta-Vector
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   2.0 GB: 4-of-4   0.0 GB   0.0 GB
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseagpl-3.0
Context Length16384
Model Max Length16384
Transformers Version4.45.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Tor 8B

Best Alternatives
Context / RAM
Downloads
Likes
Ministral 8B Instruct 2410 HF32K / 32 GB611
Ministrations 8B V132K / 16.1 GB2324
...l 8B Instruct 2410 Abliterated32K / 16.1 GB91
Ministral 8B Slerp32K / 29.2 GB70
DeepOpus 1 8B Preview32K / 16.1 GB752
DeepNeo 1 8B Preview32K / 16.1 GB632
Forgotten Safeword 8B V2.232K / 16.1 GB21
Bigger Body 8B32K / 16.1 GB47
Reflect Single Mini8B SftT1232K / 16.1 GB50
...ct Mini8B MistlrgOrcl460kSftT232K / 16.1 GB50
Note: green Score (e.g. "73.2") means that the model is better than Delta-Vector/Tor-8B.

Rank the Tor 8B 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? 51545 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 v20241124
  Support LLM Explorer