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

LocutusqueXFelladrin TinyMistral248M Instruct by Locutusque

 »  All LLMs  »  Locutusque  »  LocutusqueXFelladrin TinyMistral248M Instruct   URL Share it on

  1950   
  Merged Model   Autotrain compatible Dataset:locutusque/inst mix v2...   En   Endpoints compatible   Instruct   Mistral   Pytorch   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Locutusque/LocutusqueXFelladrin-TinyMistral248M-Instruct 

LocutusqueXFelladrin TinyMistral248M Instruct Benchmarks

ARC: 24.74 vs 96.7 (so35)-74.4%
HellaSwag: 27.79 vs 95.3 (gpt4)-70.8%
MMLU: 26.12 vs 88.3 (so35)-70.4%
TruthfulQA: 40.12 vs 59 (gpt4)-32%
WinoGrande: 49.09 vs 87.5 (gpt4)-43.9%
LLME Score: 0.22312
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LocutusqueXFelladrin TinyMistral248M Instruct (Locutusque/LocutusqueXFelladrin-TinyMistral248M-Instruct)

LocutusqueXFelladrin TinyMistral248M Instruct Parameters and Internals

Model Type 
text generation
Additional Notes 
This model was created by merging Locutusque/TinyMistral-248M-Instruct and Felladrin/TinyMistral-248M-SFT-v4 using mergekit. After the two models were merged, the resulting model was further trained on ~20,000 examples on the Locutusque/inst_mix_v2_top_100k at a low learning rate to further normalize weights. The resulting model combines the best of both worlds: Locutusque/TinyMistral-248M-Instruct's coding capabilities and reasoning skills, and Felladrin/TinyMistral-248M-SFT-v4's low hallucination and instruction-following capabilities. The resulting model has an incredible performance considering its size.
LLM NameLocutusqueXFelladrin TinyMistral248M Instruct
Repository 🤗https://huggingface.co/Locutusque/LocutusqueXFelladrin-TinyMistral248M-Instruct 
Merged ModelYes
Model Size248m
Required VRAM0.5 GB
Updated2025-02-22
MaintainerLocutusque
Model Typemistral
Instruction-BasedYes
Model Files  0.5 GB
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.0
Tokenizer ClassLlamaTokenizer
Padding Token[PAD]
Vocabulary Size32005
Torch Data Typefloat16

Best Alternatives to LocutusqueXFelladrin TinyMistral248M Instruct

Best Alternatives
Context / RAM
Downloads
Likes
TinyMistral 248M V2.5 Instruct32K / 1 GB711
TinyMistral 248M Instruct32K / 1 GB3011
Tinymistv132K / 0.5 GB170
...istral 248M V2.5 Instruct Orpo32K / 0.5 GB680
...stral V2 Pycoder Instruct 248M32K / 1 GB1342
TinyMistral 248M V2 Instruct32K / 0.5 GB1327
...mistral 248M Hypnosis Instruct32K / 0.5 GB921
...al V2 Pycoder Instruct 248M V132K / 0.5 GB961
...istral Magicoder Instruct 248M32K / 0.5 GB52
Tinymistv132K / 0.5 GB00

Rank the LocutusqueXFelladrin TinyMistral248M Instruct 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