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

Tess XS V1.3 Yarn 128K by migtissera

 »  All LLMs  »  migtissera  »  Tess XS V1.3 Yarn 128K   URL Share it on

  5834   
  Autotrain compatible   Custom code   Endpoints compatible   Mistral   Pytorch   Region:us   Yarn
Model Card on HF 🤗: https://huggingface.co/migtissera/Tess-XS-v1-3-yarn-128K 

Tess XS V1.3 Yarn 128K Benchmarks

ARC: 61.6 vs 96.7 (so35)-36.3%
HellaSwag: 82.96 vs 95.3 (gpt4)-12.9%
MMLU: 62.1 vs 88.3 (so35)-29.7%
TruthfulQA: 50.2 vs 59 (gpt4)-14.9%
WinoGrande: 74.74 vs 87.5 (gpt4)-14.6%
GSM8K: 43.37 vs 96.4 (so35)-55%
LLME Score: 0.19969
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Tess XS V1.3 Yarn 128K (migtissera/Tess-XS-v1-3-yarn-128K)

Tess XS V1.3 Yarn 128K Parameters and Internals

Model Type 
Large Language Model
Use Cases 
Limitations:
Slight repetition noticed around 16K context length.
Considerations:
Recommend testing the model for specific use cases and limiting context length.
Additional Notes 
This model has been tested on context length up to 16K.
Training Details 
Methodology:
General purpose language model trained on the Nous Research Mistral-7B-yarn-128K base.
Context Length:
16000
Input Output 
Input Format:
SYSTEM: USER: ASSISTANT:
Performance Tips:
Test the model to your use case and limit context length to improve performance.
Release Notes 
Version:
Tess-XS-v1.3
Notes:
Stable release. Issues from versions 1.0, 1.1, and 1.2 have been rectified.
LLM NameTess XS V1.3 Yarn 128K
Repository 🤗https://huggingface.co/migtissera/Tess-XS-v1-3-yarn-128K 
Required VRAM14.5 GB
Updated2025-02-22
Maintainermigtissera
Model Typemistral
Model Files  14.5 GB
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.35.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Tess XS V1.3 Yarn 128K

Best Alternatives
Context / RAM
Downloads
Likes
Krutrim 2 Instruct1000K / 49.3 GB98025
Ft V1 Violet1000K / 24.5 GB4580
Ft V1 Nemo Base1000K / 24.5 GB2120
Tiny Random MistralForCausalLM128K / 0 GB36991
Winterreise M732K / 14.4 GB00
Frostwind V2.1 M732K / 14.4 GB00
...ydaz Web AI Reasoner BaseModel32K / 14.4 GB01
MistralLite32K / 14.4 GB4078428
Snorkel Mistral PairRM DPO32K / 14.4 GB2120106
Mixtral AI Cyber Child32K / 14.5 GB141
Note: green Score (e.g. "73.2") means that the model is better than migtissera/Tess-XS-v1-3-yarn-128K.

Rank the Tess XS V1.3 Yarn 128K 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