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

CataLlama V0.1 Instruct SFT by catallama

 »  All LLMs  »  catallama  »  CataLlama V0.1 Instruct SFT   URL Share it on

  5   
  Autotrain compatible Base model:catallama/catallama... Base model:finetune:catallama/...   Ca   Catalan   Conversational Dataset:catallama/catalan-inst...   En   Endpoints compatible   Instruct   Llama   Llama-3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/catallama/CataLlama-v0.1-Instruct-SFT 

CataLlama V0.1 Instruct SFT Benchmarks

LLME Score: 0.17234
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CataLlama V0.1 Instruct SFT (catallama/CataLlama-v0.1-Instruct-SFT)

CataLlama V0.1 Instruct SFT Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
commercial, research
Applications:
natural language generation
Primary Use Cases:
assistant-like chat, information extraction, named entity recognition, translation, summarization, sentiment analysis
Limitations:
Not intended to beat benchmarks, Out-of-scope use in any unlawful manner
Additional Notes 
The model includes stages of augmenting LLMs on new languages to help preserve rare languages.
Supported Languages 
ca (High level of proficiency), en (Moderate level of proficiency)
Training Details 
Data Sources:
catallama/Catalan-Instruct
Data Volume:
445 million new tokens
Methodology:
Supervised fine-tuning (SFT) and direct preference optimisation (DPO)
Hardware Used:
6x A100 80GB GPUs
Model Architecture:
Optimized transformer architecture
Input Output 
Input Format:
Same prompt template as Llama-3 Instruct
Accepted Modalities:
text
Output Format:
Generated text responses
LLM NameCataLlama V0.1 Instruct SFT
Repository 🤗https://huggingface.co/catallama/CataLlama-v0.1-Instruct-SFT 
Base Model(s)  catallama/CataLlama-v0.1-Base   catallama/CataLlama-v0.1-Base
Model Size8b
Required VRAM16.1 GB
Updated2025-04-27
Maintainercatallama
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   4.9 GB: 3-of-4   1.2 GB: 4-of-4   0.0 GB
Supported Languagesca en
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.38.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|pad|>
Vocabulary Size128257
Torch Data Typebfloat16

Best Alternatives to CataLlama V0.1 Instruct SFT

Best Alternatives
Context / RAM
Downloads
Likes
...otron 8B UltraLong 4M Instruct4192K / 32.1 GB4080102
UltraLong Thinking4192K / 16.1 GB692
...a 3.1 8B UltraLong 4M Instruct4192K / 32.1 GB17624
...otron 8B UltraLong 2M Instruct2096K / 32.1 GB126515
...a 3.1 8B UltraLong 2M Instruct2096K / 32.1 GB8759
...otron 8B UltraLong 1M Instruct1048K / 32.1 GB356740
...a 3.1 8B UltraLong 1M Instruct1048K / 32.1 GB138729
....1 1million Ctx Dark Planet 8B1048K / 32.3 GB142
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB26668679
A4.21024K / 16.1 GB1350
Note: green Score (e.g. "73.2") means that the model is better than catallama/CataLlama-v0.1-Instruct-SFT.

Rank the CataLlama V0.1 Instruct SFT 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? 46761 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