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

Llama 2 13B Chat Norwegian GPTQ by RuterNorway

 »  All LLMs  »  RuterNorway  »  Llama 2 13B Chat Norwegian GPTQ   URL Share it on

  38   
  4-bit   Autotrain compatible Dataset:nbailab/norwegian-alpa... Dataset:ruternorway/openorcano...   En   Gptq   Llama   Llama2   No   Norsk   Norwegian   Pytorch   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian-GPTQ 

Llama 2 13B Chat Norwegian GPTQ Benchmarks

LLME Score: 0.12424
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 13B Chat Norwegian GPTQ (RuterNorway/Llama-2-13b-chat-norwegian-GPTQ)

Llama 2 13B Chat Norwegian GPTQ Parameters and Internals

Model Type 
text generation, chat
Use Cases 
Areas:
commercial, research
Primary Use Cases:
assistant-like chat
Limitations:
This is an LLM, not a knowledge model, will generally perform better on tasks that involve summarization, question answering, and chat rather than tasks requiring more domain-specific knowledge, The data used for training is machine translated, and may contain grammatical errors and other errors
Considerations:
This model requires prompt tuning to achieve optimal results.
Additional Notes 
This is a 4-bit GPTQ model aimed to be less computationally intensive but with reduced accuracy compared to full models.
Supported Languages 
norwegian (native), english (secondary)
Training Details 
Data Sources:
NbAiLab/norwegian-alpaca, RuterNorway/OpenOrcaNo-15k
Data Volume:
15000 samples of machine-translated data + small custom-made instructional data
Methodology:
Finetuned on norwegian datasets
Training Time:
one epoch
Model Architecture:
GPTQ version of Llama 2 13b
Safety Evaluation 
Methodologies:
meta safeguards
Ethical Considerations:
Llama 2 is a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts.
Input Output 
Input Format:
Special prompt format for Llama2 Chat
Accepted Modalities:
text
Output Format:
Text generation output
Performance Tips:
Requires prompt tuning for better results.
LLM NameLlama 2 13B Chat Norwegian GPTQ
Repository 🤗https://huggingface.co/RuterNorway/Llama-2-13b-chat-norwegian-GPTQ 
Base Model(s)  Llama 2 13B Chat Norwegian   RuterNorway/Llama-2-13b-chat-norwegian
Model Size13b
Required VRAM7.3 GB
Updated2025-02-22
MaintainerRuterNorway
Model Typellama
Model Files  7.3 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Llama 2 13B Chat Norwegian GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Yarn Llama 2 13B 128K GPTQ128K / 7.3 GB3816
LongAlign 13B 64K GPTQ64K / 7.3 GB841
...boros L2 13B 2 1 YaRN 64K GPTQ64K / 7.3 GB183
Yarn Llama 2 13B 64K GPTQ64K / 7.3 GB421
OrcaMaid V3 13B 32K GPTQ32K / 7.3 GB333
OrcaMaid V2 FIX 13B 32K GPTQ32K / 7.3 GB244
EverythingLM 13B 16K GPTQ16K / 7.3 GB3913
Tinybra 13B GPTQ 32g 4BIT16K / 8 GB731
Tinybra 13B GPTQ 4BIT16K / 7 GB720
WhiteRabbitNeo 13B GPTQ16K / 7.3 GB754
Note: green Score (e.g. "73.2") means that the model is better than RuterNorway/Llama-2-13b-chat-norwegian-GPTQ.

Rank the Llama 2 13B Chat Norwegian GPTQ 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