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

Llama2 13B Orca 8K 3319 by OpenAssistant

 »  All LLMs  »  OpenAssistant  »  Llama2 13B Orca 8K 3319   URL Share it on

  2069   
  Arxiv:2306.02707   Autotrain compatible Dataset:atom-in-the-universe/f...   Dataset:ehartford/dolphin   Dataset:shahules786/orca-chat Dataset:togethercomputer/redpa...   En   Endpoints compatible   Ext 8k   Llama   Pytorch   Region:us   Sft   Sharded
Model Card on HF 🤗: https://huggingface.co/OpenAssistant/llama2-13b-orca-8k-3319 

Llama2 13B Orca 8K 3319 Benchmarks

ARC: 60.75 vs 96.7 (so35)-37.2%
HellaSwag: 81.91 vs 95.3 (gpt4)-14.1%
MMLU: 57.06 vs 88.3 (so35)-35.4%
TruthfulQA: 42.64 vs 59 (gpt4)-27.7%
WinoGrande: 77.19 vs 87.5 (gpt4)-11.8%
GSM8K: 10.99 vs 96.4 (so35)-88.6%
LLME Score: 0.16922
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama2 13B Orca 8K 3319 (OpenAssistant/llama2-13b-orca-8k-3319)

Llama2 13B Orca 8K 3319 Parameters and Internals

Model Type 
text-generation
Training Details 
Data Sources:
shahules786/orca-chat, ehartford/dolphin, togethercomputer/RedPajama-Data-1T, atom-in-the-universe/fanfics-10k-50k
Methodology:
Fine-tuned on long-conversation variant of the Dolphin dataset using a context size of 8192 tokens with linear scaling of RoPE embeddings.
Context Length:
8192
LLM NameLlama2 13B Orca 8K 3319
Repository 🤗https://huggingface.co/OpenAssistant/llama2-13b-orca-8k-3319 
Model Size13b
Required VRAM26.1 GB
Updated2025-03-14
MaintainerOpenAssistant
Model Typellama
Model Files  4.3 GB: 1-of-7   4.3 GB: 2-of-7   4.2 GB: 3-of-7   4.2 GB: 4-of-7   4.3 GB: 5-of-7   4.2 GB: 6-of-7   0.6 GB: 7-of-7
Supported Languagesen
Context Length8k
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.31.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32016
Torch Data Typefloat16

Quantized Models of the Llama2 13B Orca 8K 3319

Model
Likes
Downloads
VRAM
...t Llama2 13B Orca 8K 3319 GGUF87865 GB
...nt Llama2 13B Orca 8K 3319 AWQ1917 GB
...t Llama2 13B Orca 8K 3319 GPTQ382417 GB
...t Llama2 13B Orca 8K 3319 GGML53445 GB

Best Alternatives to Llama2 13B Orca 8K 3319

Best Alternatives
Context / RAM
Downloads
Likes
Luminaura RP 13B128K / 26 GB160
Yarn Llama 2 13B 128K128K / 26 GB2395112
Agent Llama2 13B 80K80K / 26.4 GB130
Chat Llama2 13B 80K80K / 52.8 GB100
LongAlign 13B 64K64K / 26 GB4213
LongAlign 13B 64K Base64K / 26 GB323
Yarn Llama 2 13B 64K64K / 26 GB532917
Openbuddy Llama2 13B V15p1 64K64K / 26.1 GB194
Openbuddy Llama2 13b64k V1564K / 26.1 GB141
Airoboros L2 13B 2.1 YaRN 64K64K / 26 GB397
Note: green Score (e.g. "73.2") means that the model is better than OpenAssistant/llama2-13b-orca-8k-3319.

Rank the Llama2 13B Orca 8K 3319 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? 45019 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