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

Llama 33B Instructed by Secbone

 »  All LLMs  »  Secbone  »  Llama 33B Instructed   URL Share it on

  873   
  Autotrain compatible   Endpoints compatible   F16   Fp16   Ggml   Gguf   Llama   Pytorch   Q5   Q5 1   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Secbone/llama-33B-instructed 

Llama 33B Instructed Benchmarks

ARC: 64.59 vs 96.7 (so35)-33.2%
HellaSwag: 86.17 vs 95.3 (gpt4)-9.6%
MMLU: 60.5 vs 88.3 (so35)-31.5%
TruthfulQA: 44.12 vs 59 (gpt4)-25.2%
WinoGrande: 79.32 vs 87.5 (gpt4)-9.3%
GSM8K: 14.4 vs 96.4 (so35)-85.1%
LLME Score: 0.1569
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 33B Instructed (Secbone/llama-33B-instructed)

Llama 33B Instructed Parameters and Internals

Model Type 
text generation, instruction-following
LLM NameLlama 33B Instructed
Repository 🤗https://huggingface.co/Secbone/llama-33B-instructed 
Model Size33b
Required VRAM65.2 GB
Updated2025-04-28
MaintainerSecbone
Model Typellama
Model Files  5.4 GB   5.4 GB   5.4 GB   5.4 GB   5.4 GB   5.4 GB   5.4 GB   5.4 GB   5.4 GB   5.4 GB   5.4 GB   5.4 GB   0.6 GB   5.4 GB   5.4 GB   5.4 GB   5.4 GB   2.9 GB   5.4 GB   5.4 GB   5.4 GB   5.4 GB   5.4 GB   5.4 GB   2.4 GB   9.8 GB: 1-of-7   10.0 GB: 2-of-7   9.9 GB: 3-of-7   9.9 GB: 4-of-7   9.9 GB: 5-of-7   10.0 GB: 6-of-7   5.7 GB: 7-of-7   9.8 GB: 1-of-7   10.0 GB: 2-of-7   9.9 GB: 3-of-7   9.9 GB: 4-of-7   9.9 GB: 5-of-7   10.0 GB: 6-of-7   5.7 GB: 7-of-7
GGML QuantizationYes
GGUF QuantizationYes
Quantization Typefp16|ggml|q5|q5_1|gguf|f16|q8_0
Model ArchitectureLlamaForCausalLM
Licensegpl-3.0
Context Length2048
Model Max Length2048
Transformers Version4.33.2
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Llama 33B Instructed

Best Alternatives
Context / RAM
Downloads
Likes
Vicuna 33B V1.3 GGUF2K / 34.6 GB110
Guanaco 33B 4bit2K / 16.9 GB510
...Interpreter DS 33B Hf 4bit Mlx16K / 19.1 GB27
...erpreter DS 33B 4.0bpw H6 EXL216K / 17.1 GB24
...rpreter DS 33B 4.65bpw H6 EXL216K / 19.8 GB22
...erpreter DS 33B 5.0bpw H6 EXL216K / 21.2 GB21
...erpreter DS 33B 6.0bpw H6 EXL216K / 25.3 GB21
...erpreter DS 33B 8.0bpw H8 EXL216K / 33.5 GB21
...se DeepSeek 33B 4.0bpw H6 EXL216K / 17.1 GB22
...e DeepSeek 33B 4.65bpw H6 EXL216K / 19.8 GB22
Note: green Score (e.g. "73.2") means that the model is better than Secbone/llama-33B-instructed.

Rank the Llama 33B Instructed 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? 46763 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