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

Deepseek Coder 33B Instruct 4.65bpw H6 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Deepseek Coder 33B Instruct 4.65bpw H6 EXL2   URL Share it on

  12   
  Autotrain compatible   Codegen   Conversational   Endpoints compatible   Exl2   Instruct   Llama   Pytorch   Quantized   Region:us   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LoneStriker/deepseek-coder-33b-instruct-4.65bpw-h6-exl2 

Deepseek Coder 33B Instruct 4.65bpw H6 EXL2 Benchmarks

LLME Score: 0.15522
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Deepseek Coder 33B Instruct 4.65bpw H6 EXL2 (LoneStriker/deepseek-coder-33b-instruct-4.65bpw-h6-exl2)

Deepseek Coder 33B Instruct 4.65bpw H6 EXL2 Parameters and Internals

Model Type 
code language model, text generation
Use Cases 
Areas:
research, commercial applications
Applications:
project-level code completion, code infilling, multilingual code tasks
Primary Use Cases:
code algorithm development, collaborative programming
Supported Languages 
English (full proficiency), Chinese (full proficiency)
Training Details 
Data Sources:
project-level code corpus
Data Volume:
2T tokens
Methodology:
fill-in-the-blank task
Context Length:
16000
Input Output 
Input Format:
Chat template with role and content
Accepted Modalities:
text
Output Format:
Generated code snippets
LLM NameDeepseek Coder 33B Instruct 4.65bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/deepseek-coder-33b-instruct-4.65bpw-h6-exl2 
Model Size33b
Required VRAM19.8 GB
Updated2024-12-27
MaintainerLoneStriker
Model Typellama
Instruction-BasedYes
Model Files  8.6 GB: 1-of-3   8.5 GB: 2-of-3   2.7 GB: 3-of-3
Quantization Typeexl2
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length16384
Model Max Length16384
Transformers Version4.33.1
Tokenizer ClassLlamaTokenizerFast
Beginning of Sentence Token<｜begin▁of▁sentence｜>
End of Sentence Token<｜end▁of▁sentence｜>
Vocabulary Size32256
Torch Data Typebfloat16

Best Alternatives to Deepseek Coder 33B Instruct 4.65bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...er 33B Instruct 4.0bpw H6 EXL216K / 17.1 GB115
...er 33B Instruct 3.0bpw H6 EXL216K / 13 GB211
...er 33B Instruct 8.0bpw H8 EXL216K / 33.6 GB113
...er 33B Instruct 5.0bpw H6 EXL216K / 21.2 GB161
Deepseek Wizard 33B Slerp16K / 35.3 GB180
Deepseek Coder 33B Instruct16K / 66.5 GB3774463
ValidateAI 3 33B Ties16K / 66.5 GB210
ValidateAI 2 33B AT16K / 66.5 GB230
...eepseek Coder 33B Instruct AWQ16K / 18.1 GB545834
...epseek Coder 33B Instruct GPTQ16K / 17.4 GB6326
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/deepseek-coder-33b-instruct-4.65bpw-h6-exl2.

Rank the Deepseek Coder 33B Instruct 4.65bpw H6 EXL2 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? 40304 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