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 V2 Lite Base AWQ by TechxGenus

 »  All LLMs  »  TechxGenus  »  DeepSeek Coder V2 Lite Base AWQ   URL Share it on

  14   
  Arxiv:2401.06066   4-bit   Autotrain compatible   Awq   Codegen   Conversational   Custom code   Deepseek v2   Endpoints compatible   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TechxGenus/DeepSeek-Coder-V2-Lite-Base-AWQ 

DeepSeek Coder V2 Lite Base AWQ Benchmarks

LLME Score: 0.19387
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
DeepSeek Coder V2 Lite Base AWQ (TechxGenus/DeepSeek-Coder-V2-Lite-Base-AWQ)

DeepSeek Coder V2 Lite Base AWQ Parameters and Internals

Model Type 
Code language model, Mixture-of-Experts (MoE)
Supported Languages 
total (; languages_proficiency:{)
Training Details 
Data Sources:
Multi-source high-quality corpus
Data Volume:
6 trillion tokens
Methodology:
Mixture-of-Experts (MoE) approach
Context Length:
128000
Hardware Used:
80GB*8 GPUs
Input Output 
Input Format:
Text input for code completion, chat completion.
Accepted Modalities:
text
Output Format:
Generated code or chat responses.
LLM NameDeepSeek Coder V2 Lite Base AWQ
Repository 🤗https://huggingface.co/TechxGenus/DeepSeek-Coder-V2-Lite-Base-AWQ 
Model Size2.6b
Required VRAM9.1 GB
Updated2025-02-22
MaintainerTechxGenus
Model Typedeepseek_v2
Model Files  5.0 GB: 1-of-2   4.1 GB: 2-of-2
AWQ QuantizationYes
Quantization Typeawq
Generates CodeYes
Model ArchitectureDeepseekV2ForCausalLM
Licenseother
Context Length163840
Model Max Length163840
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Padding Token<｜end▁of▁sentence｜>
Vocabulary Size102400
Torch Data Typefloat16

Best Alternatives to DeepSeek Coder V2 Lite Base AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...eek Coder V2 Lite Instruct AWQ160K / 9.1 GB5127
Note: green Score (e.g. "73.2") means that the model is better than TechxGenus/DeepSeek-Coder-V2-Lite-Base-AWQ.

Rank the DeepSeek Coder V2 Lite Base AWQ 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