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

Deepseek Math 7B Rl 4bit by sudhanshu746

 »  All LLMs  »  sudhanshu746  »  Deepseek Math 7B Rl 4bit   URL Share it on

  10   
  Arxiv:2402.03300   4-bit   4bit   Autotrain compatible   Endpoints compatible   Gptq   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/sudhanshu746/deepseek-math-7b-rl-4bit 

Deepseek Math 7B Rl 4bit Benchmarks

ARC: 55.46 vs 96.7 (so35)-42.6%
HellaSwag: 72.45 vs 95.3 (gpt4)-24%
MMLU: 56.81 vs 88.3 (so35)-35.7%
TruthfulQA: 40.37 vs 59 (gpt4)-31.6%
WinoGrande: 66.77 vs 87.5 (gpt4)-23.7%
GSM8K: 5.38 vs 96.4 (so35)-94.4%
LLME Score: 0.20377
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Deepseek Math 7B Rl 4bit (sudhanshu746/deepseek-math-7b-rl-4bit)

Deepseek Math 7B Rl 4bit Parameters and Internals

Model Type 
math solving, instruction following
Use Cases 
Areas:
research, commercial applications
Additional Notes 
Quantization made by Sudhanshu Sharma using bnb 4bits.
Input Output 
Input Format:
Chain-of-thought prompt
Accepted Modalities:
text
Output Format:
Text with step-by-step reasoning
Performance Tips:
Avoid using system prompts with this model version.
LLM NameDeepseek Math 7B Rl 4bit
Repository 🤗https://huggingface.co/sudhanshu746/deepseek-math-7b-rl-4bit 
Base Model(s)  Deepseek Math 7B Rl   deepseek-ai/deepseek-math-7b-rl
Model Size7b
Required VRAM4.8 GB
Updated2025-06-01
Maintainersudhanshu746
Model Typellama
Model Files  4.8 GB
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.41.1
Vocabulary Size102400
Torch Data Typefloat16

Best Alternatives to Deepseek Math 7B Rl 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Yarn Llama 2 7B 128K GPTQ128K / 3.9 GB437
Yarn Llama 2 7B 64K GPTQ64K / 3.9 GB301
... 7B 32K Instructions V4 Marlin32K / 4.1 GB80
Aixcoder 7B GPTQ32K / 4.5 GB121
Calm2 7B Chat GPTQ32K / 4.4 GB305
...Calm2 7B Chat GPTQ Calib Ja 1K32K / 4.4 GB245
Llama 2 7B 32K Instruct GPTQ32K / 3.9 GB6627
Codebear 7B 4bit16K / 3.9 GB121
CodeLlama 7B Instruct GPTQ16K / 3.9 GB189046
...a 7B Instruct GPTQ Calib Ja 1K16K / 3.9 GB130

Rank the Deepseek Math 7B Rl 4bit 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? 47770 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