Magicoder S DS 6.7B GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Magicoder S DS 6.7B GPTQ   URL Share it on

  Arxiv:2305.06161   Arxiv:2312.02120   4-bit   Autotrain compatible Base model:ise-uiuc/magicoder-... Base model:quantized:ise-uiuc/... Dataset:ise-uiuc/magicoder-evo... Dataset:ise-uiuc/magicoder-oss...   Gptq   Instruct   Llama   Quantized   Region:us   Safetensors

Magicoder S DS 6.7B GPTQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Magicoder S DS 6.7B GPTQ (TheBloke/Magicoder-S-DS-6.7B-GPTQ)

Magicoder S DS 6.7B GPTQ Parameters and Internals

Model Type 
deepseek, text-generation
Use Cases 
Areas:
coding tasks
Limitations:
may not work well in non-coding tasks
Considerations:
Users should be aware of the model's risks, biases, and limitations.
Training Details 
Data Sources:
Magicoder-OSS-Instruct-75K, Magicoder-Evol-Instruct-110K
Methodology:
Finetuned from deepseek-coder-6.7b-base
Responsible Ai Considerations 
Fairness:
OSS-Instruct mitigates inherent bias of the LLM-synthesized instruction data.
Input Output 
Input Format:
Prompt_Template: 'You are an exceptionally intelligent coding assistant... @@Instruction {prompt} @@Response'
LLM NameMagicoder S DS 6.7B GPTQ
Repository 🤗https://huggingface.co/TheBloke/Magicoder-S-DS-6.7B-GPTQ 
Model NameMagicoder S DS 6.7B
Model CreatorIntellligent Software Engineering (iSE
Base Model(s)  ise-uiuc/Magicoder-S-DS-6.7B   ise-uiuc/Magicoder-S-DS-6.7B
Model Size6.7b
Required VRAM3.9 GB
Updated2025-03-14
MaintainerTheBloke
Model Typedeepseek
Instruction-BasedYes
Model Files  3.9 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length16384
Model Max Length16384
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Padding Token<|end▁of▁sentence|>
Vocabulary Size32256
Torch Data Typefloat16

Best Alternatives to Magicoder S DS 6.7B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...pseek Coder 6.7B Instruct GPTQ16K / 3.9 GB49324
...LI LlumiX 32K Instruct F16 0.232K / 13.5 GB351
...LI LlumiX 32K Instruct F16 0.132K / 13.5 GB180
...rpreter DS 6.7B 8.0bpw H8 EXL216K / 6.9 GB202
...rpreter DS 6.7B 6.0bpw H6 EXL216K / 5.2 GB162
...rpreter DS 6.7B 4.0bpw H6 EXL216K / 3.6 GB151
...coder S DS 6.7B 4.0bpw H6 EXL216K / 3.6 GB155
...coder S DS 6.7B 3.0bpw H6 EXL216K / 2.8 GB123
...coder S DS 6.7B 6.0bpw H6 EXL216K / 5.2 GB123
...coder S DS 6.7B 5.0bpw H6 EXL216K / 4.4 GB152
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Magicoder-S-DS-6.7B-GPTQ.

Rank the Magicoder S DS 6.7B GPTQ 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.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227