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

Magicoder S CL 7B 5.0bpw H6 EXL2 2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Magicoder S CL 7B 5.0bpw H6 EXL2 2   URL Share it on

  13   
  Arxiv:2305.06161   Arxiv:2312.02120   Autotrain compatible Dataset:ise-uiuc/magicoder-evo... Dataset:ise-uiuc/magicoder-oss...   Endpoints compatible   Exl2   Instruct   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/LoneStriker/Magicoder-S-CL-7B-5.0bpw-h6-exl2-2 

Magicoder S CL 7B 5.0bpw H6 EXL2 2 Benchmarks

LLME Score: 0.14939
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Magicoder S CL 7B 5.0bpw H6 EXL2 2 (LoneStriker/Magicoder-S-CL-7B-5.0bpw-h6-exl2-2)

Magicoder S CL 7B 5.0bpw H6 EXL2 2 Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
coding tasks
Limitations:
Magicoders may not work well in non-coding tasks, May produce misleading contents or struggle with non-coding instructions
Considerations:
Users should be aware of the risks, biases, and limitations of the model.
Training Details 
Data Sources:
ise-uiuc/Magicoder-OSS-Instruct-75K, ise-uiuc/Magicoder-Evol-Instruct-110K
Methodology:
OSS-Instruct approach using open-source repositories for generating instruction data
Input Output 
Input Format:
Prompt-based input within MAGICODER_PROMPT template
Accepted Modalities:
text
Output Format:
Text
Performance Tips:
Ensure the transformer library is installed
LLM NameMagicoder S CL 7B 5.0bpw H6 EXL2 2
Repository 🤗https://huggingface.co/LoneStriker/Magicoder-S-CL-7B-5.0bpw-h6-exl2-2 
Model Size7b
Required VRAM4.4 GB
Updated2025-02-22
MaintainerLoneStriker
Model Typellama
Instruction-BasedYes
Model Files  4.4 GB
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.36.0.dev0
Tokenizer ClassCodeLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat32

Best Alternatives to Magicoder S CL 7B 5.0bpw H6 EXL2 2

Best Alternatives
Context / RAM
Downloads
Likes
...p 0.05 Max Grad1.0 Grad Accu3232K / 14.4 GB100
...p 0.05 Max Grad1.0 Grad Accu3232K / 14.4 GB50
...ruct Solidity Bnb 4bit Smashed16K / 4.2 GB800
...B Instruct Hf Bnb 4bit Smashed16K / 4.2 GB990
CodelLama7B Inst DPO 7K Mlx16K / 4.2 GB272
...eLlama 7B Instruct Hf 4bit MLX16K / 4.2 GB231
...6.7B Instruct 8.0bpw H8 EXL2 216K / 6.8 GB72
...6.7B Instruct 3.0bpw H6 EXL2 216K / 2.8 GB81
...coder S CL 7B 3.0bpw H6 EXL2 216K / 2.8 GB121
...coder S CL 7B 4.0bpw H6 EXL2 216K / 3.6 GB101
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Magicoder-S-CL-7B-5.0bpw-h6-exl2-2.

Rank the Magicoder S CL 7B 5.0bpw H6 EXL2 2 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? 43508 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