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

CodeLlama 13B Instruct AWQ by TheBloke

 »  All LLMs  »  TheBloke  »  CodeLlama 13B Instruct AWQ   URL Share it on

  63   
  Arxiv:2308.12950   4-bit   Autotrain compatible   Awq Base model:codellama/codellama... Base model:quantized:codellama...   Code   Codegen   Instruct   Llama   Llama2   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-AWQ 

CodeLlama 13B Instruct AWQ Benchmarks

LLME Score: 0.1409
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CodeLlama 13B Instruct AWQ (TheBloke/CodeLlama-13B-Instruct-AWQ)

CodeLlama 13B Instruct AWQ Parameters and Internals

Model Type 
llama
Use Cases 
Areas:
Commercial, Research
Applications:
General code synthesis and understanding, Python programming language specialization, Instruction following
Limitations:
Limited testing beyond English
Considerations:
Perform safety testing and tuning tailored to specific applications.
Additional Notes 
Model permits efficient low-bit quantization with AWQ method for faster performance and smaller hardware deployment.
Training Details 
Data Sources:
Evol Instruct Code
Methodology:
Pretrained and fine-tuned generative text model for code synthesis and understanding. Quantization supported (AWQ).
Hardware Used:
A100-80GB GPUs on Meta’s Research Super Cluster
Model Architecture:
Optimized transformer architecture using an auto-regressive language model.
Safety Evaluation 
Ethical Considerations:
Potential for inaccurate or objectionable responses; extensive testing recommended before deployment.
Responsible Ai Considerations 
Mitigation Strategies:
Following Responsible Use Guide available at https://ai.meta.com/llama/responsible-user-guide
LLM NameCodeLlama 13B Instruct AWQ
Repository 🤗https://huggingface.co/TheBloke/CodeLlama-13B-Instruct-AWQ 
Model NameCodeLlama 13B Instruct
Model CreatorMeta
Base Model(s)  CodeLlama 13B Instruct Hf   codellama/CodeLlama-13b-Instruct-hf
Model Size13b
Required VRAM7.2 GB
Updated2024-12-22
MaintainerTheBloke
Model Typellama
Instruction-BasedYes
Model Files  7.2 GB
Supported Languagescode
AWQ QuantizationYes
Quantization Typeawq
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length16384
Model Max Length16384
Transformers Version4.32.0.dev0
Tokenizer ClassCodeLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32016
Torch Data Typebfloat16

Best Alternatives to CodeLlama 13B Instruct AWQ

Best Alternatives
Context / RAM
Downloads
Likes
NexusRaven 13B AWQ16K / 7.2 GB354
...ma 13B Instruct Hf W4 G128 AWQ16K / 7.2 GB330
CodeLlama 13B Instruct Fp1616K / 26 GB200629
...Llama 13B Instruct Hf 4bit MLX16K / 7.8 GB752
...13B Instruct Nf4 Fp16 Upscaled16K / 26 GB4460
CodeLlama 13B MORepair16K / 26 GB26502
NexusRaven V2 13B16K / 26 GB3919465
CodeLlama 13B Instruct Hf16K / 26 GB16223144
CodeLlama 13B Instruct Hf16K / 26 GB99318
TableLLM 13B16K / 26 GB23525
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/CodeLlama-13B-Instruct-AWQ.

Rank the CodeLlama 13B Instruct 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? 40066 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 v20241217
  Support LLM Explorer