Codellama Extraction by mibruel

 ยป  All LLMs  ยป  mibruel  ยป  Codellama Extraction   URL Share it on

  4bit   Autotrain compatible Base model:finetune:unsloth/co... Base model:unsloth/codellama-3...   Codegen   En   Endpoints compatible   Llama   Quantized   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl   Unsloth

Codellama Extraction Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Codellama Extraction (mibruel/codellama_extraction)

Codellama Extraction Parameters and Internals

Model Type 
text-generation-inference, transformers, unsloth, trl, sft
Additional Notes 
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
LLM NameCodellama Extraction
Repository ๐Ÿค—https://huggingface.co/mibruel/codellama_extraction 
Base Model(s)  Codellama 34B Bnb 4bit   unsloth/codellama-34b-bnb-4bit
Model Size34b
Required VRAM67.6 GB
Updated2025-03-24
Maintainermibruel
Model Typellama
Model Files  5.0 GB: 1-of-14   4.9 GB: 2-of-14   4.8 GB: 3-of-14   4.9 GB: 4-of-14   4.8 GB: 5-of-14   4.9 GB: 6-of-14   4.8 GB: 7-of-14   4.9 GB: 8-of-14   4.8 GB: 9-of-14   4.9 GB: 10-of-14   4.8 GB: 11-of-14   4.9 GB: 12-of-14   4.8 GB: 13-of-14   4.4 GB: 14-of-14
Supported Languagesen
Quantization Type4bit
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length16384
Model Max Length16384
Transformers Version4.41.2
Tokenizer ClassCodeLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Codellama Extraction

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 34B Python Fp1616K / 67.5 GB350713
CodeLlama 34B Instruct Fp1616K / 67.5 GB34717
Phind Codellama 34B V2 EXL216K /  GB1516
Codellama 34B Bnb 4bit16K / 18.2 GB8554
CodeLlama 34B Instruct Hf 4bit16K / 19.4 GB152
CodeLlama 34B Fp1616K / 67.5 GB194
XwinCoder 34B 4.0bpw H6 EXL216K / 17.4 GB91
...Codellama 34B V2 Megacode EXL216K /  GB1610
...gpt 32K Codellama 34B Instruct32K / 67.5 GB982
CodeLlama 34B Instruct Hf16K / 67.5 GB18897283
Note: green Score (e.g. "73.2") means that the model is better than mibruel/codellama_extraction.

Rank the Codellama Extraction Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 45546 in total.

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