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

BigCodeLlama 169B by nisten

 »  All LLMs  »  nisten  »  BigCodeLlama 169B   URL Share it on

  82   
  Autotrain compatible Base model:codellama/codellama... Base model:finetune:codellama/...   Code   Codegen   Conversational   Endpoints compatible   Llama   Merge   Mergekit   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nisten/BigCodeLlama-169b 

BigCodeLlama 169B Benchmarks

LLME Score: 0.17612
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
BigCodeLlama 169B (nisten/BigCodeLlama-169b)

BigCodeLlama 169B Parameters and Internals

Model Type 
conversational
Additional Notes 
This is an experimental CodeLlaMA frankenstein model designed to explore benchmarking results.
Training Details 
Methodology:
The model is constructed using a passthrough merge method with bfloat16 data type. It integrates slices from various instances of the CodeLlama model series, specifically focusing on different layer ranges from different variants of CodeLlama.
LLM NameBigCodeLlama 169B
Repository 🤗https://huggingface.co/nisten/BigCodeLlama-169b 
Base Model(s)  CodeLlama 70B Hf   codellama/CodeLlama-70b-hf
Model Size70b
Required VRAM338.2 GB
Updated2024-12-22
Maintainernisten
Model Typellama
Model Files  9.8 GB: 1-of-35   9.8 GB: 2-of-35   9.8 GB: 3-of-35   9.6 GB: 4-of-35   9.8 GB: 5-of-35   9.8 GB: 6-of-35   10.0 GB: 7-of-35   10.0 GB: 8-of-35   9.9 GB: 9-of-35   9.8 GB: 10-of-35   10.0 GB: 11-of-35   9.8 GB: 12-of-35   9.8 GB: 13-of-35   10.0 GB: 14-of-35   9.8 GB: 15-of-35   9.8 GB: 16-of-35   10.0 GB: 17-of-35   9.9 GB: 18-of-35   9.8 GB: 19-of-35   9.8 GB: 20-of-35   10.0 GB: 21-of-35   9.8 GB: 22-of-35   9.9 GB: 23-of-35   9.6 GB: 24-of-35   9.6 GB: 25-of-35   10.0 GB: 26-of-35   9.8 GB: 27-of-35   10.0 GB: 28-of-35   9.7 GB: 29-of-35   9.8 GB: 30-of-35   9.8 GB: 31-of-35   9.9 GB: 32-of-35   9.8 GB: 33-of-35   9.7 GB: 34-of-35   3.8 GB: 35-of-35
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length16384
Model Max Length16384
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32016
Torch Data Typebfloat16

Best Alternatives to BigCodeLlama 169B

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 70B Hf16K / 77 GB663312
Sqlcoder 70B Alpha16K / 138.7 GB614219
CodeLlama 70B Hf16K / 77 GB8320
...enbuddy Codellama 70B V17.1 4K16K / 138.9 GB161
CodeLlama 70B Instruct Hf4K / 72.3 GB4291204
Code Llama 70B Python Instruct4K / 138.1 GB821
CodeLlama 70B Python Hf4K / 77 GB301107
CodeRosa 70B AB14K / 61.3 GB1261
CodeLlama 70B Instruct Hf4K / 72.3 GB28616
CodeLlama 70B Python Hf4K / 77 GB7411
Note: green Score (e.g. "73.2") means that the model is better than nisten/BigCodeLlama-169b.

Rank the BigCodeLlama 169B 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