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

Octocoder GGML by TheBloke

 »  All LLMs  »  TheBloke  »  Octocoder GGML   URL Share it on

  3   
  Arxiv:2308.07124   Base model:bigcode/octocoder Base model:finetune:bigcode/oc...   Code   Dataset:bigcode/commitpackft   Dataset:bigcode/oasst-octopack   Ggml   Model-index   Quantized   Region:us   Starcoder
Model Card on HF 🤗: https://huggingface.co/TheBloke/Octocoder-GGML 

Octocoder GGML Benchmarks

LLME Score: 0.10599
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Octocoder GGML (TheBloke/Octocoder-GGML)
🌟 Advertise your project 🚀

Octocoder GGML Parameters and Internals

Model Type 
text-generation
Additional Notes 
OctoCoder is an instruction tuned model created by fine-tuning StarCoder on CommitPackFT & OASST.
Supported Languages 
80+ Programming languages ()
Training Details 
Data Sources:
CommitPackFT, OASST
Data Volume:
1 trillion pretraining & 2M instruction tuning tokens
Methodology:
Instruction tuning
Training Time:
24 days pretraining, 4 hours instruction tuning
Hardware Used:
512 Tesla A100 GPUs for pretraining, 8 Tesla A100 GPUs for instruction tuning
Model Architecture:
GPT-2 model with multi-query attention and Fill-in-the-Middle objective
LLM NameOctocoder GGML
Repository 🤗https://huggingface.co/TheBloke/Octocoder-GGML 
Model CreatorBigCode
Base Model(s)  Octocoder   bigcode/octocoder
Required VRAM10.7 GB
Updated2025-08-22
MaintainerTheBloke
Model Typestarcoder
Model Files  10.7 GB   11.9 GB   13.1 GB   14.3 GB   20.1 GB
GGML QuantizationYes
Quantization Typeggml
Model ArchitectureAutoModel
Licensebigcode-openrail-m

Best Alternatives to Octocoder GGML

Best Alternatives
Context / RAM
Downloads
Likes
Athena V1 GGML0K / 5.5 GB21
MythoMax Kimiko Mix GGML0K / 5.7 GB23
...ax22b Instruct Falseblock GGML0K / 9.2 GB26
PULI GPT 3SX GGML0K / 3.9 GB35
NewHope GGML0K / 5.7 GB438
Spring Dragon GGML0K / 5.5 GB23
QCammel 13 GGML0K / 5.5 GB28
OpenChat V3.2 GGML0K / 5.7 GB314
QCammel 70 X GGML0K / 28.6 GB63
Replit Openorca GGML0K / 1.5 GB26
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Octocoder-GGML.

Rank the Octocoder GGML 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? 50835 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 v20241124
  Support LLM Explorer