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

Granite 8B Code Base 128K by ibm-granite

 »  All LLMs  »  ibm-granite  »  Granite 8B Code Base 128K   URL Share it on

  828   
  Arxiv:2405.04324   Autotrain compatible   Code   Dataset:bigcode/starcoderdata Dataset:codeparrot/github-code...   Dataset:math-ai/stackmathqa Dataset:open-web-math/open-web...   Granite   Llama   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ibm-granite/granite-8b-code-base-128k 

Granite 8B Code Base 128K Benchmarks

LLME Score: 0.2169
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Granite 8B Code Base 128K (ibm-granite/granite-8b-code-base-128k)

Granite 8B Code Base 128K Parameters and Internals

Model Type 
text generation, code-related tasks
Use Cases 
Areas:
enterprise software engineering productivity
Applications:
code generation, code explanation, code fixing, generating unit tests, generating documentation, addressing technical debt issues, vulnerability detection, code translation
Primary Use Cases:
support for 128K context length tasks
Limitations:
Generated code is not guaranteed to work as intended., Has not undergone any safety alignment, potential for problematic outputs., Potential increased susceptibility to hallucination in smaller models.
Considerations:
Urge ethical use and responsibly check outputs for accuracy and reliability.
Supported Languages 
language_proficiency (/** languages and their proficiency levels **/), proficiencies (Python, C, C++, Go, Java, JavaScript, TypeScript)
Training Details 
Data Sources:
codeparrot/github-code-clean, bigcode/starcoderdata, open-web-math/open-web-math, math-ai/StackMathQA
Data Volume:
4B tokens
Methodology:
Continual pretraining and repository-level file packing with per-language length upsampling.
Context Length:
128000
Hardware Used:
NVIDIA A100 GPUs, NVIDIA H100 GPUs
Model Architecture:
Progressively adjusted RoPE theta
Responsible Ai Considerations 
Mitigation Strategies:
Caution urged against complete reliance on generated code; not undergone any safety alignment, could produce problematic outputs.
Release Notes 
Date:
July 18th, 2024
LLM NameGranite 8B Code Base 128K
Repository 🤗https://huggingface.co/ibm-granite/granite-8b-code-base-128k 
Model Size8b
Required VRAM16.2 GB
Updated2025-02-22
Maintaineribm-granite
Model Typellama
Model Files  5.0 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   1.3 GB: 4-of-4
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length128000
Model Max Length128000
Transformers Version4.41.0
Tokenizer ClassGPT2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size49152
Torch Data Typebfloat16

Best Alternatives to Granite 8B Code Base 128K

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB3927680
MrRoboto ProLong 8B V4i1024K / 16.1 GB661
...o ProLongBASE Pt8 Unaligned 8B1024K / 16.1 GB240
MrRoboto BASE V2 Unholy 8B 64K1024K / 16.1 GB271
Mpasila Viking 8B1024K / 16.1 GB840
Thor V1.4 8B DARK FICTION1024K / 16.1 GB9412
41024K / 16.1 GB3220
Hel V2 8B DARK FICTION1024K / 16.1 GB220
161024K / 16.1 GB1690
...di95 LewdStorytellerMix 8B 64K1024K / 16.1 GB692
Note: green Score (e.g. "73.2") means that the model is better than ibm-granite/granite-8b-code-base-128k.

Rank the Granite 8B Code Base 128K 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? 43470 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