Granite 8B Code Instruct by ibm-granite

 ยป  All LLMs  ยป  ibm-granite  ยป  Granite 8B Code Instruct   URL Share it on

  Arxiv:2405.04324   Autotrain compatible Base model:ibm-granite/granite...   Code   Conversational   Dataset:bigcode/commitpackft Dataset:bugdaryan/sql-create-c... Dataset:garage-baind/open-plat... Dataset:glaive-function-callin... Dataset:glaiveai/glaive-code-a...   Dataset:meta-math/metamathqa   Dataset:nvidia/helpsteer   Dataset:tiger-lab/mathinstruct   Granite   Instruct   License:apache-2.0   Llama   Model-index   Region:us   Safetensors   Sharded   Tensorflow

Granite 8B Code Instruct Parameters and Internals

LLM NameGranite 8B Code Instruct
RepositoryOpen on ๐Ÿค— 
Base Model(s)  Granite 8B Code Base   ibm-granite/granite-8b-code-base
Model Size8b
Required VRAM16.2 GB
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
Context Length4096
Model Max Length4096
Transformers Version4.41.0.dev0
Tokenizer ClassGPT2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size49152
Torch Data Typebfloat16
Granite 8B Code Instruct (ibm-granite/granite-8b-code-instruct)

Best Alternatives to Granite 8B Code Instruct

Best Alternatives
HF Rank
...a 3 8B Instruct Gradient 1048K0.51024K / 16.1 GB38344654
...struct Gradient 1048K MAC Lora0.31024K / 5.9 GB157270
...SLERP Gradient1048k OpenBioLLM0.31024K / 16.1 GB4880
... Instruct Gradient 1048K Agent0.31024K / 16.1 GB3291
Llama 3 8B Instruct 1048K0.21024K / 16.1 GB324
... V0.1.0 Llama 3 8B Instruct 1M0.21024K / 16.1 GB290
Llama 3 8B Instruct V41 1048K0.21024K / 16.1 GB133
Llama 3 8B Instruct V41 1048K1024K / 16.1 GB00
...ma3 8B 360Zhinao 360K Instruct0.2361K / 16.1 GB74
Llama 3 8B Instruct 262K0.4256K / 16.1 GB12387249
Note: green Score (e.g. "73.2") means that the model is better than ibm-granite/granite-8b-code-instruct.

Rank the Granite 8B Code Instruct 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? 34255 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024071601